[{"links":[{"url":"https://developer.nvidia.com/blog/optimizing-data-center-performance-with-ai-agents-and-the-ooda-loop-strategy/","text":"Learn more"}],"title":"Optimizing Data Center Performance with AI Agents and the OODA Loop Strategy","excerpt":"For any data center, operating large, complex GPU clusters is not for the faint of heart! There is a tremendous amount of complexity. Cooling, power, networking…","featured":false,"products":["NeMo Retriever","NIM"],"sort_key":"2|optimizing data center performance with ai agents and the ooda loop strategy","created_at":1726558200,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/develop-secure-reliable-medical-apps-with-rag-and-nvidia-nemo-guardrails/","text":"Learn more"}],"title":"Develop Secure, Reliable Medical Apps with RAG and NVIDIA NeMo Guardrails","excerpt":"Imagine an application that can sift through mountains of patient data, intelligently searching and answering questions about diagnoses, health histories…","featured":false,"products":["NeMo","NeMo Guardrails"],"sort_key":"2|develop secure, reliable medical apps with rag and nvidia nemo guardrails","created_at":1715778000,"content_type":"Blog","learning_levels":["Beginner","Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/generative-ai-agents-developer-contest-top-tips-for-getting-started/","text":"Learn more"}],"title":"Generative AI Agents Developer Contest: Top Tips for Getting Started","excerpt":"Join our contest that runs through June 17 and showcase your innovation using cutting-edge generative AI-powered applications using NVIDIA and LangChain…","featured":false,"products":["NeMo","NeMo Curator"],"sort_key":"2|generative ai agents developer contest: top tips for getting started","created_at":1716973270,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/training-localized-multilingual-llms-with-nvidia-nemo-part-2/","text":"Learn more"}],"title":"Training Localized Multilingual LLMs with NVIDIA NeMo, Part 2","excerpt":"In Part 1, we discussed how to train a monolingual tokenizer and merge it with a pretrained LLM’s tokenizer to form a multilingual tokenizer. In this post…","featured":false,"products":["NeMo","NeMo Curator","NeMo Customizer","NeMo Microservices"],"sort_key":"2|training localized multilingual llms with nvidia nemo, part 2","created_at":1715941789,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/training-localized-multilingual-llms-with-nvidia-nemo-part-1/","text":"Learn more"}],"title":"Training Localized Multilingual LLMs with NVIDIA NeMo, Part 1","excerpt":"In today’s globalized world, the ability of AI systems to understand and communicate in diverse languages is increasingly crucial. Large language models (LLMs)…","featured":false,"products":["NeMo","NeMo Curator","NeMo Microservices"],"sort_key":"2|training localized multilingual llms with nvidia nemo, part 1","created_at":1715941753,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/building-ai-agents-with-nvidia-nim-microservices-and-langchain/","text":"Learn more"}],"title":"Building AI Agents with NVIDIA NIM Microservices and LangChain","excerpt":"NVIDIA NIM, part of NVIDIA AI Enterprise, now supports tool-calling for models like Llama 3.1. It also integrates with LangChain to provide you with a…","featured":false,"products":["NeMo","NeMo Retriever","NIM"],"sort_key":"2|building ai agents with nvidia nim microservices and langchain","created_at":1723021200,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/building-a-speech-enabled-ai-virtual-assistant-with-riva-on-amazon-ec2/","text":"Learn more"}],"title":"Building a Speech-Enabled AI Virtual Assistant with NVIDIA Riva on Amazon EC2","excerpt":"\nLearn how to get started with NVIDIA Riva, a fully accelerated speech AI SDK, on AWS EC2 using Jupyter Notebooks and a sample virtual assistant application.\n\n","featured":false,"products":["Riva"],"sort_key":"2|building a speech-enabled ai virtual assistant with nvidia riva on amazon ec2","created_at":1658997000,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/enhancing-rag-applications-with-nvidia-nim/","text":"Learn more"}],"title":"Enhancing RAG Applications with NVIDIA NIM","excerpt":"The advent of large language models (LLMs) has significantly benefited the AI industry, offering versatile tools capable of generating human-like text and…","featured":false,"products":["NeMo Retriever","NIM"],"sort_key":"2|enhancing rag applications with nvidia nim","created_at":1724749200,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/enhancing-rag-pipelines-with-re-ranking/","text":"Learn more"}],"title":"Enhancing RAG Pipelines with Re-Ranking","excerpt":"In the rapidly evolving landscape of AI-driven applications, re-ranking has emerged as a pivotal technique to enhance the precision and relevance of enterprise…","featured":false,"products":["NeMo","NeMo Retriever","NIM"],"sort_key":"2|enhancing rag pipelines with re-ranking","created_at":1722330000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://www.minervacq.com/minervacq-first-to-deploy-nvidia-riva-in-energy#new_tab","text":"Learn more"}],"title":"Minerva CQ Deploys NVIDIA Riva Enterprise in the Energy Sector","excerpt":"Learn how NVIDIA Inception member Minerva CQ is using NVIDIA Riva to deliver faster, personalized experiences within a global EV charging and electric mobility company.","featured":false,"products":["Riva"],"sort_key":"2|minerva cq deploys nvidia riva enterprise in the energy sector","created_at":1656597600,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/solving-automatic-speech-recognition-deployment-challenges/","text":"Learn more"}],"title":"Solving Automatic Speech Recognition Deployment Challenges","excerpt":"Top speech recognition challenges developers face when building and deploying an ASR application and how to solve them using a speech AI-optimized workflow.","featured":false,"products":["Riva"],"sort_key":"2|solving automatic speech recognition deployment challenges","created_at":1661936400,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/build-an-enterprise-scale-multimodal-document-retrieval-pipeline-with-nvidia-nim-agent-blueprint/","text":"Learn more"}],"title":"Build an Enterprise-Scale Multimodal PDF Data Extraction Pipeline with an NVIDIA AI Blueprint","excerpt":"Trillions of PDF files are generated every year, each file likely consisting of multiple pages filled with various content types, including text, images, charts…","featured":false,"products":["NeMo","NeMo Retriever","NIM"],"sort_key":"2|build an enterprise-scale multimodal pdf data extraction pipeline with an nvidia ai blueprint","created_at":1724832000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/accelerating-oracle-database-gen-ai-workloads-with-nvidia-nim-and-nvidia-cuvs/","text":"Learn more"}],"title":"Accelerating Oracle Database Generative AI Workloads with NVIDIA NIM and NVIDIA cuVS","excerpt":"The vast majority of the world’s data remains untapped, and enterprises are looking to generate value from this data by creating the next wave of generative AI…","featured":false,"products":["CUDA","cuVS","Fleet Command","NeMo Retriever","NIM"],"sort_key":"2|accelerating oracle database generative ai workloads with nvidia nim and nvidia cuvs","created_at":1726574656,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/create-lifelike-avatars-with-ai-animation-and-speech-features-in-nvidia-ace/","text":"Learn more"}],"title":"Create Lifelike Avatars with AI Animation and Speech Features in NVIDIA ACE","excerpt":"NVIDIA today unveiled major upgrades to the NVIDIA Avatar Cloud Engine (ACE) suite of technologies, bringing enhanced realism and accessibility to AI-powered…","featured":false,"products":["Avatar Cloud Engine (ACE)","Audio2Face","NeMo","NeMo Guardrails"],"sort_key":"2|create lifelike avatars with ai animation and speech features in nvidia ace","created_at":1701698400,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/state-of-the-art-multimodal-generative-ai-model-development-with-nvidia-nemo/","text":"Learn more"}],"title":"State-of-the-Art Multimodal Generative AI Model Development with NVIDIA NeMo","excerpt":"Generative AI has rapidly evolved from text-based models to multimodal capabilities. These models perform tasks like image captioning and visual question…","featured":false,"products":["NeMo","NeMo Curator"],"sort_key":"2|state-of-the-art multimodal generative ai model development with nvidia nemo","created_at":1730880000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/customizing-neural-machine-translation-models-with-nvidia-nemo-part-2/","text":"Learn more"}],"title":"Customizing Neural Machine Translation Models with NVIDIA NeMo, Part 2","excerpt":"In the first post, we walked through the prerequisites for a neural machine translation example from English to Chinese, running the pretrained model with NeMo…","featured":false,"products":["NeMo","NeMo Curator","NeMo Evaluator"],"sort_key":"2|customizing neural machine translation models with nvidia nemo, part 2","created_at":1715595458,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-to-build-a-voice-agent-with-rag-and-safety-guardrails/","text":"Learn more"}],"title":"How to Build a Voice Agent with RAG and Safety Guardrails","excerpt":"Building an agent is more than just “call an API”—it requires stitching together retrieval, speech, safety, and reasoning components so they behave like one…","featured":false,"products":["NeMo Retriever","Nemotron"],"sort_key":"2|how to build a voice agent with rag and safety guardrails","created_at":1767621966,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/enhancing-phone-customer-service-with-asr-customization/","text":"Learn more"}],"title":"Enhancing Phone Customer Service with ASR Customization","excerpt":"At the core of understanding people correctly and having natural conversations is automatic speech recognition (ASR). To make customer-led voice assistants and…","featured":false,"products":["Riva"],"sort_key":"2|enhancing phone customer service with asr customization","created_at":1704790800,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://nvda.ws/3waljI7#new_tab","text":"Learn more"}],"title":"Event: Cybersecurity Developer Day at NVIDIA GTC 2024","excerpt":"Join us on March 20 for Cybersecurity Developer Day at GTC to gain insights on leveraging generative AI for cyber defense.","featured":false,"products":["AI Workbench","LaunchPad","Morpheus"],"sort_key":"2|event: cybersecurity developer day at nvidia gtc 2024","created_at":1709110800,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://nvda.ws/4bL7WhV#new_tab","text":"Learn more"}],"title":"Featured Cybersecurity Sessions at NVIDIA GTC 2024","excerpt":"Discover how generative AI is powering cybersecurity solutions with enhanced speed, accuracy, and scalability.","featured":false,"products":["AI Workbench","LaunchPad","Morpheus"],"sort_key":"2|featured cybersecurity sessions at nvidia gtc 2024","created_at":1707913611,"content_type":"Blog","learning_levels":["Beginner","Intermediate","Advanced"]},{"links":[{"url":"https://nvda.ws/48FJ4pR#new_tab","text":"Learn more"}],"title":"Webinar: Improve Spear Phishing Detection with AI","excerpt":"Learn how generative AI can help defend against spear phishing in this January 30 webinar.","featured":false,"products":["Morpheus"],"sort_key":"2|webinar: improve spear phishing detection with ai","created_at":1706090400,"content_type":"Blog","learning_levels":["Beginner","Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/bolstering-cybersecurity-how-large-language-models-and-generative-ai-are-transforming-digital-security/","text":"Learn more"}],"title":"Bolstering Cybersecurity: How Large Language Models and Generative AI are Transforming Digital Security","excerpt":"Identity-based attacks are on the rise, with phishing remaining the most common and second-most expensive attack vector. Some attackers are using AI to craft…","featured":false,"products":["Morpheus"],"sort_key":"2|bolstering cybersecurity: how large language models and generative ai are transforming digital security","created_at":1701046800,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/realizing-the-power-of-real-time-network-processing-with-nvidia-doca-gpunetio/","text":"Learn more"}],"title":"Realizing the Power of Real-Time Network Processing with NVIDIA DOCA GPUNetIO","excerpt":"NVIDIA DOCA GPUNetIO library can be adopted in a wide range of applications from different contexts, providing huge improvements for latency, throughput, and system...","featured":false,"products":["Aerial","BlueField DPU","ConnectX","DOCA","Morpheus"],"sort_key":"2|realizing the power of real-time network processing with nvidia doca gpunetio","created_at":1690203600,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/automate-early-security-patching-in-ci-pipelines-on-aws-using-nvidia-ai-blueprints/","text":"Learn more"}],"title":"Automate Early Security Patching in CI Pipelines on AWS Using NVIDIA AI Blueprints","excerpt":"The evolution of modern application development has led to a significant shift toward microservice-based architectures. This approach offers great flexibility…","featured":false,"products":["Morpheus","NIM"],"sort_key":"2|automate early security patching in ci pipelines on aws using nvidia ai blueprints","created_at":1733221800,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/supercharge-ransomware-detection-with-ai-enhanced-cybersecurity-solutions/","text":"Learn more"}],"title":"Supercharge Ransomware Detection with AI-Enhanced Cybersecurity Solutions","excerpt":"Ransomware attacks have become increasingly popular, more sophisticated, and harder to detect. For example, in 2022, a destructive ransomware attack took 233…","featured":false,"products":["BlueField DPU","DOCA","Morpheus"],"sort_key":"2|supercharge ransomware detection with ai-enhanced cybersecurity solutions","created_at":1694002135,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/generative-ai-and-accelerated-computing-for-spear-phishing-detection/","text":"Learn more"}],"title":"Generative AI and Accelerated Computing for Spear Phishing Detection","excerpt":"Spear phishing is the largest and most costly form of cyber threat, with an estimated 300,000 reported victims in 2021 representing $44 million in reported…","featured":false,"products":["Morpheus","NeMo Framework"],"sort_key":"2|generative ai and accelerated computing for spear phishing detection","created_at":1694516400,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/unlocking-the-power-of-enterprise-ready-llms-with-nemo/","text":"Learn more"}],"title":"Unlocking the Power of Enterprise-Ready LLMs with NVIDIA NeMo","excerpt":"Generative AI has introduced a new era in computing, one promising to revolutionize human-computer interaction. At the forefront of this technological marvel…","featured":false,"products":["NeMo","NeMo Guardrails"],"sort_key":"2|unlocking the power of enterprise-ready llms with nvidia nemo","created_at":1691494511,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://nvda.ws/3UreHhQ#new_tab","text":"Learn more"}],"title":"Upcoming Webinar: Enhance Generative AI Model Accuracy Through High-Quality Data Processing","excerpt":"Learn how to build scalable data processing pipelines to create high-quality datasets.","featured":false,"products":["NeMo","NeMo Curator"],"sort_key":"2|upcoming webinar: enhance generative ai model accuracy through high-quality data processing","created_at":1730118229,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://nvda.ws/4ePqHkD#new_tab","text":"Learn more"}],"title":"Just Released: NVIDIA NeMo Curator Improvements for Accelerating Data Curation","excerpt":"NeMo Curator now supports images, enabling you to process data for training accurate generative AI models.","featured":false,"products":["NeMo","NeMo Curator"],"sort_key":"2|just released: nvidia nemo curator improvements for accelerating data curation","created_at":1728032400,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://nvda.ws/3J7ZHzx#new_tab","text":"Learn more"}],"title":"Webinar: AI-Enabled Cybersecurity for Financial Services","excerpt":"Learn how financial firms can build automated, real-time fraud and threat detection solutions with NVIDIA Morpheus.","featured":false,"products":["Morpheus"],"sort_key":"2|webinar: ai-enabled cybersecurity for financial services","created_at":1687265642,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://nvda.ws/44L3bRZ#new_tab","text":"Learn more"}],"title":"Webinar: Cybersecurity and AI in Retail","excerpt":"Join NVIDIA on Tuesday, June 6, 2023 at 9AM PT, for a webinar on cybersecurity and AI in retail. We discuss how AI can bring a new level of information security to the...","featured":false,"products":["Morpheus"],"sort_key":"2|webinar: cybersecurity and ai in retail","created_at":1683536400,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/developers-design-innovative-network-security-solutions-at-the-nvidia-cybersecurity-hackathon/","text":"Learn more"}],"title":"Developers Design Innovative Network Security Solutions at the NVIDIA Cybersecurity Hackathon","excerpt":"The latest NVIDIA Cybersecurity Hackathon brought together 10 teams to create exciting cybersecurity innovations using the NVIDIA Morpheus cybersecurity AI…","featured":false,"products":["BlueField DPU","DOCA","Morpheus"],"sort_key":"2|developers design innovative network security solutions at the nvidia cybersecurity hackathon","created_at":1671008400,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://info.nvidia.com/detecting-cyber-threats-with-unsupervised-learning.html?nvid=nv-int-txtad-297947-vt43#cid=dl24_nv-int-txtad_en-us#new_tab","text":"Learn more"}],"title":"Upcoming Webinar: Detecting Cyber Threats with Unsupervised Learning ","excerpt":"Discover how to detect cyber threats using machine learning and NVIDIA Morpheus, an open-source AI framework. ","featured":false,"products":["BlueField DPU","EGX","Morpheus"],"sort_key":"2|upcoming webinar: detecting cyber threats with unsupervised learning","created_at":1659690000,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://info.nvidia.com/improve-your-cybersecurity-posture-with-ai.html?nvid=nv-int-tblg-746753-vt22#cid=dl24_nv-int-tblg_en-us#new_tab","text":"Learn more"}],"title":"Upcoming Event: Improve Your Cybersecurity Posture with AI","excerpt":"Find out how federal agencies are adopting AI to improve cybersecurity in this November 16 webinar featuring Booz Allen Hamilton.","featured":false,"products":["BlueField DPU","EGX","Morpheus"],"sort_key":"2|upcoming event: improve your cybersecurity posture with ai","created_at":1666794600,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://www.nvidia.com/en-us/launchpad/ai/digital-fingerprinting-to-detect-cyber-threats/#new_tab","text":"Learn more"}],"title":"Hands-on Lab: Digital Fingerprinting to Detect Cyber Threats","excerpt":"Learn how to use an NVIDIA AI workflow to uniquely fingerprint users and machines across your network in a new, free NVIDIA LaunchPad hands-on lab.","featured":false,"products":["LaunchPad","Morpheus"],"sort_key":"2|hands-on lab: digital fingerprinting to detect cyber threats","created_at":1675843200,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/nvidia-morpheus-helps-defend-against-spear-phishing-with-generative-ai/","text":"Learn more"}],"title":"NVIDIA Morpheus Helps Defend Against Spear Phishing with Generative AI","excerpt":"The NVIDIA Morpheus cybersecurity framework helps defend against spear phishing using generative AI.","featured":false,"products":["Morpheus"],"sort_key":"2|nvidia morpheus helps defend against spear phishing with generative ai","created_at":1679392253,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/from-neuroscience-to-data-science-my-road-into-cybersecurity/","text":"Learn more"}],"title":"From Neuroscience to Data Science: My Road Into Cybersecurity","excerpt":"If you asked a group of cybersecurity professionals how they got into the field, you might be surprised by the answers that you receive. With military officers…","featured":false,"products":["Morpheus"],"sort_key":"2|from neuroscience to data science: my road into cybersecurity","created_at":1678784400,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/safeguarding-networks-and-assets-with-digital-fingerprinting/","text":"Learn more"}],"title":"Safeguarding Networks and Assets with Digital Fingerprinting","excerpt":"Use of stolen or compromised credentials remains at the top of the list as the most common cause of a data breach. Because an attacker is using credentials or…","featured":false,"products":["Morpheus"],"sort_key":"2|safeguarding networks and assets with digital fingerprinting","created_at":1664960400,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/detecting-threats-faster-with-ai-based-cybersecurity/","text":"Learn more"}],"title":"Detecting Threats Faster with AI-Based Cybersecurity","excerpt":"The latest release of NVIDIA Morpheus includes new visualization capabilities enabling cybersecurity analysts to more quickly pinpoint and react to threats. ","featured":false,"products":["BlueField DPU","EGX","Morpheus"],"sort_key":"2|detecting threats faster with ai-based cybersecurity","created_at":1663846800,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/addressing-cybersecurity-in-the-enterprise-with-ai/","text":"Learn more"}],"title":"Addressing Cybersecurity in the Enterprise with AI","excerpt":"Traditional cybersecurity approaches are falling short. See how AI can help you manage risks, identify vulnerabilities, and stop breaches in your enterprise.","featured":false,"products":["Morpheus"],"sort_key":"2|addressing cybersecurity in the enterprise with ai","created_at":1660813200,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://nvda.ws/41vYE4d","text":"Learn more"}],"title":"Top Cybersecurity Sessions at NVIDIA GTC 2023","excerpt":"Learn how AI is improving your cybersecurity to detect threats faster.","featured":false,"products":["Morpheus"],"sort_key":"2|top cybersecurity sessions at nvidia gtc 2023","created_at":1677679200,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/insiders-guide-to-gtc-cybersecurity-data-center-data-science-and-networking/","text":"Learn more"}],"title":"Insider’s Guide to GTC: Cybersecurity, Data Center, Data Science, and Networking","excerpt":"Informative sessions on automated cyberattack prevention, power grid management from the edge, optimizing network storage, edge AI-on-5G, and addressing malware with...","featured":false,"products":["Morpheus","RAPIDS"],"sort_key":"2|insider’s guide to gtc: cybersecurity, data center, data science, and networking","created_at":1646907312,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/building-an-ai-agent-for-supply-chain-optimization-with-nvidia-nim-and-cuopt/","text":"Learn more"}],"title":"Building an AI Agent for Supply Chain Optimization with NVIDIA NIM and cuOpt","excerpt":"Enterprises face significant challenges in making supply chain decisions that maximize profits while adapting quickly to dynamic changes.","featured":false,"products":["cuOpt","NeMo Retriever","NIM"],"sort_key":"2|building an ai agent for supply chain optimization with nvidia nim and cuopt","created_at":1721137904,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/mitigating-stored-prompt-injection-attacks-against-llm-applications/","text":"Learn more"}],"title":"Mitigating Stored Prompt Injection Attacks Against LLM Applications","excerpt":"Explore how information retrieval systems may be used to perpetrate prompt injection attacks and how application developers can mitigate this risk.","featured":false,"products":["General","NeMo Guardrails"],"sort_key":"2|mitigating stored prompt injection attacks against llm applications","created_at":1691139950,"content_type":"Blog","learning_levels":["Beginner","Intermediate"]},{"links":[{"url":"https://info.nvidia.com/rethinking-zero-trust-an-ai-based-approach-to-cybersecurity.html?nvid=nv-int-txtad-883906-vt43#cid=dl24_nv-int-txtad_en-us#new_tab","text":"Learn more"}],"title":"Upcoming Event: Rethinking Zero-Trust: An AI-Based Approach to Cybersecurity","excerpt":"Join us on May 26 to learn how you can leverage accelerated AI frameworks to build high performance zero-trust solutions with reduced friction and fewer lines of code.","featured":false,"products":["BlueField DPU","EGX","Morpheus"],"sort_key":"2|upcoming event: rethinking zero-trust: an ai-based approach to cybersecurity","created_at":1652691600,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/reallusion-brings-digital-characters-to-life-with-nvidia-ai/","text":"Learn more"}],"title":"Reallusion Brings Digital Characters to Life with NVIDIA AI","excerpt":"In today’s digital age, creating realistic animated characters is crucial for filmmakers, game developers, and content creators looking to bring their visions…","featured":false,"products":["Maxine"],"sort_key":"2|reallusion brings digital characters to life with nvidia ai","created_at":1718020773,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/video-talk-to-your-supply-chain-data-using-nvidia-nim/","text":"Learn more"}],"title":"Video: Talk to Your Supply Chain Data Using NVIDIA NIM","excerpt":"NVIDIA operates one of the largest and most complex supply chains in the world. The supercomputers we build connect tens of thousands of NVIDIA GPUs with…","featured":false,"products":["cuOpt","NeMo","NeMo Microservices","NeMo Retriever","NIM"],"sort_key":"2|video: talk to your supply chain data using nvidia nim","created_at":1718626409,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/supercharging-ai-accelerated-cybersecurity-threat-detection/","text":"Learn more"}],"title":"Supercharging AI-Accelerated Cybersecurity Threat Detection","excerpt":"NVIDIA Morpheus, now available for download, enables you to use AI to achieve up to 1000x improved performance.","featured":false,"products":["BlueField DPU","EGX","Morpheus"],"sort_key":"2|supercharging ai-accelerated cybersecurity threat detection","created_at":1648022460,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/improving-enterprise-it-fraud-prevention/","text":"Learn more"}],"title":"Improving Enterprise IT Fraud Prevention","excerpt":"This post discusses infrastructure factors to consider, such as performance, hardware, and types of AI software for implementing a fraud prevention strategy.","featured":false,"products":["Morpheus"],"sort_key":"2|improving enterprise it fraud prevention","created_at":1656489600,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/designing-a-new-net-for-phishing-detection-with-nvidia-morpheus/","text":"Learn more"}],"title":"Designing a New Net for Phishing Detection with NVIDIA Morpheus","excerpt":"With NVIDIA Morpheus, now available for download, you can achieve up to 99% accuracy for phishing detection, using AI.","featured":false,"products":["Morpheus"],"sort_key":"2|designing a new net for phishing detection with nvidia morpheus","created_at":1652697379,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/enhancing-zero-trust-security-with-data/","text":"Learn more"}],"title":"Enhancing Zero Trust Security with Data","excerpt":"This post discusses how a thoughtful cybersecurity team can structure a zero-trust system that keeps users and data safe, and maintain a seamless user experience.","featured":false,"products":["Morpheus"],"sort_key":"2|enhancing zero trust security with data","created_at":1652787788,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://catalog.ngc.nvidia.com/orgs/nvidia/teams/riva/models/punctuationcapitalization_en_us_bert_base","text":"Learn more"}],"title":"RIVA Punctuation and Capitalization for English","excerpt":"For each word in the input text, the model: 1) predicts a punctuation mark that should follow the word (if any), the model supports commas, periods and question marks) and 2) predicts if the word should be capitalized or not.","featured":false,"products":["Riva"],"sort_key":"2|riva punctuation and capitalization for english","created_at":1751575822,"content_type":"Model","learning_levels":["Advanced"]},{"links":[{"url":"https://nvda.ws/3P8tOKc%20#new_tab","text":"Learn more"}],"title":"Top Video Streaming and Conferencing Sessions at NVIDIA GTC 2024","excerpt":"Learn how AI and NVIDIA Maxine are transforming the video streaming and conferencing industry.","featured":false,"products":["Maxine"],"sort_key":"2|top video streaming and conferencing sessions at nvidia gtc 2024","created_at":1709824255,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://catalog.ngc.nvidia.com/orgs/nvidia/teams/riva/models/speechtotext_es_us_conformer","text":"Learn more"}],"title":"RIVA Conformer ASR Spanish - ASR set 3.0","excerpt":"Spanish Conformer ASR model trained on ASR set 3.0","featured":false,"products":["Riva"],"sort_key":"2|riva conformer asr spanish - asr set 3.0","created_at":1743693488,"content_type":"Model","learning_levels":["Advanced"]},{"links":[{"url":"https://catalog.ngc.nvidia.com/orgs/nvidia/teams/riva/models/speechtotext_en_us_conformer","text":"Learn more"}],"title":"RIVA Conformer ASR English - ASR set 6.0","excerpt":"English Conformer ASR model trained on ASR set 6.0","featured":false,"products":["Riva"],"sort_key":"2|riva conformer asr english - asr set 6.0","created_at":1743692919,"content_type":"Model","learning_levels":["Advanced"]},{"links":[{"url":"https://catalog.ngc.nvidia.com/orgs/nvidia/teams/riva/models/speechtotext_en_us_citrinet","text":"Learn more"}],"title":"RIVA Citrinet ASR English en-US","excerpt":"English en-US Citrinet ASR model trained on RIVA ASR set","featured":false,"products":["Riva"],"sort_key":"2|riva citrinet asr english en-us","created_at":1680635131,"content_type":"Model","learning_levels":["Advanced"]},{"links":[{"url":"https://catalog.ngc.nvidia.com/orgs/nvidia/teams/riva/models/speechtotext_ja_jp_conformer","text":"Learn more"}],"title":"RIVA Conformer ASR Japanese","excerpt":"Japanese Conformer ASR model trained on RIVA ASR set","featured":false,"products":["Riva"],"sort_key":"2|riva conformer asr japanese","created_at":1743693535,"content_type":"Model","learning_levels":["Advanced"]},{"links":[{"url":"https://catalog.ngc.nvidia.com/orgs/nvidia/teams/riva/models/speechtotext_ar_ar_conformer","text":"Learn more"}],"title":"RIVA Conformer ASR Arabic","excerpt":"Arabic (ar-AR) Conformer ASR model trained on ASR set 2.0","featured":false,"products":["Riva"],"sort_key":"2|riva conformer asr arabic","created_at":1743693189,"content_type":"Model","learning_levels":["Advanced"]},{"links":[{"url":"https://catalog.ngc.nvidia.com/orgs/nvidia/teams/riva/models/speechtotext_ru_ru_conformer","text":"Learn more"}],"title":"RIVA Conformer ASR Russian","excerpt":"Russian Conformer ASR model trained on RIVA ASR set","featured":false,"products":["Riva"],"sort_key":"2|riva conformer asr russian","created_at":1743693565,"content_type":"Model","learning_levels":["Advanced"]},{"links":[{"url":"https://catalog.ngc.nvidia.com/orgs/nvidia/teams/riva/models/speechtotext_hi_in_conformer","text":"Learn more"}],"title":"RIVA Conformer ASR Hindi","excerpt":"Hindi Conformer ASR model trained on RIVA ASR set","featured":false,"products":["Riva"],"sort_key":"2|riva conformer asr hindi","created_at":1743693434,"content_type":"Model","learning_levels":["Advanced"]},{"links":[{"url":"https://catalog.ngc.nvidia.com/orgs/nvidia/teams/riva/models/speechtotext_en_us_lm","text":"Learn more"}],"title":"Riva ASR English LM","excerpt":"Base English n-gram LM trained on LibriSpeech, Switchboard and Fisher","featured":false,"products":["Riva"],"sort_key":"2|riva asr english lm","created_at":1719943458,"content_type":"Model","learning_levels":["Advanced"]},{"links":[{"url":"https://developer.nvidia.com/blog/quickly-voice-your-apps-with-nvidia-nim-microservices-for-speech-and-translation/","text":"Learn more"}],"title":"Quickly Voice Your Apps with NVIDIA NIM Microservices for Speech and Translation","excerpt":"NVIDIA NIM, part of NVIDIA AI Enterprise, provides containers to self-host GPU-accelerated inferencing microservices for pretrained and customized AI models…","featured":false,"products":["NIM","Riva"],"sort_key":"2|quickly voice your apps with nvidia nim microservices for speech and translation","created_at":1726674523,"content_type":"Blog","learning_levels":["Intermediate","Advanced"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-to-take-a-rag-application-from-pilot-to-production-in-four-steps/","text":"Learn more"}],"title":"How to Take a RAG Application from Pilot to Production in Four Steps","excerpt":"Generative AI has the potential to transform every industry. Human workers are already using large language models (LLMs) to explain, reason about…","featured":false,"products":["AI Enterprise","Metropolis","Morpheus","NeMo","NeMo Microservices","NeMo Retriever","NIM","RAPIDS","Riva"],"sort_key":"2|how to take a rag application from pilot to production in four steps","created_at":1710774000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/spotlight-convai-reinvents-non-playable-character-interactions/","text":"Learn more"}],"title":"Spotlight: Convai Reinvents Non-Playable Character Interactions","excerpt":"Convai is a versatile developer platform for designing characters with advanced multimodal perception abilities. These characters are designed to integrate…","featured":false,"products":["AI Enterprise","Avatar Cloud Engine (ACE)","Audio2Face","NeMo","Omniverse","Riva","Triton Inference Server","Dynamo"],"sort_key":"2|spotlight: convai reinvents non-playable character interactions","created_at":1704702600,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/nvidia-speech-and-translation-ai-models-set-records-for-speed-and-accuracy/","text":"Learn more"}],"title":"NVIDIA Speech and Translation AI Models Set Records for Speed and Accuracy","excerpt":"Speech and translation AI models developed at NVIDIA are pushing the boundaries of performance and innovation. The NVIDIA Parakeet automatic speech recognition…","featured":false,"products":["LaunchPad","Riva"],"sort_key":"2|nvidia speech and translation ai models set records for speed and accuracy","created_at":1710838800,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/video-exploring-speech-ai-from-research-to-practical-production-applications/","text":"Learn more"}],"title":"Video: Exploring Speech AI from Research to Practical Production Applications","excerpt":"The integration of speech and translation AI into our daily lives is rapidly reshaping our interactions, from virtual assistants to call centers and augmented…","featured":false,"products":["Riva"],"sort_key":"2|video: exploring speech ai from research to practical production applications","created_at":1699344442,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-to-deploy-riva-speech-and-translation-ai-in-the-public-cloud/","text":"Learn more"}],"title":"How to Deploy NVIDIA Riva Speech and Translation AI in the Public Cloud","excerpt":"From start-ups to large enterprises, businesses use cloud marketplaces to find the new solutions needed to quickly transform their businesses.","featured":false,"products":["Riva"],"sort_key":"2|how to deploy nvidia riva speech and translation ai in the public cloud","created_at":1693303200,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/experience-real-time-audio-and-video-communication-with-nvidia-maxine/","text":"Learn more"}],"title":"Experience Real-Time Audio and Video Communication with NVIDIA Maxine ","excerpt":"NVIDIA Maxine Live Portrait webpage as seen on NVIDIA AI Foundation Models.","featured":false,"products":["Maxine"],"sort_key":"2|experience real-time audio and video communication with nvidia maxine","created_at":1704884400,"content_type":"Blog","learning_levels":["General Interest","Beginner"]},{"links":[{"url":"https://nvda.ws/48oZgfp#new_tab","text":"Learn more"}],"title":"Workshop: Building Conversational AI Applications","excerpt":"Learn how to build and deploy production-quality conversational AI apps with real-time transcription and NLP.","featured":false,"products":["NeMo Framework","Riva"],"sort_key":"2|workshop: building conversational ai applications","created_at":1695204000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://catalog.ngc.nvidia.com/orgs/nvidia/teams/riva/models/speechtotext_pt_br_conformer","text":"Learn more"}],"title":"RIVA Conformer ASR Brazilian Portuguese","excerpt":"Brazilian Portuguese (pt-BR) Conformer ASR model trained on ASR set 1.0","featured":false,"products":["Riva"],"sort_key":"2|riva conformer asr brazilian portuguese","created_at":1743693798,"content_type":"Model","learning_levels":["Advanced"]},{"links":[{"url":"https://catalog.ngc.nvidia.com/orgs/nvidia/teams/riva/containers/riva-speech","text":"Learn more"}],"title":"Riva Speech Skills","excerpt":"Riva Speech Skills is a scalable Conversational AI service platform.","featured":false,"products":["Riva"],"sort_key":"2|riva speech skills","created_at":1781627928,"content_type":"Container","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-speech-recognition-improves-customer-service-in-telecommunications/","text":"Learn more"}],"title":"How Speech Recognition Improves Customer Service in Telecommunications","excerpt":"The telecommunication industry has seen a proliferation of AI-powered technologies in recent years, with speech recognition and translation leading the charge.","featured":false,"products":["NeMo Framework","Riva"],"sort_key":"2|how speech recognition improves customer service in telecommunications","created_at":1683018000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/speech-ai-spotlight-visualizing-spoken-language-and-sounds-on-ar-glasses/","text":"Learn more"}],"title":"Speech AI Spotlight: Visualizing Spoken Language and Sounds on AR Glasses","excerpt":"Audio can include a wide range of sounds, from human speech to non-speech sounds like barking dogs and sirens. When designing accessible applications for people…","featured":false,"products":["Riva"],"sort_key":"2|speech ai spotlight: visualizing spoken language and sounds on ar glasses","created_at":1687507200,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://nvda.ws/3VbKm5I#new_tab","text":"Learn more"}],"title":"Webinar: Empower Telco Contact Center Agents with Multi-Language Speech-AI-Customized Agent Assists","excerpt":"Join Infosys, NVIDIA and Quantiphi on June 7 to learn how to use speech and translation AI to improve agent assist solutions in multiple languages.","featured":false,"products":["Riva"],"sort_key":"2|webinar: empower telco contact center agents with multi-language speech-ai-customized agent assists","created_at":1684227600,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/unlocking-speech-ai-technology-for-global-language-users-top-qas/","text":"Learn more"}],"title":"Unlocking Speech AI Technology for Global Language Users: Top Q\u0026As","excerpt":"This post summarizes the top questions asked during Unlocking Speech AI Technology for Global Language Users, a recorded talk from the Speech AI Summit 2022.","featured":false,"products":["NeMo Framework","Riva"],"sort_key":"2|unlocking speech ai technology for global language users: top q\u0026as","created_at":1686045600,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/create-xr-experiences-using-natural-language-voice-commands-test-project-mellon/","text":"Learn more"}],"title":"Create XR Experiences Using Natural-Language Voice Commands: Test Project Mellon","excerpt":"At GTC 2023, NVIDIA announced that developers can start testing Project Mellon to explore creating hands-free extended reality (XR) experiences controlled by...","featured":false,"products":["Riva"],"sort_key":"2|create xr experiences using natural-language voice commands: test project mellon","created_at":1679558400,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://nvda.ws/3EOo4QR#new_tab","text":"Learn more"}],"title":"Top Video Streaming and Conferencing Sessions at NVIDIA GTC 2023","excerpt":"Learn about advancements in video conferencing that have transformed how we communicate.","featured":false,"products":["Maxine","Riva"],"sort_key":"2|top video streaming and conferencing sessions at nvidia gtc 2023","created_at":1677834000,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://nvda.ws/3onruEu#new_tab","text":"Learn more"}],"title":"Workshop: How to Enable Your Product with Voice Interface","excerpt":"This hands-on workshop will guide you through the process of voice-enabling your product, from familiarizing yourself with NVIDIA Riva to assessing the costs and...","featured":false,"products":["Riva"],"sort_key":"2|workshop: how to enable your product with voice interface","created_at":1681896548,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://nvda.ws/3LCd3po#new_tab","text":"Learn more"}],"title":"Webinar: How Telcos Transform Customer Experiences with Conversational AI","excerpt":"Join Infosys, Quantiphi, Talkmap, and NVIDIA on May 31 for a live webinar to learn how telecommunications companies are using AI to improve operational efficiency and...","featured":false,"products":["Riva"],"sort_key":"2|webinar: how telcos transform customer experiences with conversational ai","created_at":1683018000,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://nvda.ws/448NHGO#new_tab","text":"Learn more"}],"title":"Explainer: What Is Agent Assist?","excerpt":"Agent-assist technology uses AI and ML to provide facts and make real-time suggestions that help human agents across retail, telecom, and other industries conduct...","featured":false,"products":["Riva"],"sort_key":"2|explainer: what is agent assist?","created_at":1683198000,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://nvda.ws/41sYdaR#new_tab","text":"Learn more"}],"title":"Top Conversational AI Sessions at NVIDIA GTC 2023","excerpt":"Learn about the latest tools, trends, and technologies for building and deploying conversational AI.","featured":false,"products":["NeMo Framework","Riva"],"sort_key":"2|top conversational ai sessions at nvidia gtc 2023","created_at":1677583827,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/autoscaling-nvidia-riva-deployment-with-kubernetes-for-speech-ai-in-production/","text":"Learn more"}],"title":"Autoscaling NVIDIA Riva Deployment with Kubernetes for Speech AI in Production","excerpt":"Learn how to deploy NVIDIA Riva servers on a large scale with Kubernetes for autoscaling and Traefik for load balancing.\n","featured":false,"products":["Riva","Triton Inference Server","Dynamo"],"sort_key":"2|autoscaling nvidia riva deployment with kubernetes for speech ai in production","created_at":1673515800,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/speech-ai-spotlight-how-pendulum-nabs-harmful-narratives-online/","text":"Learn more"}],"title":"Speech AI Spotlight: How Pendulum Nabs Harmful Narratives Online","excerpt":"Over 55% of the global population uses social media, easily sharing online content with just one click. While connecting with others and consuming entertaining…","featured":false,"products":["Riva","Triton Inference Server","Dynamo"],"sort_key":"2|speech ai spotlight: how pendulum nabs harmful narratives online","created_at":1675846800,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/reducing-development-time-for-intelligent-virtual-assistants-in-contact-centers/","text":"Learn more"}],"title":"Reducing Development Time for Intelligent Virtual Assistants in Contact Centers","excerpt":"As the global service economy grows, companies rely increasingly on contact centers to drive better customer experiences, increase customer satisfaction…","featured":false,"products":["Riva"],"sort_key":"2|reducing development time for intelligent virtual assistants in contact centers","created_at":1671091200,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://info.nvidia.com/ai-virtual-assistant-for-finance-contact-centers-webinar.html#new_tab","text":"Learn more"}],"title":"Upcoming Webinar: Building an Intelligent Virtual Assistant for Financial Services","excerpt":"Join this webinar on January 25 and learn how to build a voice-enabled intelligent virtual assistant to improve customer experiences at contact centers.","featured":false,"products":["Riva"],"sort_key":"2|upcoming webinar: building an intelligent virtual assistant for financial services","created_at":1673427600,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/making-an-nvidia-riva-asr-service-for-a-new-language/","text":"Learn more"}],"title":"Making an NVIDIA Riva ASR Service for a New Language","excerpt":"NVIDIA Riva facilitates the process of creating ASR services with the tools and methodologies to help you realize your skills, all the way from raw data to a...","featured":false,"products":["Riva"],"sort_key":"2|making an nvidia riva asr service for a new language","created_at":1666951200,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://courses.nvidia.com/courses/course-v1:DLI+S-FX-04+V1/?nvid=nv-int-tblg-973505#cid=dli03_nv-int-tblg_en-us#new_tab","text":"Learn more"}],"title":"New Course: Get Started with Highly Accurate Custom ASR for Speech AI","excerpt":"Learn how to build, train, customize, and deploy a GPU-accelerated automatic speech recognition service with NVIDIA Riva in this self-paced course.","featured":false,"products":["Riva"],"sort_key":"2|new course: get started with highly accurate custom asr for speech ai","created_at":1666603800,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/speech-ai-technology-enables-natural-interactions-with-service-robots/","text":"Learn more"}],"title":"Speech AI Technology Enables Natural Interactions with Service Robots","excerpt":"From taking your order and serving you food in a restaurant to playing poker with you, service robots are becoming increasingly prevalent. Globally…","featured":false,"products":["Riva"],"sort_key":"2|speech ai technology enables natural interactions with service robots","created_at":1671207787,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://www.nvidia.com/en-us/launchpad/ai/intelligent-virtual-assistant/#new_tab","text":"Learn more"}],"title":"New Hands-on Lab: Intelligent Virtual Assistant","excerpt":"Learn to build an engaging and intelligent virtual assistant with NVIDIA AI workflows powered by NVIDIA Riva in this free hands-on lab from NVIDIA LaunchPad…","featured":false,"products":["LaunchPad","Riva"],"sort_key":"2|new hands-on lab: intelligent virtual assistant","created_at":1674565200,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://nvda.ws/3jRS331#new_tab","text":"Learn more"}],"title":"Top Speech AI Developer Day Sessions at NVIDIA GTC 2023","excerpt":"Explore the latest advances in accurate and customizable automatic speech recognition, multi-language translation, and text-to-speech.","featured":false,"products":["Riva"],"sort_key":"2|top speech ai developer day sessions at nvidia gtc 2023","created_at":1676383200,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/riva/getting-started#new_tab","text":"Learn more"}],"title":"Just Released: New Updates to NVIDIA Riva","excerpt":"Build better GPU-accelerated Speech AI applications with the latest NVIDIA Riva updates, including enterprise support.","featured":false,"products":["Riva"],"sort_key":"2|just released: new updates to nvidia riva","created_at":1664186400,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/transforming-telco-network-operations-centers-with-nvidia-nemo-retriever-and-nvidia-nim/","text":"Learn more"}],"title":"Transforming Telco Network Operations Centers with NVIDIA NeMo Retriever and NVIDIA NIM","excerpt":"Telecom companies are challenged with consistently meeting service level agreements (SLAs) for end customers that ensure network quality of service.","featured":false,"products":["NeMo","NeMo Guardrails","NeMo Retriever","NIM"],"sort_key":"2|transforming telco network operations centers with nvidia nemo retriever and nvidia nim","created_at":1721714400,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/customize-generative-ai-models-for-enterprise-applications-with-llama-3-1/","text":"Learn more"}],"title":"Customize Generative AI Models for Enterprise Applications with Llama 3.1","excerpt":"The newly unveiled Llama 3.1 collection of 8B, 70B, and 405B large language models (LLMs) is narrowing the gap between proprietary and open-source models.","featured":false,"products":["NeMo","NeMo Curator","NeMo Customizer","NeMo Evaluator","NeMo Guardrails","NeMo Retriever","NIM"],"sort_key":"2|customize generative ai models for enterprise applications with llama 3.1","created_at":1721722500,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/build-an-agentic-rag-pipeline-with-llama-3-1-and-nvidia-nemo-retriever-nims/","text":"Learn more"}],"title":"Build an Agentic RAG Pipeline with Llama 3.1 and NVIDIA NeMo Retriever NIMs","excerpt":"Employing retrieval-augmented generation (RAG) is an effective strategy for ensuring large language model (LLM) responses are up-to-date and not hallucinated.","featured":false,"products":["NeMo","NeMo Microservices","NeMo Retriever","NIM"],"sort_key":"2|build an agentic rag pipeline with llama 3.1 and nvidia nemo retriever nims","created_at":1721722500,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/new-languages-enhanced-cybersecurity-and-medical-ai-frameworks-unveiled-at-gtc/","text":"Learn more"}],"title":"New Languages, Enhanced Cybersecurity, and Medical AI Frameworks Unveiled at GTC","excerpt":"Major updates to AI frameworks for building real-time speech AI apps, designing high-performing recommenders at scale, applying AI to cybersecurity challenges, and...","featured":false,"products":["BioNeMo","Clara Holoscan","cuOpt","DRIVE","Isaac SDK","Maxine","Merlin","Metropolis","MONAI","Morpheus","NeMo Framework","Riva","Triton Inference Server","Dynamo"],"sort_key":"2|new languages, enhanced cybersecurity, and medical ai frameworks unveiled at gtc","created_at":1663748280,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/deliver-personalized-retail-experiences-with-an-ai-powered-shopping-advisor/","text":"Learn more"}],"title":"Deliver Personalized Retail Experiences with an AI-Powered Shopping Advisor","excerpt":"Imagine being able to put your best sales associate in front of every customer for every interaction. Your best sales associate offers product recommendations…","featured":false,"products":["NGC","NeMo","NeMo Retriever","NIM"],"sort_key":"2|deliver personalized retail experiences with an ai-powered shopping advisor","created_at":1722514132,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/accelerating-inference-on-end-to-end-workflows-with-h2o-ai-and-nvidia/","text":"Learn more"}],"title":"Accelerating Inference on End-to-End Workflows with H2O.ai and NVIDIA","excerpt":"Data scientists are combining generative AI and predictive analytics to build the next generation of AI applications. In financial services…","featured":false,"products":["NeMo Guardrails","NeMo Retriever","RAPIDS","Triton Inference Server","Dynamo"],"sort_key":"2|accelerating inference on end-to-end workflows with h2o.ai and nvidia","created_at":1704348000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/automating-telco-network-design-using-nvidia-nim-and-nvidia-nemo/","text":"Learn more"}],"title":"Automating Telco Network Design using NVIDIA NIM and NVIDIA NeMo","excerpt":"Telecom wireless network design demands streamlined processes and standardized approaches. Network architects, engineers, and IT professionals are challenged…","featured":false,"products":["NeMo","NeMo Guardrails","NeMo Retriever","NIM"],"sort_key":"2|automating telco network design using nvidia nim and nvidia nemo","created_at":1721714400,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/a-deep-dive-into-the-latest-ai-models-optimized-with-nvidia-nim/","text":"Learn more"}],"title":"A Deep Dive into the Latest AI Models Optimized with NVIDIA NIM","excerpt":"Delivered as optimized containers, NVIDIA NIM microservices are designed to accelerate AI application development for businesses of all sizes…","featured":false,"products":["NeMo Retriever","NIM"],"sort_key":"2|a deep dive into the latest ai models optimized with nvidia nim","created_at":1722934800,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/supercharging-llama-3-1-across-nvidia-platforms/","text":"Learn more"}],"title":"Supercharging Llama 3.1 across NVIDIA Platforms","excerpt":"Meta’s Llama collection of large language models are the most popular foundation models in the open-source community today, supporting a variety of use cases.","featured":false,"products":["AI Enterprise","AI Foundation Models","NeMo Curator","NeMo Evaluator","NeMo Guardrails","NeMo Retriever","NIM","TensorRT"],"sort_key":"2|supercharging llama 3.1 across nvidia platforms","created_at":1721722500,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/developing-the-next-generation-of-extended-reality-applications-with-speech-ai/","text":"Learn more"}],"title":"Developing the Next Generation of Extended Reality Applications with Speech AI","excerpt":"Technical tutorial for extended reality (XR) developers adding speech AI skills, like ASR and TTS, to AR/VR/MR applications using Riva SDK as an example.","featured":false,"products":["CloudXR","Riva"],"sort_key":"2|developing the next generation of extended reality applications with speech ai","created_at":1663146000,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/three-building-blocks-for-creating-ai-virtual-assistants-for-customer-service-with-an-nvidia-nim-agent-blueprint/","text":"Learn more"}],"title":"Three Building Blocks for Creating AI Virtual Assistants for Customer Service with an NVIDIA AI Blueprint","excerpt":"In today’s fast-paced business environment, providing exceptional customer service is no longer just a nice-to-have—it’s a necessity.","featured":false,"products":["NeMo","NeMo Microservices","NeMo Retriever","NIM"],"sort_key":"2|three building blocks for creating ai virtual assistants for customer service with an nvidia ai blueprint","created_at":1733932156,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/develop-multilingual-and-cross-lingual-information-retrieval-systems-with-efficient-data-storage/","text":"Learn more"}],"title":"Develop Multilingual and Cross-Lingual Information Retrieval Systems with Efficient Data Storage","excerpt":"Efficient text retrieval is critical for a broad range of information retrieval applications such as search, question answering, semantic textual similarity…","featured":false,"products":["NeMo Retriever","NIM"],"sort_key":"2|develop multilingual and cross-lingual information retrieval systems with efficient data storage","created_at":1734422400,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/advanced-rag-techniques-for-telco-o-ran-specifications-using-nvidia-nim-microservices/","text":"Learn more"}],"title":"Advanced RAG Techniques for Telco O-RAN Specifications Using NVIDIA NIM Microservices","excerpt":"Mobile communication standards play a crucial role in the telecommunications ecosystem by harmonizing technology protocols to facilitate interoperability…","featured":false,"products":["NeMo","NeMo Guardrails","NeMo Retriever","NIM"],"sort_key":"2|advanced rag techniques for telco o-ran specifications using nvidia nim microservices","created_at":1728554081,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/expanding-ai-agent-interface-options-with-2d-and-3d-digital-human-avatars/","text":"Learn more"}],"title":"Expanding AI Agent Interface Options with 2D and 3D Digital Human Avatars","excerpt":"When interfacing with generative AI applications, users have multiple communication options—text, voice, or through digital avatars.","featured":false,"products":["Avatar Cloud Engine (ACE)","Audio2Face","NeMo Microservices","NeMo Retriever","NIM","NIM Agent Blueprint","Omniverse","Riva"],"sort_key":"2|expanding ai agent interface options with 2d and 3d digital human avatars","created_at":1731516803,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/build-a-digital-human-interface-for-ai-apps-with-an-nvidia-nim-agent-blueprint/","text":"Learn more"}],"title":"Build a Digital Human Interface for AI Apps with an NVIDIA NIM Agent Blueprint","excerpt":"Providing customers with quality service remains a top priority for businesses across industries, from answering questions and troubleshooting issues to…","featured":false,"products":["AI Enterprise","Avatar Cloud Engine (ACE)","NIM","Riva"],"sort_key":"2|build a digital human interface for ai apps with an nvidia nim agent blueprint","created_at":1727271000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/datastax-announces-new-ai-development-platform-built-with-nvidia-ai/","text":"Learn more"}],"title":"DataStax Announces New AI Development Platform, Built with NVIDIA AI","excerpt":"As enterprises increasingly adopt AI technologies, they face a complex challenge of efficiently developing, securing, and continuously improving AI applications…","featured":false,"products":["AI Enterprise","NeMo","NeMo Curator","NeMo Customizer","NeMo Evaluator","NeMo Guardrails","NeMo Microservices","NeMo Retriever","NIM"],"sort_key":"2|datastax announces new ai development platform, built with nvidia ai","created_at":1728972000,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/an-easy-introduction-to-multimodal-retrieval-augmented-generation-for-video-and-audio/","text":"Learn more"}],"title":"An Easy Introduction to Multimodal Retrieval-Augmented Generation for Video and Audio","excerpt":"Building a multimodal retrieval-augmented generation (RAG) system is challenging. The difficulty comes from capturing and indexing information from across…","featured":false,"products":["Riva"],"sort_key":"2|an easy introduction to multimodal retrieval-augmented generation for video and audio","created_at":1734339600,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/nvidia-ai-foundation-models-build-custom-enterprise-chatbots-and-co-pilots-with-production-ready-llms/","text":"Learn more"}],"title":"NVIDIA AI Foundation Models: Build Custom Enterprise Chatbots and Co-Pilots with Production-Ready LLMs","excerpt":"Large language models (LLMs) are revolutionizing data science, enabling advanced capabilities in natural language understanding, AI, and machine learning.","featured":false,"products":["NeMo Guardrails"],"sort_key":"2|nvidia ai foundation models: build custom enterprise chatbots and co-pilots with production-ready llms","created_at":1700035200,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/content-moderation-and-safety-checks-with-nvidia-nemo-guardrails/","text":"Learn more"}],"title":"Content Moderation and Safety Checks with NVIDIA NeMo Guardrails","excerpt":"Content moderation has become essential in retrieval-augmented generation (RAG) applications powered by generative AI, given the extensive volume of user…","featured":false,"products":["NeMo Guardrails","NIM"],"sort_key":"2|content moderation and safety checks with nvidia nemo guardrails","created_at":1733477031,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/streamline-generative-ai-development-with-nvidia-nemo-on-gpu-accelerated-google-cloud/","text":"Learn more"}],"title":"Streamline Generative AI Development with NVIDIA NeMo on GPU-Accelerated Google Cloud","excerpt":"Generative AI has become a transformative force of our era, empowering organizations spanning every industry to achieve unparalleled levels of productivity…","featured":false,"products":["NeMo Guardrails"],"sort_key":"2|streamline generative ai development with nvidia nemo on gpu-accelerated google cloud","created_at":1693303200,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/augmenting-security-operations-centers-with-accelerated-alert-triage-and-llm-agents-using-nvidia-morpheus/","text":"Learn more"}],"title":"Augmenting Security Operations Centers with Accelerated Alert Triage and LLM Agents Using NVIDIA Morpheus","excerpt":"Every day, security operation center (SOC) analysts receive an overwhelming amount of incoming security alerts. To ensure the continued safety of their…","featured":false,"products":["Morpheus","NeMo Retriever"],"sort_key":"2|augmenting security operations centers with accelerated alert triage and llm agents using nvidia morpheus","created_at":1729767736,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/rapidly-triage-container-security-with-the-vulnerability-analysis-nvidia-nim-agent-blueprint/","text":"Learn more"}],"title":"Rapidly Triage Container Security with the Vulnerability Analysis NVIDIA NIM Agent Blueprint","excerpt":"Addressing software security issues is becoming more challenging as the number of vulnerabilities reported in the CVE database continues to grow at an…","featured":false,"products":["Morpheus","NIM"],"sort_key":"2|rapidly triage container security with the vulnerability analysis nvidia nim agent blueprint","created_at":1728374400,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/curating-custom-datasets-for-llm-parameter-efficient-fine-tuning-with-nvidia-nemo-curator/","text":"Learn more"}],"title":"Curating Custom Datasets for LLM Parameter-Efficient Fine-Tuning with NVIDIA NeMo Curator","excerpt":"In a recent post, we discussed how to use NVIDIA NeMo Curator to curate custom datasets for pretraining or continuous training use cases of large language…","featured":false,"products":["NeMo","NeMo Curator"],"sort_key":"2|curating custom datasets for llm parameter-efficient fine-tuning with nvidia nemo curator","created_at":1722416400,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/supercharging-fraud-detection-in-financial-services-with-graph-neural-networks/","text":"Learn more"}],"title":"Supercharging Fraud Detection in Financial Services with Graph Neural Networks (Updated)","excerpt":"Note: This blog post was originally published on Oct. 28, 2024, but has been edited to reflect new updates. Fraud in financial services is a massive problem.","featured":false,"products":["AI Enterprise","Morpheus","RAPIDS"],"sort_key":"2|supercharging fraud detection in financial services with graph neural networks (updated)","created_at":1748905200,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/streamlining-data-processing-for-domain-adaptive-pretraining-with-nvidia-nemo-curator/","text":"Learn more"}],"title":"Streamlining Data Processing for Domain Adaptive Pretraining with NVIDIA NeMo Curator","excerpt":"Domain-adaptive pretraining (DAPT) of large language models (LLMs) is an important step towards building domain-specific models.","featured":false,"products":["NeMo","NeMo Curator"],"sort_key":"2|streamlining data processing for domain adaptive pretraining with nvidia nemo curator","created_at":1725960600,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/processing-high-quality-vietnamese-language-data-with-nvidia-nemo-curator/","text":"Learn more"}],"title":"Processing High-Quality Vietnamese Language Data with NVIDIA NeMo Curator","excerpt":"Open-source large language models (LLMs) excel in English but struggle with other languages, especially the languages of Southeast Asia. This is primarily due…","featured":false,"products":["NeMo","NeMo Curator"],"sort_key":"2|processing high-quality vietnamese language data with nvidia nemo curator","created_at":1732021453,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/curating-non-english-datasets-for-llm-training-with-nvidia-nemo-curator/","text":"Learn more"}],"title":"Curating Non-English Datasets for LLM Training with NVIDIA NeMo Curator","excerpt":"Data curation plays a crucial role in the development of effective and fair large language models (LLMs). High-quality, diverse training data directly impacts…","featured":false,"products":["NeMo","NeMo Curator"],"sort_key":"2|curating non-english datasets for llm training with nvidia nemo curator","created_at":1720602000,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/curating-custom-datasets-for-llm-training-with-nvidia-nemo-curator/","text":"Learn more"}],"title":"Curating Custom Datasets for LLM Training with NVIDIA NeMo Curator","excerpt":"Data curation is the first, and arguably the most important, step in the pretraining and continuous training of large language models (LLMs) and small language…","featured":false,"products":["NeMo","NeMo Curator"],"sort_key":"2|curating custom datasets for llm training with nvidia nemo curator","created_at":1716285600,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/harnessing-data-with-ai-to-boost-zero-trust-cyber-defense/","text":"Learn more"}],"title":"Harnessing Data with AI to Boost Zero Trust Cyber Defense","excerpt":"Modern cyber threats have grown increasingly sophisticated, posing significant risks to federal agencies and critical infrastructure. According to Deloitte…","featured":false,"products":["Morpheus","NeMo","NeMo Retriever","NIM"],"sort_key":"2|harnessing data with ai to boost zero trust cyber defense","created_at":1727343355,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/mastering-llm-techniques-data-preprocessing/","text":"Learn more"}],"title":"Mastering LLM Techniques: Text Data Processing","excerpt":"Training and customizing LLMs for high accuracy is fraught with challenges, primarily due to their dependency on high-quality data. Poor data quality and…","featured":false,"products":["NeMo","NeMo Curator"],"sort_key":"2|mastering llm techniques: text data processing","created_at":1731492306,"content_type":"Blog","learning_levels":["Intermediate","Advanced"]},{"links":[{"url":"https://developer.nvidia.com/blog/build-enterprise-retrieval-augmented-generation-apps-with-nvidia-retrieval-qa-embedding-model/","text":"Learn more"}],"title":"Build Enterprise Retrieval-Augmented Generation Apps with NVIDIA Retrieval QA Embedding Model","excerpt":"Large language models (LLMs) are transforming the AI landscape with their profound grasp of human and programming languages. Essential for next-generation…","featured":false,"products":["NeMo","NeMo Retriever"],"sort_key":"2|build enterprise retrieval-augmented generation apps with nvidia retrieval qa embedding model","created_at":1701166250,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/scale-and-curate-high-quality-datasets-for-llm-training-with-nemo-curator/","text":"Learn more"}],"title":"Scale and Curate High-Quality Datasets for LLM Training with NVIDIA NeMo Curator","excerpt":"Enterprises are using large language models (LLMs) as powerful tools to improve operational efficiency and drive innovation. NVIDIA NeMo microservices aim to…","featured":false,"products":["DGX Cloud","NeMo","NeMo Curator","NeMo Customizer"],"sort_key":"2|scale and curate high-quality datasets for llm training with nvidia nemo curator","created_at":1711537200,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/scaling-enterprise-rag-with-accelerated-ethernet-networking-and-networked-storage/","text":"Learn more"}],"title":"Scaling Enterprise RAG with Accelerated Ethernet Networking and Networked Storage","excerpt":"In the era of generative AI, where machines are not just learning from data but generating human-like text, images, video, and more…","featured":false,"products":["NeMo","NeMo Retriever"],"sort_key":"2|scaling enterprise rag with accelerated ethernet networking and networked storage","created_at":1710774000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/tips-for-building-a-rag-pipeline-with-nvidia-ai-langchain-ai-endpoints/","text":"Learn more"}],"title":"Tips for Building a RAG Pipeline with NVIDIA AI LangChain AI Endpoints","excerpt":"Retrieval-augmented generation (RAG) is a technique that combines information retrieval with a set of carefully designed system prompts to provide more accurate…","featured":false,"products":["AI Foundation Models","NeMo Retriever"],"sort_key":"2|tips for building a rag pipeline with nvidia ai langchain ai endpoints","created_at":1715158800,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/simplify-custom-generative-ai-development-with-nvidia-nemo-microservices/","text":"Learn more"}],"title":"Simplify Custom Generative AI Development with NVIDIA NeMo Microservices","excerpt":"Across the globe, enterprises are realizing the benefits of generative AI models. They are racing to adopt these models in various applications…","featured":false,"products":["NeMo","NeMo Curator","NeMo Customizer","NeMo Evaluator"],"sort_key":"2|simplify custom generative ai development with nvidia nemo microservices","created_at":1710774240,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/rag-101-retrieval-augmented-generation-questions-answered/","text":"Learn more"}],"title":"RAG 101: Retrieval-Augmented Generation Questions Answered","excerpt":"Data scientists, AI engineers, MLOps engineers, and IT infrastructure professionals must consider a variety of factors when designing and deploying a RAG…","featured":false,"products":["NeMo Guardrails","NeMo Retriever","TensorRT","Triton Inference Server","Dynamo"],"sort_key":"2|rag 101: retrieval-augmented generation questions answered","created_at":1702899882,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/curating-trillion-token-datasets-introducing-nemo-data-curator/","text":"Learn more"}],"title":"Curating Trillion-Token Datasets: Introducing NVIDIA NeMo Data Curator","excerpt":"The latest developments in large language model (LLM) scaling laws have shown that when scaling the number of model parameters, the number of tokens used for…","featured":false,"products":["NeMo Curator"],"sort_key":"2|curating trillion-token datasets: introducing nvidia nemo data curator","created_at":1691494380,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/an-easy-introduction-to-multimodal-retrieval-augmented-generation/","text":"Learn more"}],"title":"An Easy Introduction to Multimodal Retrieval-Augmented Generation","excerpt":"A retrieval-augmented generation (RAG) application has exponentially higher utility if it can work with a wide variety of data types—tables, graphs, charts…","featured":false,"products":["General","NeMo Retriever"],"sort_key":"2|an easy introduction to multimodal retrieval-augmented generation","created_at":1710932400,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/nvidia-text-embedding-model-tops-mteb-leaderboard/","text":"Learn more"}],"title":"NVIDIA Text Embedding Model Tops MTEB Leaderboard","excerpt":"The latest embedding model from NVIDIA—NV-Embed—set a new record for embedding accuracy with a score of 69.32 on the Massive Text Embedding Benchmark (MTEB)…","featured":false,"products":["AI Enterprise","NeMo Retriever"],"sort_key":"2|nvidia text embedding model tops mteb leaderboard","created_at":1718013600,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/evaluating-retriever-for-enterprise-grade-rag/","text":"Learn more"}],"title":"Evaluating Retriever for Enterprise-Grade RAG","excerpt":"The conversation about designing and evaluating Retrieval-Augmented Generation (RAG) systems is a long, multi-faceted discussion. Even when we look at retrieval…","featured":false,"products":["NeMo","NeMo Retriever"],"sort_key":"2|evaluating retriever for enterprise-grade rag","created_at":1708686146,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/year-in-review-trending-posts-of-2023-2/","text":"Learn more"}],"title":"Most Popular NVIDIA Technical Blog Posts of 2023: Generative AI, LLMs, Robotics, and Virtual Worlds Breakthroughs","excerpt":"NVIDIA developments in generative AI, large language models, high-performance computing are transforming AI solutions and sparking reader interest.","featured":false,"products":["DGX","Grace CPU","Jetson","Jetson Orin","Maxine","NeMo Guardrails","TensorRT","TensorRT-LLM"],"sort_key":"2|most popular nvidia technical blog posts of 2023: generative ai, llms, robotics, and virtual worlds breakthroughs","created_at":1702979421,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/announcing-nemotron-cc-a-trillion-token-english-language-dataset-for-llm-pretraining/","text":"Learn more"}],"title":"Announcing Nemotron-CC: A Trillion-Token English Language Dataset for LLM Pretraining","excerpt":"NVIDIA is excited to announce the release of Nemotron-CC, a 6.3-trillion-token English language Common Crawl dataset for pretraining highly accurate large…","featured":false,"products":["NeMo","NeMo Curator"],"sort_key":"2|announcing nemotron-cc: a trillion-token english language dataset for llm pretraining","created_at":1736421616,"content_type":"Blog","learning_levels":["Beginner","Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/elevating-video-communication-with-the-nvidia-maxine-ai-developer-platform-and-videorequest/","text":"Learn more"}],"title":"Elevating Video Communication with the NVIDIA Maxine AI Developer Platform and VideoRequest","excerpt":"Effective video communication is important for everyone who communicates online. For businesses, educators, and content creators, it is vital.","featured":false,"products":["Maxine"],"sort_key":"2|elevating video communication with the nvidia maxine ai developer platform and videorequest","created_at":1723474391,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/enhance-your-training-data-with-new-nvidia-nemo-curator-classifier-models/","text":"Learn more"}],"title":"Enhance Your Training Data with New NVIDIA NeMo Curator Classifier Models","excerpt":"Classifier models are specialized in categorizing data into predefined groups or classes, playing a crucial role in optimizing data processing pipelines for…","featured":false,"products":["cuDF","NeMo","NeMo Curator","RAPIDS"],"sort_key":"2|enhance your training data with new nvidia nemo curator classifier models","created_at":1734620888,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/nvidia-deep-learning-institute-releases-new-generative-ai-teaching-kit/","text":"Learn more"}],"title":"NVIDIA Deep Learning Institute Releases New Generative AI Teaching Kit","excerpt":"Generative AI, powered by advanced machine learning models and deep neural networks, is revolutionizing industries by generating novel content and driving…","featured":false,"products":["General","NeMo Guardrails"],"sort_key":"2|nvidia deep learning institute releases new generative ai teaching kit","created_at":1740476869,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/nvidia-enables-trustworthy-safe-and-secure-large-language-model-conversational-systems/","text":"Learn more"}],"title":"NVIDIA Enables Trustworthy, Safe, and Secure Large Language Model Conversational Systems","excerpt":"Large language models (LLMs) are incredibly powerful and capable of answering complex questions, performing feats of creative writing, developing…","featured":false,"products":["NeMo Guardrails"],"sort_key":"2|nvidia enables trustworthy, safe, and secure large language model conversational systems","created_at":1682402400,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/insiders-guide-to-gtc-ar-vr-rendering-simulation-and-video-streaming/","text":"Learn more"}],"title":"Insider’s Guide to GTC: AR/VR, Rendering, Simulation, and Video Streaming","excerpt":"Notable sessions in the making of Green Planet AR, animating realistic digital humans, building a power industry digital twin, and making virtual production more...","featured":false,"products":["CloudXR","DLSS","Maxine","PhysicsNeMo","Nsight Tools - Graphics"],"sort_key":"2|insider’s guide to gtc: ar/vr, rendering, simulation, and video streaming","created_at":1646899998,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/orchestrating-innovation-at-scale-with-nvidia-maxine-and-texel/","text":"Learn more"}],"title":"Orchestrating Innovation at Scale with NVIDIA Maxine and Texel","excerpt":"The NVIDIA Maxine AI developer platform is a suite of NVIDIA NIM microservices, cloud-accelerated microservices, and SDKs that offer state-of-the-art features…","featured":false,"products":["Maxine"],"sort_key":"2|orchestrating innovation at scale with nvidia maxine and texel","created_at":1726496381,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/generative-ai-sparks-life-into-virtual-characters-with-ace-for-games/","text":"Learn more"}],"title":"Generative AI Sparks Life into Virtual Characters with NVIDIA ACE for Games","excerpt":"Use NVIDIA ACE for Games to build and deploy customized speech, conversation, and animation AI models in software and games.","featured":false,"products":["Avatar Cloud Engine (ACE)","Audio2Face","DGX","NeMo Guardrails"],"sort_key":"2|generative ai sparks life into virtual characters with nvidia ace for games","created_at":1685305800,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://nvda.ws/3Hmqvex#new_tab","text":"Learn more"}],"title":"Now Available: NVIDIA NeMo Guardrails","excerpt":"Develop safe and trustworthy LLM conversational applications with NVIDIA NeMo Guardrails, an open-source toolkit that enables programmable guardrails for defining...","featured":false,"products":["NeMo Guardrails"],"sort_key":"2|now available: nvidia nemo guardrails","created_at":1682672400,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/new-maxine-microservices-enhance-real-time-audio-and-video-effects-for-video-conferences-at-scale/","text":"Learn more"}],"title":"New NVIDIA Maxine Microservices Enhance Real-Time Audio and Video Effects for Conferences at Scale","excerpt":"Editor’s note: NVIDIA Maxine is now part of NVIDIA AI for Media. Learn more on the NVIDIA AI for Media developer page. At CES 2023, NVIDIA Maxine announced SDK…","featured":false,"products":["Maxine"],"sort_key":"2|new nvidia maxine microservices enhance real-time audio and video effects for conferences at scale","created_at":1672912800,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/major-updates-to-nvidia-ai-software-advancing-speech-recommenders-inference-and-more-announced-at-nvidia-gtc-2022/","text":"Learn more"}],"title":"Major Updates to NVIDIA AI Software Advancing Speech, Recommenders, Inference, and More Announced at NVIDIA GTC 2022","excerpt":"At GTC 2022, NVIDIA announced Riva 2.0, Merlin 1.0, new features to NVIDIA Triton, and more.","featured":false,"products":["Maxine","Merlin","NeMo Framework","Triton Inference Server","Dynamo"],"sort_key":"2|major updates to nvidia ai software advancing speech, recommenders, inference, and more announced at nvidia gtc 2022","created_at":1647943320,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/new-ai-sdks-and-tools-released-for-nvidia-blackwell-geforce-rtx-50-series-gpus/","text":"Learn more"}],"title":"New AI SDKs and Tools Released for NVIDIA Blackwell GeForce RTX 50 Series GPUs","excerpt":"NVIDIA recently announced a new generation of PC GPUs—the GeForce RTX 50 Series—alongside new AI-powered SDKs and tools for developers. Powered by the NVIDIA…","featured":false,"products":["ACE","Blackwell","CUDA","Maxine","Nsight Tools - Graphics","RTX GPU","TensorRT","Video Codec SDK"],"sort_key":"2|new ai sdks and tools released for nvidia blackwell geforce rtx 50 series gpus","created_at":1738216800,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/advancing-telepresence-and-next-generation-digital-humans-with-nvidia-maxine/","text":"Learn more"}],"title":"Advancing Telepresence and Next-Generation Digital Human Technology with NVIDIA Maxine","excerpt":"Editor’s note: NVIDIA Maxine is now part of NVIDIA AI for Media. Learn more on the NVIDIA AI for Media developer page. At SIGGRAPH 2024 this week…","featured":false,"products":["Maxine"],"sort_key":"2|advancing telepresence and next-generation digital human technology with nvidia maxine","created_at":1722259800,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/improve-human-connection-in-video-conferences-with-nvidia-maxine-eye-contact/","text":"Learn more"}],"title":"Improve Human Connection in Video Conferences with NVIDIA Maxine Eye Contact","excerpt":"Video conferencing is at the heart of several streaming use cases, such as vlogging, vtubing, webcasting, and even video streaming for remote work.","featured":false,"products":["Maxine"],"sort_key":"2|improve human connection in video conferences with nvidia maxine eye contact","created_at":1673503200,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/software-defined-broadcast-with-nvidia-holoscan-for-media/","text":"Learn more"}],"title":"Software-Defined Broadcast with NVIDIA Holoscan for Media","excerpt":"The broadcast industry is undergoing a transformation in how content is created, managed, distributed, and consumed. This transformation includes a shift from…","featured":false,"products":["Ampere","BlueField DPU","CV-CUDA","DeepStream","Holoscan","Maxine"],"sort_key":"2|software-defined broadcast with nvidia holoscan for media","created_at":1694692800,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/enhancing-generative-ai-model-accuracy-with-nvidia-nemo-curator/","text":"Learn more"}],"title":"Enhancing Generative AI Model Accuracy with NVIDIA NeMo Curator","excerpt":"In the rapidly evolving landscape of artificial intelligence, the quality of the data used for training models is paramount. High-quality data ensures that…","featured":false,"products":["NeMo Curator"],"sort_key":"2|enhancing generative ai model accuracy with nvidia nemo curator","created_at":1736758800,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/nvidia-maxine-elevates-video-conferencing-in-the-cloud/","text":"Learn more"}],"title":"NVIDIA Maxine Elevates Video Conferencing in the Cloud","excerpt":"NVIDIA Maxine has expanded to provide microservices that can be deployed in private or public clouds, enabling developers to leverage GPU power from remote servers. ","featured":false,"products":["Maxine"],"sort_key":"2|nvidia maxine elevates video conferencing in the cloud","created_at":1679486400,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://nvda.ws/3CwRR2w#new_tab","text":"Learn more"}],"title":"New NVIDIA AI Blueprint: Build a Customizable RAG Pipeline","excerpt":"Connect AI applications to enterprise data using embedding and reranking models for information retrieval.","featured":false,"products":["NeMo Retriever","NIM"],"sort_key":"2|new nvidia ai blueprint: build a customizable rag pipeline","created_at":1738247172,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://register.nvidia.com/events/widget/nvidia/gtcfall2022/1661384036108001cWc5#new_tab","text":"Learn more"}],"title":"Top Rendering Sessions for Developers at GTC 2022","excerpt":"Learn about the latest traditional and neural rendering technologies and how they are accelerating professional visualization.","featured":false,"products":["Maxine","Nsight Tools - Graphics"],"sort_key":"2|top rendering sessions for developers at gtc 2022","created_at":1661950800,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/deploying-nvidia-riva-multilingual-asr-with-whisper-and-canary-architectures-while-selectively-deactivating-nmt/","text":"Learn more"}],"title":"Deploying NVIDIA Riva Multilingual ASR with Whisper and Canary Architectures While Selectively Deactivating NMT","excerpt":"NVIDIA has consistently developed automatic speech recognition (ASR) models that set the benchmark in the industry. Earlier versions of NVIDIA Riva…","featured":false,"products":["NIM","Riva"],"sort_key":"2|deploying nvidia riva multilingual asr with whisper and canary architectures while selectively deactivating nmt","created_at":1740048888,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-using-a-reranking-microservice-can-improve-accuracy-and-costs-of-information-retrieval/","text":"Learn more"}],"title":"How Using a Reranking Microservice Can Improve Accuracy and Costs of Information Retrieval","excerpt":"Applications requiring high-performance information retrieval span a wide range of domains, including search engines, knowledge management systems, AI agents…","featured":false,"products":["Blueprint","NeMo","NeMo Retriever","NIM"],"sort_key":"2|how using a reranking microservice can improve accuracy and costs of information retrieval","created_at":1741257218,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/measuring-the-effectiveness-and-performance-of-ai-guardrails-in-generative-ai-applications/","text":"Learn more"}],"title":"Measuring the Effectiveness and Performance of AI Guardrails in Generative AI Applications","excerpt":"Safeguarding AI agents and other conversational AI applications to ensure safe, on-brand and reliable behavior is essential for enterprises.","featured":false,"products":["NeMo","NeMo Guardrails"],"sort_key":"2|measuring the effectiveness and performance of ai guardrails in generative ai applications","created_at":1740993729,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/spotlight-personal-ai-brings-ai-receptionists-to-small-business-owners-with-nvidia-riva/","text":"Learn more"}],"title":"Spotlight: Personal AI Brings AI Receptionists to Small Business Owners with NVIDIA Riva","excerpt":"It’s 10 p.m. on a Tuesday when the phone rings at the Sapochnick Law Firm, a specialized law practice in San Diego, California. The caller, a client of the firm…","featured":false,"products":["NIM","Riva"],"sort_key":"2|spotlight: personal ai brings ai receptionists to small business owners with nvidia riva","created_at":1745941447,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/streamline-evaluation-of-llms-for-accuracy-with-nvidia-nemo-evaluator/","text":"Learn more"}],"title":"Streamline Evaluation of LLMs for Accuracy with NVIDIA NeMo Evaluator","excerpt":"Large language models (LLMs) have demonstrated remarkable capabilities, from tackling complex coding tasks to crafting compelling stories to translating natural…","featured":false,"products":["NeMo","NeMo Customizer","NeMo Evaluator","NeMo Microservices","NIM"],"sort_key":"2|streamline evaluation of llms for accuracy with nvidia nemo evaluator","created_at":1711537200,"content_type":"Blog","learning_levels":["Beginner","Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/customizing-nvidia-nims-for-domain-specific-needs-with-nvidia-nemo/","text":"Learn more"}],"title":"Customizing NVIDIA NIM for Domain-Specific Needs with NVIDIA NeMo","excerpt":"Large language models (LLMs) adopted for specific enterprise applications most often benefit from model customization. Enterprises need to tailor ‌LLMs for…","featured":false,"products":["NGC","NeMo","NeMo Customizer","NIM"],"sort_key":"2|customizing nvidia nim for domain-specific needs with nvidia nemo","created_at":1720610181,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/maximize-ai-agent-performance-with-data-flywheels-using-nvidia-nemo-microservices/","text":"Learn more"}],"title":"Maximize AI Agent Performance with Data Flywheels","excerpt":"AI agents need to continuously evolve. With NeMo microservices developers can create and maintain a robust data flywheel for AI agents.","featured":false,"products":["NeMo","NeMo Retriever","NeMo Curator","NeMo Evaluator"],"sort_key":"1|maximize ai agent performance with data flywheels","created_at":1791278003,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/mastering-llm-techniques-evaluation/","text":"Learn more"}],"title":"Mastering LLM Techniques: Evaluation","excerpt":"Explore robust evaluation techniques and best practices for assessing the accuracy and reliability of LLMs and RAG systems.","featured":false,"products":["NeMo Evaluator","NeMo"],"sort_key":"1|mastering llm techniques: evaluation","created_at":1791278003,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/defining-llm-red-teaming/","text":"Learn more"}],"title":"Defining LLM Red Teaming","excerpt":"There is an activity where people provide inputs to generative AI technologies, such as large language models (LLMs), to see if the outputs can be made to…","featured":false,"products":["AI Enterprise","NeMo Guardrails"],"sort_key":"2|defining llm red teaming","created_at":1740480566,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/building-nemotron-cc-a-high-quality-trillion-token-dataset-for-llm-pretraining-from-common-crawl-using-nvidia-nemo-curator/","text":"Learn more"}],"title":"Building Nemotron-CC, A High-Quality Trillion Token Dataset for LLM Pretraining from Common Crawl Using NVIDIA NeMo Curator","excerpt":"Curating high-quality pretraining datasets is critical for enterprise developers aiming to train state-of-the-art large language models (LLMs).","featured":false,"products":["cuDF","cuML","NeMo Curator","Nemotron","RAPIDS"],"sort_key":"2|building nemotron-cc, a high-quality trillion token dataset for llm pretraining from common crawl using nvidia nemo curator","created_at":1746609751,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/r2d2-advancing-robot-mobility-whole-body-control-with-ai-from-nvidia-research/","text":"Learn more"}],"title":"R²D²: Advancing Robot Mobility and Whole-Body Control with Novel Workflows and AI Foundation Models from NVIDIA Research","excerpt":"Welcome to the first edition of the NVIDIA Robotics Research and Development Digest (R2D2). This technical blog series will give developers and researchers…","featured":false,"products":["Cosmos","Isaac Sim","Omniverse"],"sort_key":"2|r2d2: advancing robot mobility and whole-body control with novel workflows and ai foundation models from nvidia research","created_at":1743062400,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/accelerating-the-future-of-transportation-with-ses-ais-nvidia-powered-innovation-for-electric-vehicles/","text":"Learn more"}],"title":"Accelerating the Future of Transportation with SES AI's NVIDIA-Powered Innovation for Electric Vehicles","excerpt":"Electric vehicles (EVs) are transforming transportation, but challenges such as cost, longevity, and range remain barriers to widespread adoption.","featured":false,"products":["DGX Cloud","NeMo","NeMo Curator","NIM"],"sort_key":"2|accelerating the future of transportation with ses ai's nvidia-powered innovation for electric vehicles","created_at":1742893200,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/prevent-llm-hallucinations-with-the-cleanlab-trustworthy-language-model-in-nvidia-nemo-guardrails/","text":"Learn more"}],"title":"Prevent LLM Hallucinations with the Cleanlab Trustworthy Language Model in NVIDIA NeMo Guardrails","excerpt":"As more enterprises integrate LLMs into their applications, they face a critical challenge: LLMs can generate plausible but incorrect responses…","featured":false,"products":["NeMo","NeMo Guardrails","NIM"],"sort_key":"2|prevent llm hallucinations with the cleanlab trustworthy language model in nvidia nemo guardrails","created_at":1744203600,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/enhance-your-ai-agent-with-data-flywheels-using-nvidia-nemo-microservices/","text":"Learn more"}],"title":"Enhance Your AI Agent with Data Flywheels Using NVIDIA NeMo Microservices","excerpt":"Enterprise data is constantly changing. This presents significant challenges for maintaining AI system accuracy over time. As organizations increasingly rely on…","featured":false,"products":["NeMo","NeMo Curator","NeMo Customizer","NeMo Evaluator","NeMo Guardrails","NeMo Microservices","NIM"],"sort_key":"2|enhance your ai agent with data flywheels using nvidia nemo microservices","created_at":1745388000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/developing-an-ai-powered-tool-for-automatic-citation-validation-using-nvidia-nim/","text":"Learn more"}],"title":"Developing an AI-Powered Tool for Automatic Citation Validation Using NVIDIA NIM","excerpt":"The accuracy of citations is crucial for maintaining the integrity of both academic and AI-generated content. When citations are inaccurate or wrong…","featured":false,"products":["A100","NeMo Retriever","NIM"],"sort_key":"2|developing an ai-powered tool for automatic citation validation using nvidia nim","created_at":1744796450,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/evaluating-and-enhancing-rag-pipeline-performance-using-synthetic-data/","text":"Learn more"}],"title":"Evaluating and Enhancing RAG Pipeline Performance Using Synthetic Data ","excerpt":"As large language models (LLM) gain popularity in various question-answering systems, retrieval-augmented generation (RAG) pipelines have also become a focal…","featured":false,"products":["NeMo Curator","NeMo Retriever"],"sort_key":"2|evaluating and enhancing rag pipeline performance using synthetic data","created_at":1744025946,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/simulating-robots-in-industrial-facility-digital-twins/","text":"Learn more"}],"title":"Simulating Robots in Industrial Facility Digital Twins","excerpt":"Industrial enterprises are embracing physical AI and autonomous systems to transform their operations. This involves deploying heterogeneous robot fleets that…","featured":false,"products":["Blueprint","Metropolis","Omniverse"],"sort_key":"2|simulating robots in industrial facility digital twins","created_at":1743411600,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo-microservices/collections/nemo-microservices","text":"Learn more"}],"title":"NVIDIA NeMo Microservices","excerpt":"This collection contains the NeMo microservices to build an end-to-end platform for fine-tuning, evaluating, and serving LLMs on your Kubernetes cluster.","featured":true,"products":["NeMo","NeMo Evaluator","NeMo Guardrails","NeMo Customizer"],"sort_key":"0|nvidia nemo microservices","created_at":1791278003,"content_type":"Container","learning_levels":["Intermediate"]},{"links":[{"url":"https://www.youtube.com/watch?v=TX-NNK2FRdY","text":"Learn more"}],"title":"Customizing AI Agents for Tool Calling\n","excerpt":"Learn how to customize AI agents for precise function calling with this end-to-end example with NVIDIA NeMo microservices.","featured":true,"products":["NeMo","NeMo Customizer","NeMo Evaluator","NeMo Guardrails"],"sort_key":"0|customizing ai agents for tool calling","created_at":1791278003,"content_type":"Video","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/applying-autoencoder-based-gnns-for-high-throughput-network-anomaly-detection-in-netflow-data/","text":"Learn more"}],"title":"Applying Autoencoder-Based GNNs for High-Throughput Network Anomaly Detection in NetFlow Data","excerpt":"As modern enterprise and cloud environments scale, the complexity and volume of network traffic increase dramatically. NetFlow is used to record metadata about…","featured":false,"products":["Morpheus"],"sort_key":"2|applying autoencoder-based gnns for high-throughput network anomaly detection in netflow data","created_at":1746717521,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/stream-smarter-and-safer-learn-how-nvidia-nemo-guardrails-enhance-llm-output-streaming/","text":"Learn more"}],"title":"Stream Smarter and Safer: Learn how NVIDIA NeMo Guardrails Enhance LLM Output Streaming","excerpt":"​​LLM Streaming sends a model’s response incrementally in real time, token by token, as it’s being generated. The output streaming capability has evolved from a…","featured":false,"products":["NeMo Guardrails","NeMo Microservices"],"sort_key":"2|stream smarter and safer: learn how nvidia nemo guardrails enhance llm output streaming","created_at":1747995368,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/accelerating-text-to-sql-inference-on-vanna-with-nvidia-nim-for-faster-analytics/","text":"Learn more"}],"title":"Accelerating Text-to-SQL Inference on Vanna with NVIDIA NIM for Faster Analytics","excerpt":"Slow and inefficient query generation from natural language inputs bottlenecks decision-making. This forces analysts and business users to rely heavily on data…","featured":false,"products":["NeMo Retriever","NIM"],"sort_key":"2|accelerating text-to-sql inference on vanna with nvidia nim for faster analytics","created_at":1748594728,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/concept%e2%80%91driven-ai-teaching-assistant-guides-students-to-deeper-insights/","text":"Learn more"}],"title":"Concept‑Driven AI Teaching Assistant Guides Students to Deeper Insights","excerpt":"In today’s educational landscape, generative AI tools have become both a blessing and a challenge. While these tools offer unprecedented access to information…","featured":false,"products":["Blueprint","DGX Cloud","NeMo Guardrails","NeMo Retriever"],"sort_key":"2|concept-driven ai teaching assistant guides students to deeper insights","created_at":1746626271,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/nvidia-deep-learning-institute-offers-multilingual-ai-training-at-gtc-paris/","text":"Learn more"}],"title":"NVIDIA Deep Learning Institute Offers Multilingual AI Training at GTC Paris","excerpt":"Large language models (LLMs) are capable of recognizing, summarizing, translating, predicting, and generating content. Yet even the most powerful LLMs face…","featured":false,"products":["NeMo","NeMo Evaluator","TensorRT-LLM"],"sort_key":"2|nvidia deep learning institute offers multilingual ai training at gtc paris","created_at":1748605362,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/build-custom-reasoning-models-with-advanced-open-post-training-datasets/","text":"Learn more"}],"title":"Build Custom Reasoning Models with Advanced, Open Post-Training Datasets","excerpt":"Synthetic data has become a standard part of large language model (LLM) post-training procedures. Using a large number of synthetically generated examples from…","featured":false,"products":["NeMo","NeMo Curator","NeMo Customizer","Nemotron"],"sort_key":"2|build custom reasoning models with advanced, open post-training datasets","created_at":1747215206,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/designing-ai-factories-using-openusd-and-simready-assets/","text":"Learn more"}],"title":"Designing AI Factories Using OpenUSD and SimReady Assets","excerpt":"Announced at COMPUTEX 2025, the NVIDIA Omniverse Blueprint for AI factory digital twins has expanded to support OpenUSD schemas. The blueprint features new…","featured":false,"products":["Blueprint","Omniverse"],"sort_key":"2|designing ai factories using openusd and simready assets","created_at":1747609200,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://www.nvidia.com/en-us/events/supercharge-agentic-ai-build-scalable-data-flywheels/","text":"Learn more"}],"title":"Supercharge Agentic AI: Build Scalable Data Flywheels","excerpt":"Learn best practices for integrating NeMo components to optimize AI agent performance.","featured":true,"products":["NeMo","NeMo Evaluator","NeMo Customizer","NeMo Guardrails"],"sort_key":"0|supercharge agentic ai: build scalable data flywheels","created_at":1791278003,"content_type":"Webinar","learning_levels":["Beginner"]},{"links":[{"url":"https://www.youtube.com/watch?v=8Mwrfvq-GeY%20","text":"Learn more"}],"title":"How Robot Brains Dream and Explore Unseen Worlds","excerpt":"NVIDIA Isaac GR00T-Dreams enables developers to generate large-scale synthetic trajectory data from minimal human demonstrations, enabling robots to quickly…","featured":false,"products":["Cosmos"],"sort_key":"2|how robot brains dream and explore unseen worlds","created_at":1748607403,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/enhance-robot-learning-with-synthetic-trajectory-data-generated-by-world-foundation-models/","text":"Learn more"}],"title":"Enhance Robot Learning with Synthetic Trajectory Data Generated by World Foundation Models","excerpt":"Generalist robotics have arrived, powered by advances in mechatronics and robot AI foundation models. But a key bottleneck remains: robots need vast training…","featured":false,"products":["Blueprint","Cosmos","Isaac Sim","Jetson Orin","Omniverse"],"sort_key":"2|enhance robot learning with synthetic trajectory data generated by world foundation models","created_at":1750068000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/isaac-sim-and-isaac-lab-are-now-available-for-early-developer-preview/","text":"Learn more"}],"title":"Announcing General Availability for NVIDIA Isaac Sim 5.0 and NVIDIA Isaac Lab 2.2","excerpt":"At SIGGRAPH 2025, NVIDIA released general access for NVIDIA Isaac Sim and NVIDIA Isaac Lab reference robotics simulation and learning frameworks.","featured":false,"products":["Cosmos","Isaac Sim","Omniverse"],"sort_key":"2|announcing general availability for nvidia isaac sim 5.0 and nvidia isaac lab 2.2","created_at":1754899200,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/nvidia-speech-ai-models-deliver-industry-leading-accuracy-and-performance/","text":"Learn more"}],"title":"NVIDIA Speech AI Models Deliver Industry-Leading Accuracy and Performance","excerpt":"NVIDIA is driving state-of-the-art performance, efficiency, and accessibility in both speech AI and language models, setting the stage for innovations that are…","featured":false,"products":["NIM","Riva"],"sort_key":"2|nvidia speech ai models deliver industry-leading accuracy and performance","created_at":1749032191,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/run-multimodal-extraction-for-more-efficient-ai-pipelines-using-one-gpu/","text":"Learn more"}],"title":"Run Multimodal Extraction for More Efficient AI Pipelines Using One GPU","excerpt":"As enterprises generate and consume increasing volumes of diverse data, extracting insights from multimodal documents, like PDFs and presentations…","featured":false,"products":["Blueprint","NeMo Retriever"],"sort_key":"2|run multimodal extraction for more efficient ai pipelines using one gpu","created_at":1750253511,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/introducing-nvfp4-for-efficient-and-accurate-low-precision-inference/","text":"Learn more"}],"title":"Introducing NVFP4 for Efficient and Accurate Low-Precision Inference","excerpt":"To get the most out of AI, optimizations are critical. When developers think about optimizing AI models for inference, model compression techniques—such as…","featured":false,"products":["Blackwell","TensorRT","TensorRT-LLM"],"sort_key":"2|introducing nvfp4 for efficient and accurate low-precision inference","created_at":1750756726,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/build-efficient-ai-agents-through-model-distillation-with-nvidias-data-flywheel-blueprint/","text":"Learn more"}],"title":"Build Efficient AI Agents With the Data Flywheel Blueprint","excerpt":"Explore how our new AI blueprint can help enable self-improving AI agents by automating model optimization.","featured":false,"products":["NeMo","NeMo Evaluator","NeMo Customizer","NeMo Guardrails"],"sort_key":"1|build efficient ai agents with the data flywheel blueprint","created_at":1791278003,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/run-high-performance-ai-applications-with-nvidia-tensorrt-for-rtx/","text":"Learn more"}],"title":"Run High-Performance AI Applications with NVIDIA TensorRT for RTX","excerpt":"NVIDIA TensorRT for RTX is now available for download as an SDK that can be integrated into C++ and Python applications for both Windows and Linux.","featured":false,"products":["TensorRT"],"sort_key":"2|run high-performance ai applications with nvidia tensorrt for rtx","created_at":1749708000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/accelerate-decision-optimization-using-open-source-nvidia-cuopt/","text":"Learn more"}],"title":"Accelerate Decision Optimization Using Open Source NVIDIA cuOpt","excerpt":"Businesses make thousands of decisions every day—what to produce, where to ship, how to allocate resources. At scale, optimizing these decisions becomes a…","featured":false,"products":["cuOpt"],"sort_key":"2|accelerate decision optimization using open source nvidia cuopt","created_at":1749614400,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://youtu.be/hTYrjYbFHyU","text":"Learn more"}],"title":"Optimize AI Agents With a Data Flywheel","excerpt":"Get an overview of what a data flywheel is, how a data flywheel automates the optimization of AI agents by continuously automating model distillation and experimentation.","featured":false,"products":["NeMo","NeMo Evaluator","NeMo Customizer","NeMo Guardrails"],"sort_key":"1|optimize ai agents with a data flywheel","created_at":1791278003,"content_type":"Video","learning_levels":["Beginner"]},{"links":[{"url":"https://build.nvidia.com/nvidia/build-an-enterprise-data-flywheel","text":"Learn more"}],"title":"Data Flywheel Blueprint","excerpt":"Build a data flywheel, with NVIDIA NeMo microservices, that continuously optimizes AI agents for latency and cost — while maintaining accuracy targets.","featured":true,"products":["NeMo","NeMo Evaluator","NeMo Customizer","NeMo Guardrails"],"sort_key":"0|data flywheel blueprint","created_at":1791278003,"content_type":"Example","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/best-in-class-multimodal-rag-how-the-llama-3-2-nemo-retriever-embedding-model-boosts-pipeline-accuracy/","text":"Learn more"}],"title":"Best-in-Class Multimodal RAG: How the Llama 3.2 NeMo Retriever Embedding Model Boosts Pipeline Accuracy","excerpt":"Data goes far beyond text—it is inherently multimodal, encompassing images, video, audio, and more, often in complex and unstructured formats.","featured":false,"products":["NeMo","NeMo Retriever"],"sort_key":"2|best-in-class multimodal rag: how the llama 3.2 nemo retriever embedding model boosts pipeline accuracy","created_at":1751277394,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/r2d2-training-generalist-robots-with-nvidia-research-workflows-and-world-foundation-models/","text":"Learn more"}],"title":"R²D²: Training Generalist Robots with NVIDIA Research Workflows and World Foundation Models","excerpt":"A major challenge in robotics is training robots to perform new tasks without the massive effort of collecting and labeling datasets for every new task and…","featured":false,"products":["Cosmos","Isaac ROS"],"sort_key":"2|r2d2: training generalist robots with nvidia research workflows and world foundation models","created_at":1752653668,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/fine-tuning-llmops-for-rapid-model-evaluation-and-ongoing-optimization/","text":"Learn more"}],"title":"Fine-Tuning LLMOps for Rapid Model Evaluation and Ongoing Optimization","excerpt":"Large language models (LLMs) have created unprecedented opportunities across various industries. However, moving LLMs from research and development into…","featured":false,"products":["AI Enterprise","Blueprint","NeMo Curator","NeMo Customizer","NeMo Evaluator","NeMo Guardrails","NeMo Microservices","NIM"],"sort_key":"2|fine-tuning llmops for rapid model evaluation and ongoing optimization","created_at":1750154400,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/enhancing-multilingual-human-like-speech-and-voice-cloning-with-nvidia-riva-tts/","text":"Learn more"}],"title":"Enhancing Multilingual Human-Like Speech and Voice Cloning with NVIDIA Riva TTS","excerpt":"While speech AI is used to build digital assistants and voice agents, its impact extends far beyond these applications. Core technologies like text-to-speech…","featured":false,"products":["AI Enterprise","NIM","Riva"],"sort_key":"2|enhancing multilingual human-like speech and voice cloning with nvidia riva tts","created_at":1752485400,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/llm-inference-benchmarking-performance-tuning-with-tensorrt-llm/","text":"Learn more"}],"title":"LLM Inference Benchmarking: Performance Tuning with TensorRT-LLM","excerpt":"This is the third post in the large language model latency-throughput benchmarking series, which aims to instruct developers on how to benchmark LLM inference…","featured":false,"products":["TensorRT","TensorRT-LLM"],"sort_key":"2|llm inference benchmarking: performance tuning with tensorrt-llm","created_at":1751882400,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/run-google-deepminds-gemma-3n-on-nvidia-jetson-and-rtx/","text":"Learn more"}],"title":"Run Google DeepMind’s Gemma 3n on NVIDIA Jetson and RTX","excerpt":"As of today, NVIDIA now supports the general availability of Gemma 3n on NVIDIA RTX and Jetson. Gemma, previewed by Google DeepMind at Google I/O last month…","featured":false,"products":["Jetson","Jetson Orin","NeMo","NeMo Curator","NeMo Evaluator","NeMo Microservices","RTX GPU"],"sort_key":"2|run google deepmind’s gemma 3n on nvidia jetson and rtx","created_at":1750931100,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://www.nvidia.com/en-us/events/sovereign-ai-in-practice-webinar/?ncid=ref-dev-171762-emeatalks","text":"Learn more"}],"title":"Check Out Sovereign AI in Practice Through an NVIDIA Webinar","excerpt":"Join NVIDIA experts and leading European model builders on July 8 for a webinar on building and deploying multilingual large language models.","featured":false,"products":["NeMo","NeMo Evaluator","TensorRT-LLM"],"sort_key":"2|check out sovereign ai in practice through an nvidia webinar","created_at":1750849192,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/boost-embedding-model-accuracy-for-custom-information-retrieval/","text":"Learn more"}],"title":"Boost Embedding Model Accuracy for Custom Information Retrieval","excerpt":"Customizing embedding models is crucial for effective information retrieval, especially when working with domain-specific data like legal text, medical records…","featured":false,"products":["NeMo Curator"],"sort_key":"2|boost embedding model accuracy for custom information retrieval","created_at":1750819748,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://huggingface.co/nvidia/llama-nemoretriever-colembed-3b-v1/tree/main#new_tab","text":"Learn more"}],"title":"NVIDIA NeMo Retriever Scores First Place for Visual Retrieval","excerpt":"NeMo Retriever tops several visual document retrieval leaderboards, setting new standards for RAG apps.","featured":false,"products":["NeMo Retriever"],"sort_key":"2|nvidia nemo retriever scores first place for visual retrieval","created_at":1751276579,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/build-more-accurate-and-efficient-ai-agents-with-the-new-nvidia-llama-nemotron-super-v1-5/","text":"Learn more"}],"title":"Build More Accurate and Efficient AI Agents with the New NVIDIA Llama Nemotron Super v1.5","excerpt":"AI agents now solve multi-step problems, write production-level code, and act as general assistants across multiple domains. But to reach their full potential…","featured":false,"products":["Nemotron","NIM"],"sort_key":"2|build more accurate and efficient ai agents with the new nvidia llama nemotron super v1.5","created_at":1753798500,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/serverless-distributed-data-processing-with-apache-spark-and-nvidia-ai-on-azure/","text":"Learn more"}],"title":"Serverless Distributed Data Processing with Apache Spark and NVIDIA AI on Azure","excerpt":"The process of converting vast libraries of text into numerical representations known as embeddings is essential for generative AI.","featured":false,"products":["NIM","RAPIDS"],"sort_key":"2|serverless distributed data processing with apache spark and nvidia ai on azure","created_at":1753266600,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://huggingface.co/spaces/hf-audio/open_asr_leaderboard#new_tab","text":"Learn more"}],"title":"NVIDIA Canary‑Qwen‑2.5B: Open‑Source ASR/LLM for Superior Transcription and Summarization","excerpt":"Top‑ranked on the HuggingFace Open‑ASR leaderboard, the model is production‑ready.","featured":false,"products":["Riva"],"sort_key":"2|nvidia\u0001canary-qwen-2.5b: open-source asr/llm for superior transcription and summarization","created_at":1752747447,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/approaches-to-pdf-data-extraction-for-information-retrieval/","text":"Learn more"}],"title":"Approaches to PDF Data Extraction for Information Retrieval","excerpt":"The PDF is among the most common file formats for sharing information such as financial reports, research papers, technical documents, and marketing materials.","featured":false,"products":["Blueprint","cuVS","NeMo","NeMo Retriever"],"sort_key":"2|approaches to pdf data extraction for information retrieval","created_at":1753268174,"content_type":"Blog","learning_levels":["Intermediate","Advanced"]},{"links":[{"url":"https://developer.nvidia.com/blog/train-a-reasoning-capable-llm-in-one-weekend-with-nvidia-nemo/","text":"Learn more"}],"title":"Train a Reasoning-Capable LLM in One Weekend with NVIDIA NeMo","excerpt":"Have you ever wanted to build your own reasoning models such as the open NVIDIA Nemotron, but thought it was too complicated or required massive resources?","featured":false,"products":["NeMo","NeMo Curator","NeMo Evaluator","Nemotron"],"sort_key":"2|train a reasoning-capable llm in one weekend with nvidia nemo","created_at":1753208336,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/safeguard-agentic-ai-systems-with-the-nvidia-safety-recipe/","text":"Learn more"}],"title":"Safeguard Agentic AI Systems with the NVIDIA Safety Recipe","excerpt":"As large language models (LLMs) power more agentic systems capable of performing autonomous actions, tool use, and reasoning, enterprises are drawn to their…","featured":false,"products":["NeMo","NeMo Guardrails","NIM"],"sort_key":"2|safeguard agentic ai systems with the nvidia safety recipe","created_at":1752742800,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/bringing-verifiable-trust-to-ai-models-model-signing-in-ngc/","text":"Learn more"}],"title":"Bringing Verifiable Trust to AI Models: Model Signing in NGC","excerpt":"AI is entering a new era—one defined by agents that reason, plan, and take action. These agentic systems dynamically interact with APIs, tools…","featured":false,"products":["AI Enterprise","NGC","NIM"],"sort_key":"2|bringing verifiable trust to ai models: model signing in ngc","created_at":1753696800,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://www.youtube.com/watch?v=NBcZOQHn46g","text":"Learn more"}],"title":"Beyond the Algorithm with NVIDIA","excerpt":"Explore the NVIDIA Data Flywheel Blueprint, an open reference architecture for distilling knowledge from larger models into smaller, faster, and cost-efficient alternatives.","featured":true,"products":["NeMo","NeMo Evaluator","NeMo Customizer","NeMo Guardrails"],"sort_key":"0|beyond the algorithm with nvidia","created_at":1791278003,"content_type":"Video","learning_levels":["Beginner"]},{"links":[{"url":"https://build.nvidia.com/moonshotai/kimi-k2-instruct#new_tab","text":"Learn more"}],"title":"Kimi-K2-Instruct Now Available as NVIDIA NIM","excerpt":"Try the new 1T-parameter open source MoE LLM today.","featured":false,"products":["NIM"],"sort_key":"2|kimi-k2-instruct now available as nvidia nim","created_at":1753173416,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/delivering-1-5-m-tps-inference-on-nvidia-gb200-nvl72-nvidia-accelerates-openai-gpt-oss-models-from-cloud-to-edge/","text":"Learn more"}],"title":"NVIDIA Accelerates OpenAI gpt-oss Models Delivering 1.5 M TPS Inference on NVIDIA GB200 NVL72","excerpt":"NVIDIA and OpenAI began pushing the boundaries of AI with the launch of NVIDIA DGX back in 2016. The collaborative AI innovation continues with the OpenAI gpt…","featured":false,"products":["Blackwell","Dynamo","NIM","RTX GPU","TensorRT-LLM"],"sort_key":"2|nvidia accelerates openai gpt-oss models delivering 1.5 m tps inference on nvidia gb200 nvl72","created_at":1754388600,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/identify-speakers-in-meetings-calls-and-voice-apps-in-real-time-with-nvidia-streaming-sortformer/","text":"Learn more"}],"title":"Identify Speakers in Meetings, Calls, and Voice Apps in Real-Time with NVIDIA Streaming Sortformer","excerpt":"September 2026 update: Our latest diarization release is Nemotron 3 Diarization. It’s #1 on the VoiceArena leaderboard, and supports up to 8 speakers.","featured":false,"products":["NeMo","Riva"],"sort_key":"2|identify speakers in meetings, calls, and voice apps in real-time with nvidia streaming sortformer","created_at":1755507600,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://huggingface.co/blog/nvidia/supercharge-ai-reasoning-with-nemotron-nano-2?nvid=nv-int-tblg-513492%20","text":"Learn more"}],"title":"New Nemotron Nano 2 Open Reasoning Model Tops Leaderboard and Delivers 6x Higher Throughput","excerpt":"There’s a new leaderboard-topping NVIDIA Nemotron Nano 2 model. It’s an open model with leading accuracy and up to 6x higher throughput compared to the next…","featured":false,"products":["Nemotron","NIM"],"sort_key":"2|new nemotron nano 2 open reasoning model tops leaderboard and delivers 6x higher throughput","created_at":1755611407,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-to-enhance-rag-pipelines-with-reasoning-using-nvidia-llama-nemotron-models/","text":"Learn more"}],"title":"How to Enhance RAG Pipelines with Reasoning Using NVIDIA Llama Nemotron Models","excerpt":"A key challenge for retrieval-augmented generation (RAG) systems is handling user queries that lack explicit clarity or carry implicit intent.","featured":false,"products":["NeMo Retriever","NIM"],"sort_key":"2|how to enhance rag pipelines with reasoning using nvidia llama nemotron models","created_at":1754301600,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/introducing-nvidia-jetson-thor-the-ultimate-platform-for-physical-ai/","text":"Learn more"}],"title":"Introducing NVIDIA Jetson Thor, the Ultimate Platform for Physical AI","excerpt":"Robotics is undergoing a revolution, moving beyond the era of specialist machines to generalist robotics. This shift moves away from single-purpose…","featured":false,"products":["Blackwell","Blueprint","Cosmos","GR00T","Holoscan","Isaac SDK","Jetson","Metropolis"],"sort_key":"2|introducing nvidia jetson thor, the ultimate platform for physical ai","created_at":1756119420,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/optimizing-llms-for-performance-and-accuracy-with-post-training-quantization/","text":"Learn more"}],"title":"Optimizing LLMs for Performance and Accuracy with Post-Training Quantization","excerpt":"Quantization is a core tool for developers aiming to improve inference performance with minimal overhead. It delivers significant gains in latency, throughput…","featured":false,"products":["Blackwell","TensorRT"],"sort_key":"2|optimizing llms for performance and accuracy with post-training quantization","created_at":1754058443,"content_type":"Blog","learning_levels":["Advanced"]},{"links":[{"url":"https://developer.nvidia.com/blog/turn-complex-documents-into-usable-data-with-vlm-nvidia-nemotron-parse-1-1/","text":"Learn more"}],"title":"Turn Complex Documents into Usable Data with VLM, NVIDIA Nemotron Parse 1.1","excerpt":"Enterprises generate and store vast amounts of unstructured data in documents like legal documents, sales documents, statement of work, delivery notices…","featured":false,"products":["NeMo Retriever"],"sort_key":"2|turn complex documents into usable data with vlm, nvidia nemotron parse 1.1","created_at":1753780155,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://www.nvidia.com/en-us/events/supercharge-agentic-ai-build-scalable-data-flywheels/#new_tab","text":"Learn more"}],"title":"Upcoming Webinar: Supercharge Agentic AI with Scalable Data Flywheels","excerpt":"Join our live webinar on June 18 to see how NVIDIA NeMo microservices speed AI agent development.","featured":false,"products":["NeMo Curator","NeMo Customizer","NeMo Evaluator","NeMo Guardrails","NeMo Microservices","NeMo Retriever"],"sort_key":"2|upcoming webinar: supercharge agentic ai with scalable data flywheels","created_at":1748360626,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-to-run-ai-powered-cae-simulations/","text":"Learn more"}],"title":"How to Run AI-Powered CAE Simulations","excerpt":"In modern engineering, the pace of innovation is closely linked to the ability to perform accelerated simulations. Computer-aided engineering (CAE) plays a…","featured":false,"products":["Blueprint","NeMo","NIM","Omniverse","PhysicsNeMo"],"sort_key":"2|how to run ai-powered cae simulations","created_at":1756890587,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/new-open-source-qwen3-next-models-preview-hybrid-moe-architecture-delivering-improved-accuracy-and-accelerated-parallel-processing-across-nvidia-platform/","text":"Learn more"}],"title":"New Open Source Qwen3-Next Models Preview Hybrid MoE Architecture Delivering Improved Accuracy and Accelerated Parallel Processing across NVIDIA Platform ","excerpt":"As AI models grow larger and process longer sequences of text, efficiency becomes just as important as scale. To showcase what’s next, Alibaba released two new…","featured":false,"products":["NIM"],"sort_key":"2|new open source qwen3-next models preview hybrid moe architecture delivering improved accuracy and accelerated parallel processing across nvidia platform","created_at":1757916000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/smarter-anomaly-detection-in-semiconductor-manufacturing-with-nvidia-nv-tesseract-and-nvidia-nim/","text":"Learn more"}],"title":"Smarter Anomaly Detection in Semiconductor Manufacturing with NVIDIA NV-Tesseract and NVIDIA NIM","excerpt":"In an earlier blog post, we introduced NVIDIA NV-Tesseract, a family of models designed to tackle diverse time-series tasks—such as anomaly detection…","featured":false,"products":["NIM"],"sort_key":"2|smarter anomaly detection in semiconductor manufacturing with nvidia nv-tesseract and nvidia nim","created_at":1759480140,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/nvidia-hardware-innovations-and-open-source-contributions-are-shaping-ai/","text":"Learn more"}],"title":"NVIDIA Hardware Innovations and Open Source Contributions Are Shaping AI","excerpt":"Open source AI models such as Cosmos, DeepSeek, Gemma, GPT-OSS, Llama, Nemotron, Phi, Qwen, and many more are the foundation of AI innovation.","featured":false,"products":["Blackwell","Cosmos","Dynamo","GR00T","NeMo","NVLink","PhysicsNeMo","RAPIDS","TensorRT","TensorRT-LLM"],"sort_key":"2|nvidia hardware innovations and open source contributions are shaping ai","created_at":1755849600,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/build-a-log-analysis-multi-agent-self-corrective-rag-system-with-nvidia-nemotron/","text":"Learn more"}],"title":"Build a Log Analysis Multi-Agent Self-Corrective RAG System with NVIDIA Nemotron","excerpt":"Logs are the lifeblood of modern systems. But as applications scale, logs often grow into endless walls of text—noisy, repetitive, and overwhelming.","featured":false,"products":["NeMo Retriever","Nemotron","NIM"],"sort_key":"2|build a log analysis multi-agent self-corrective rag system with nvidia nemotron","created_at":1760086800,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/an-introduction-to-speculative-decoding-for-reducing-latency-in-ai-inference/","text":"Learn more"}],"title":"An Introduction to Speculative Decoding for Reducing Latency in AI Inference","excerpt":"Generating text with large language models (LLMs) often involves running into a fundamental bottleneck. GPUs offer massive compute, yet much of that power sits…","featured":false,"products":["TensorRT","TensorRT-LLM"],"sort_key":"2|an introduction to speculative decoding for reducing latency in ai inference","created_at":1758107352,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-to-build-ai-systems-in-house-with-outerbounds-and-dgx-cloud-lepton/","text":"Learn more"}],"title":"How to Build AI Systems In House with Outerbounds and DGX Cloud Lepton","excerpt":"It’s easy to underestimate how many moving parts a real-world, production-grade AI system involves. Whether you’re building an agent that combines internal data…","featured":false,"products":["DGX Cloud","H100","NIM"],"sort_key":"2|how to build ai systems in house with outerbounds and dgx cloud lepton","created_at":1757322000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/modeling-attacks-on-ai-powered-apps-with-the-ai-kill-chain-framework/","text":"Learn more"}],"title":"Modeling Attacks on AI-Powered Apps with the AI Kill Chain Framework","excerpt":"AI-powered applications are introducing new attack surfaces that traditional security models don’t fully capture, especially as these agentic systems gain…","featured":false,"products":["cuVS","NIM"],"sort_key":"2|modeling attacks on ai-powered apps with the ai kill chain framework","created_at":1757581200,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/build-a-rag-agent-with-nvidia-nemotron/","text":"Learn more"}],"title":"Build a Retrieval-Augmented Generation (RAG) Agent with NVIDIA Nemotron","excerpt":"Unlike traditional LLM-based systems that are limited by their training data, retrieval-augmented generation (RAG) improves text generation by incorporating…","featured":false,"products":["NeMo Retriever","Nemotron","NIM"],"sort_key":"2|build a retrieval-augmented generation (rag) agent with nvidia nemotron","created_at":1758614400,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/deploy-scalable-ai-inference-with-nvidia-nim-operator-3-0-0/","text":"Learn more"}],"title":"Deploy Scalable AI Inference with NVIDIA NIM Operator 3.0.0","excerpt":"AI models, inference engine backends, and distributed inference frameworks continue to evolve in architecture, complexity, and scale. With the rapid pace of…","featured":false,"products":["NeMo Microservices","NIM"],"sort_key":"2|deploy scalable ai inference with nvidia nim operator 3.0.0","created_at":1757496600,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://nvidia-aws.devpost.com/?utm_source=devpost\u0026#038;utm_medium=linkedin\u0026#038;utm_campaign=agenticaiunleashed25","text":"Learn more"}],"title":"Agentic AI Unleashed: Join the AWS \u0026 NVIDIA Hackathon","excerpt":"Build the next generation of intelligent, autonomous applications. This isn’t just a hackathon—it’s your chance to unleash the power of agentic AI and show the…","featured":false,"products":["NeMo","Nemotron","NIM"],"sort_key":"2|agentic ai unleashed: join the aws \u0026 nvidia hackathon","created_at":1760531960,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/solve-linear-programs-using-the-gpu-accelerated-barrier-method-in-nvidia-cuopt/","text":"Learn more"}],"title":"Solve Linear Programs Using the GPU-Accelerated Barrier Method in NVIDIA cuOpt","excerpt":"How does the NFL schedule all its regular-season games while avoiding stadium conflicts with Beyoncé concerts? How can doctors use a single donated kidney to…","featured":false,"products":["cuOpt","H200"],"sort_key":"2|solve linear programs using the gpu-accelerated barrier method in nvidia cuopt","created_at":1761296400,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/building-an-interactive-ai-agent-for-lightning-fast-machine-learning-tasks/","text":"Learn more"}],"title":"Building an Interactive AI Agent for Lightning-Fast Machine Learning Tasks","excerpt":"Data scientists spend a lot of time cleaning and preparing large, unstructured datasets before analysis can begin, often requiring strong programming and…","featured":false,"products":["NeMo","NIM"],"sort_key":"2|building an interactive ai agent for lightning-fast machine learning tasks","created_at":1762508692,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://www.addevent.com/event/kffjqsqb67nq#new_tab","text":"Learn more"}],"title":"Upcoming Livestream: Build Visual AI Agents with NVIDIA Cosmos Reason and Metropolis","excerpt":"On November 18, learn how to fine-tune the NVIDIA Cosmos Reason VLM with your own data to create visual AI agents.","featured":false,"products":["Cosmos","Metropolis"],"sort_key":"2|upcoming livestream: build visual ai agents with nvidia cosmos reason and metropolis","created_at":1762784576,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-nvidia-dgx-sparks-performance-enables-intensive-ai-tasks/","text":"Learn more"}],"title":"How NVIDIA DGX Spark's Performance Enables Intensive AI Tasks","excerpt":"Today’s demanding AI developer workloads often need more memory than desktop systems provide or require access to software that laptops or PCs lack.","featured":false,"products":["Blackwell","Nemotron","NIM"],"sort_key":"2|how nvidia dgx spark's performance enables intensive ai tasks","created_at":1761296400,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-to-predict-biomolecular-structures-using-the-openfold3-nim/","text":"Learn more"}],"title":"How to Predict Biomolecular Structures Using the OpenFold3 NIM","excerpt":"​​For decades, one of biology’s deepest mysteries was how a string of amino acids folds itself into the intricate architecture of life.","featured":false,"products":["FLARE","NIM","TensorRT"],"sort_key":"2|how to predict biomolecular structures using the openfold3 nim","created_at":1762250400,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-to-achieve-4x-faster-inference-for-math-problem-solving/","text":"Learn more"}],"title":"How to Achieve 4x Faster Inference for Math Problem Solving","excerpt":"Large language models can solve challenging math problems. However, making them work efficiently at scale requires more than a strong checkpoint.","featured":false,"products":["NeMo","TensorRT-LLM"],"sort_key":"2|how to achieve 4x faster inference for math problem solving","created_at":1762764270,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/build-an-ai-agent-to-analyze-it-tickets-with-nvidia-nemotron/","text":"Learn more"}],"title":"Build an AI Agent to Analyze IT Tickets with NVIDIA Nemotron","excerpt":"Modern organizations generate a massive volume of operational data through ticketing systems, incident reports, service requests, support escalations, and more.","featured":false,"products":["Nemotron","NIM"],"sort_key":"2|build an ai agent to analyze it tickets with nvidia nemotron","created_at":1760954400,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/build-and-run-secure-data-driven-ai-agents/","text":"Learn more"}],"title":"Build and Run Secure, Data-Driven AI Agents ","excerpt":"As generative AI advances, organizations need AI agents that are accurate, reliable, and informed by data specific to their business. The NVIDIA AI-Q Research…","featured":false,"products":["Blueprint","NIM"],"sort_key":"2|build and run secure, data-driven ai agents","created_at":1763984952,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://catalog.ngc.nvidia.com/orgs/nvidia/teams/riva/models/speechsynthesis_multilingual_magpietts_ipa","text":"Learn more"}],"title":"RIVA Magpie-TTS Multilingual","excerpt":"Riva NeMo-MagpieTTS Multilingual IPA multispeaker model with Emotions","featured":false,"products":["Riva"],"sort_key":"2|riva magpie-tts multilingual","created_at":1752784739,"content_type":"Model","learning_levels":["Advanced"]},{"links":[{"url":"https://developer.nvidia.com/blog/building-scalable-ai-on-enterprise-data-with-nvidia-nemotron-rag-and-microsoft-sql-server-2025/","text":"Learn more"}],"title":"Building Scalable AI on Enterprise Data with NVIDIA Nemotron RAG and Microsoft SQL Server 2025","excerpt":"At Microsoft Ignite 2025, the vision for an AI-ready enterprise database becomes a reality with the announcement of Microsoft SQL Server 2025…","featured":false,"products":["Nemotron","NIM"],"sort_key":"2|building scalable ai on enterprise data with nvidia nemotron rag and microsoft sql server 2025","created_at":1763467200,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/faster-chemistry-and-materials-discovery-with-ai-powered-simulations-using-nvidia-alchemi/","text":"Learn more"}],"title":"Faster Chemistry and Materials Discovery with AI-Powered Simulations Using NVIDIA ALCHEMI","excerpt":"Almost all manufactured products are enabled by chemistry and materials science. However, new discoveries are costly and time-consuming and often hindered by…","featured":false,"products":["NIM"],"sort_key":"2|faster chemistry and materials discovery with ai-powered simulations using nvidia alchemi","created_at":1763456400,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/nvidia-accelerated-mistral-3-open-models-deliver-efficiency-accuracy-at-any-scale/","text":"Learn more"}],"title":"NVIDIA-Accelerated Mistral 3 Open Models Deliver Efficiency, Accuracy at Any Scale ","excerpt":"The new Mistral 3 open model family delivers industry-leading accuracy, efficiency, and customization capabilities for developers and enterprises.","featured":false,"products":["GB200","H200","NIM","TensorRT-LLM"],"sort_key":"2|nvidia-accelerated mistral 3 open models deliver efficiency, accuracy at any scale","created_at":1764670202,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/nvidia-blackwell-delivers-massive-performance-leaps-in-mlperf-inference-v5-0/","text":"Learn more"}],"title":"NVIDIA Blackwell Delivers Massive Performance Leaps in MLPerf Inference v5.0","excerpt":"The compute demands for large language model (LLM) inference are growing rapidly, fueled by the combination of growing model sizes…","featured":false,"products":["Blackwell","DGX","GB200","H100","Hopper","NVLink","TensorRT","TensorRT-LLM"],"sort_key":"2|nvidia blackwell delivers massive performance leaps in mlperf inference v5.0","created_at":1743592488,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-to-build-privacy-preserving-evaluation-benchmarks-with-synthetic-data/","text":"Learn more"}],"title":"How to Build Privacy-Preserving Evaluation Benchmarks with Synthetic Data","excerpt":"Validating AI systems requires benchmarks—datasets and evaluation workflows that mimic real-world conditions—to measure accuracy, reliability…","featured":false,"products":["NeMo","NeMo Customizer","NeMo Evaluator","Nemotron","NIM"],"sort_key":"2|how to build privacy-preserving evaluation benchmarks with synthetic data","created_at":1765528439,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-to-scale-data-generation-for-physical-ai-with-the-nvidia-cosmos-cookbook/","text":"Learn more"}],"title":"How to Scale Data Generation for Physical AI with the NVIDIA Cosmos Cookbook","excerpt":"Building powerful physical AI models requires diverse, controllable, and physically-grounded data at scale. Collecting large-scale, diverse real-world datasets…","featured":false,"products":["Cosmos","Isaac Sim"],"sort_key":"2|how to scale data generation for physical ai with the nvidia cosmos cookbook","created_at":1764579600,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/enabling-horizontal-autoscaling-of-enterprise-rag-components-on-kubernetes/","text":"Learn more"}],"title":"Enabling Horizontal Autoscaling of Enterprise RAG Components on Kubernetes","excerpt":"Today’s best AI agents rely on retrieval-augmented generation (RAG) to enable more accurate results. A RAG system facilitates the use of a knowledge base to…","featured":false,"products":["Blueprint","cuVS","NIM"],"sort_key":"2|enabling horizontal autoscaling of enterprise rag components on kubernetes","created_at":1765544400,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/pioneering-ai-co-scientists-for-fusion-research-and-cancer-treatment/","text":"Learn more"}],"title":"Pioneering AI Co-Scientists for Fusion Research and Cancer Treatment","excerpt":"AI is reshaping scientific research and innovation. Scientists can leverage AI to generate, summarize, combine, and analyze scientific data. AI models can find…","featured":false,"products":["BioNeMo","NeMo","NeMo Curator","Nemotron"],"sort_key":"2|pioneering ai co-scientists for fusion research and cancer treatment","created_at":1763389800,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/top-5-ai-model-optimization-techniques-for-faster-smarter-inference/","text":"Learn more"}],"title":"Top 5 AI Model Optimization Techniques for Faster, Smarter Inference","excerpt":"As AI models get larger and architectures more complex, researchers and engineers are continuously finding new techniques to optimize the performance and…","featured":false,"products":["TensorRT"],"sort_key":"2|top 5 ai model optimization techniques for faster, smarter inference","created_at":1765274400,"content_type":"Blog","learning_levels":["General Interest","Beginner","Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/multi-agent-warehouse-ai-command-layer-enables-operational-excellence-and-supply-chain-intelligence/","text":"Learn more"}],"title":"Multi-Agent Warehouse AI Command Layer Enables Operational Excellence and Supply Chain Intelligence","excerpt":"Warehouses have never been more automated, more data-rich, or more operationally demanding than they are now—yet they still rely on systems that can’t keep up.","featured":false,"products":["AI Enterprise","Blueprint","cuML","cuVS","NeMo","NIM"],"sort_key":"2|multi-agent warehouse ai command layer enables operational excellence and supply chain intelligence","created_at":1767938400,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/building-generalist-humanoid-capabilities-with-nvidia-isaac-gr00t-n1-6-using-a-sim-to-real-workflow/","text":"Learn more"}],"title":"Building Generalist Humanoid Capabilities with NVIDIA Isaac GR00T N1.6 Using a Sim-to-Real Workflow ","excerpt":"To make humanoid robots useful, they need cognition and loco-manipulation that span perception, planning, and whole-body control in dynamic environments.","featured":false,"products":["Cosmos","GR00T","Isaac Lab"],"sort_key":"2|building generalist humanoid capabilities with nvidia isaac gr00t n1.6 using a sim-to-real workflow","created_at":1767865133,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/ai-factories-physical-ai-and-advances-in-models-agents-and-infrastructure-that-shaped-2025/","text":"Learn more"}],"title":"AI Factories, Physical AI, and Advances in Models, Agents, and Infrastructure That Shaped 2025","excerpt":"NVIDIA developments in generative AI, large language models, high-performance computing are transforming AI solutions and sparking reader interest.","featured":false,"products":["General","Grace CPU","Hopper","NIM","TensorRT-LLM"],"sort_key":"2|ai factories, physical ai, and advances in models, agents, and infrastructure that shaped 2025","created_at":1767173400,"content_type":"Blog","learning_levels":["General Interest","Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/accelerating-ai-powered-chemistry-and-materials-science-simulations-with-nvidia-alchemi-toolkit-ops/","text":"Learn more"}],"title":"Accelerating AI-Powered Chemistry and Materials Science Simulations with NVIDIA ALCHEMI Toolkit-Ops","excerpt":"Machine learning interatomic potentials (MLIPs) are transforming the landscape of computational chemistry and materials science.","featured":false,"products":["NIM"],"sort_key":"2|accelerating ai-powered chemistry and materials science simulations with nvidia alchemi toolkit-ops","created_at":1766134800,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/build-an-ai-catalog-system-that-delivers-localized-interactive-product-experiences/","text":"Learn more"}],"title":"Build an AI Catalog System That Delivers Localized, Interactive Product Experiences","excerpt":"E-commerce catalogs often contain sparse product data, generic images, a basic title, and short description. This limits discoverability, engagement…","featured":false,"products":["Blueprint","Nemotron","NIM"],"sort_key":"2|build an ai catalog system that delivers localized, interactive product experiences","created_at":1767938400,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/learn-how-nvidia-cuopt-accelerates-mixed-integer-optimization-using-primal-heuristics/","text":"Learn more"}],"title":"Learn How NVIDIA cuOpt Accelerates Mixed Integer Optimization using Primal Heuristics","excerpt":"NVIDIA cuOpt is a GPU-accelerated optimization engine designed to deliver fast, high-quality solutions for large, complex decision-making problems.","featured":false,"products":["cuOpt"],"sort_key":"2|learn how nvidia cuopt accelerates mixed integer optimization using primal heuristics","created_at":1768307564,"content_type":"Blog","learning_levels":["Advanced"]},{"links":[{"url":"https://developer.nvidia.com/blog/adaptive-inference-in-nvidia-tensorrt-for-rtx-enables-automatic-optimization/","text":"Learn more"}],"title":"Adaptive Inference in NVIDIA TensorRT for RTX Enables Automatic Optimization","excerpt":"Deploying AI applications across diverse consumer hardware has traditionally forced a trade-off. You can optimize for specific GPU configurations and achieve…","featured":false,"products":["RTX GPU","TensorRT"],"sort_key":"2|adaptive inference in nvidia tensorrt for rtx enables automatic optimization","created_at":1769432400,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-to-build-a-document-processing-pipeline-for-rag-with-nemotron/","text":"Learn more"}],"title":"How to Build a Document Processing Pipeline for RAG with Nemotron ","excerpt":"What if your AI agent could instantly parse complex PDFs, extract nested tables, and “see” data within charts as easily as reading a text file?","featured":false,"products":["NeMo","NeMo Microservices","NeMo Retriever","Nemotron"],"sort_key":"2|how to build a document processing pipeline for rag with nemotron","created_at":1770192000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://catalog.ngc.nvidia.com/orgs/nvidia/teams/riva/models/sortformer_diarizer","text":"Learn more"}],"title":"Sortformer Speaker Diarization","excerpt":"Sortformer based speaker diarization model","featured":false,"products":["Riva"],"sort_key":"2|sortformer speaker diarization","created_at":1752784762,"content_type":"Model","learning_levels":["Advanced"]},{"links":[{"url":"https://developer.nvidia.com/blog/develop-native-multimodal-agents-with-qwen3-5-vlm-using-nvidia-gpu-accelerated-endpoints/","text":"Learn more"}],"title":"Develop Native Multimodal Agents with Qwen3.5 VLM Using NVIDIA GPU-Accelerated Endpoints","excerpt":"Alibaba has introduced the new open source Qwen3.5 series built for native multimodal agents. The first model in this series is a ~400B parameter native vision…","featured":false,"products":["NeMo","NIM"],"sort_key":"2|develop native multimodal agents with qwen3.5 vlm using nvidia gpu-accelerated endpoints","created_at":1772184600,"content_type":"Blog","learning_levels":["Beginner","Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/nvidia-tensorrt-for-rtx-introduces-an-optimized-inference-ai-library-on-windows/","text":"Learn more"}],"title":"NVIDIA TensorRT for RTX Introduces an Optimized Inference AI Library on Windows 11","excerpt":"AI experiences are rapidly expanding on Windows in creativity, gaming, and productivity apps. There are various frameworks available to accelerate AI inference…","featured":false,"products":["TensorRT"],"sort_key":"2|nvidia tensorrt for rtx introduces an optimized inference ai library on windows 11","created_at":1747645200,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-language-neutralization-is-transforming-customer-service-contact-centers/","text":"Learn more"}],"title":"How Language Neutralization Is Transforming Customer Service Contact Centers","excerpt":"The powerful language neutralization offered by Infosys Cortex and based on NVIDIA Riva speech and translation enables contact center agents to communicate effectively...","featured":false,"products":["Riva"],"sort_key":"2|how language neutralization is transforming customer service contact centers","created_at":1685462314,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/automating-inference-optimizations-with-nvidia-tensorrt-llm-autodeploy/","text":"Learn more"}],"title":"Automating Inference Optimizations with NVIDIA TensorRT LLM AutoDeploy","excerpt":"NVIDIA TensorRT LLM enables developers to build high-performance inference engines for large language models (LLMs), but deploying a new architecture…","featured":false,"products":["Blackwell","TensorRT","TensorRT-LLM"],"sort_key":"2|automating inference optimizations with nvidia tensorrt llm autodeploy","created_at":1770633000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/unlock-massive-token-throughput-with-gpu-fractioning-in-nvidia-runai/","text":"Learn more"}],"title":"Unlock Massive Token Throughput with GPU Fractioning in NVIDIA Run:ai","excerpt":"As AI workloads scale, achieving high throughput, efficient resource usage, and predictable latency becomes essential. NVIDIA Run:ai addresses these challenges…","featured":false,"products":["NIM","Run:ai"],"sort_key":"2|unlock massive token throughput with gpu fractioning in nvidia run:ai","created_at":1771408800,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/boost-meeting-productivity-with-ai-powered-note-taking-and-summarization/","text":"Learn more"}],"title":"Boost Meeting Productivity with AI-Powered Note-Taking and Summarization","excerpt":"Meetings are the lifeblood of an organization. They foster collaboration and informed decision-making. They eliminate silos through brainstorming and problem…","featured":false,"products":["Riva"],"sort_key":"2|boost meeting productivity with ai-powered note-taking and summarization","created_at":1701262800,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/r2d2-scaling-multimodal-robot-learning-with-nvidia-isaac-lab/","text":"Learn more"}],"title":"R²D²: Scaling Multimodal Robot Learning with NVIDIA Isaac Lab","excerpt":"Building robust, intelligent robots requires testing them in complex environments. However, gathering data in the physical world is expensive, slow…","featured":false,"products":["Cosmos","Isaac Lab"],"sort_key":"2|r2d2: scaling multimodal robot learning with nvidia isaac lab","created_at":1770719400,"content_type":"Blog","learning_levels":["General Interest"]},{"links":[{"url":"https://developer.nvidia.com/blog/maximizing-gpu-utilization-with-nvidia-runai-and-nvidia-nim/","text":"Learn more"}],"title":"Maximizing GPU Utilization with NVIDIA Run:ai and NVIDIA NIM","excerpt":"Organizations deploying LLMs are challenged by inference workloads with different resource requirements. A small embedding model might use only a few gigabytes…","featured":false,"products":["NIM","Run:ai"],"sort_key":"2|maximizing gpu utilization with nvidia run:ai and nvidia nim","created_at":1772182800,"content_type":"Blog","learning_levels":["Advanced"]},{"links":[{"url":"https://catalog.ngc.nvidia.com/orgs/nvidia/teams/riva/models/parakeet-rnnt-riva-1-1b-unified-ml-cs-universal","text":"Learn more"}],"title":"RIVA Parakeet-RNNT-XXL-1.1B ASR Multilingual Universal Tokenizer","excerpt":"Multilingual Parakeet-RNNT-XXL-1.1B ASR model with Universal Tokenizer trained on ASR set 1.0","featured":false,"products":["Riva"],"sort_key":"2|riva parakeet-rnnt-xxl-1.1b asr multilingual universal tokenizer","created_at":1752784810,"content_type":"Model","learning_levels":["Advanced"]},{"links":[{"url":"https://developer.nvidia.com/blog/minimax-m2-7-advances-scalable-agentic-workflows-on-nvidia-platforms-for-complex-ai-applications/","text":"Learn more"}],"title":"MiniMax M2.7 Advances Scalable Agentic Workflows on NVIDIA Platforms for Complex AI Applications ","excerpt":"The release of MiniMax M2.7 adds enhancements to the popular MiniMax M2.5 model, built for agentic harnesses, and other complex use cases in fields such as…","featured":false,"products":["General","NIM"],"sort_key":"2|minimax m2.7 advances scalable agentic workflows on nvidia platforms for complex ai applications","created_at":1775930564,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/introducing-nemotron-3-super-an-open-hybrid-mamba-transformer-moe-for-agentic-reasoning/","text":"Learn more"}],"title":"Introducing Nemotron 3 Super: An Open Hybrid Mamba-Transformer MoE for Agentic Reasoning","excerpt":"Agentic AI systems need models with the specialized depth to solve dense technical problems autonomously. They must excel at reasoning, coding…","featured":false,"products":["NeMo","Nemotron","NIM","TensorRT-LLM"],"sort_key":"2|introducing nemotron 3 super: an open hybrid mamba-transformer moe for agentic reasoning","created_at":1773219600,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/scaling-token-factory-revenue-and-ai-efficiency-by-maximizing-performance-per-watt/","text":"Learn more"}],"title":"Scaling Token Factory Revenue and AI Efficiency by Maximizing Performance per Watt","excerpt":"In the AI era, power is the ultimate constraint, and every AI factory operates within a hard limit. This makes performance per watt—the rate at which power is…","featured":false,"products":["Blackwell","Blueprint","cuLitho","Grace CPU","Hopper","NVLink","Omniverse"],"sort_key":"2|scaling token factory revenue and ai efficiency by maximizing performance per watt","created_at":1774411200,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/developers-build-fast-and-reliable-robot-simulations-with-nvidia-omniverse-libraries/","text":"Learn more"}],"title":"Developers Build Fast and Reliable Robot Simulations with NVIDIA Omniverse Libraries","excerpt":"At SIGGRAPH, NVIDIA announced updates to the NVIDIA Omniverse libraries and Cosmos world foundation models (WFMs). Powered by OpenUSD, developers can access new…","featured":false,"products":["Cosmos","Isaac Lab","Isaac Sim","Omniverse"],"sort_key":"2|developers build fast and reliable robot simulations with nvidia omniverse libraries","created_at":1754899200,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/nvidia-blackwell-delivers-world-record-deepseek-r1-inference-performance/","text":"Learn more"}],"title":"NVIDIA Blackwell Delivers World-Record DeepSeek-R1 Inference Performance","excerpt":"NVIDIA announced world-record DeepSeek-R1 inference performance at NVIDIA GTC 2025. A single NVIDIA DGX system with eight NVIDIA Blackwell GPUs can achieve over…","featured":false,"products":["Blackwell","TensorRT","TensorRT-LLM"],"sort_key":"2|nvidia blackwell delivers world-record deepseek-r1 inference performance","created_at":1742294502,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/building-the-ai-grid-with-nvidia-orchestrating-intelligence-everywhere/","text":"Learn more"}],"title":"Building the AI Grid with NVIDIA: Orchestrating Intelligence Everywhere ","excerpt":"AI-native services are exposing a new bottleneck in AI infrastructure: As millions of users, agents, and devices demand access to intelligence…","featured":false,"products":["Holoscan","Maxine","Metropolis","Riva"],"sort_key":"2|building the ai grid with nvidia: orchestrating intelligence everywhere","created_at":1773742400,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/enhancing-customer-experience-in-telecom-with-nvidia-customized-speech-ai/","text":"Learn more"}],"title":"Enhancing Customer Experience in Telecom with NVIDIA Customized Speech AI","excerpt":"Learn why conversational AI systems are essential and why it is important to have a high level of transcription accuracy for optimal performance in downstream tasks.","featured":false,"products":["Riva"],"sort_key":"2|enhancing customer experience in telecom with nvidia customized speech ai","created_at":1685433600,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/develop-custom-physical-ai-foundation-models-with-nvidia-cosmos-predict-2/","text":"Learn more"}],"title":"Develop Custom Physical AI Foundation Models with NVIDIA Cosmos Predict-2","excerpt":"Building smarter robots and autonomous vehicles (AVs) starts with physical AI models that understand real-world dynamics. These models serve two critical roles…","featured":false,"products":["Cosmos"],"sort_key":"2|develop custom physical ai foundation models with nvidia cosmos predict-2","created_at":1749614400,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/introducing-riva-a-gpu-accelerated-sdk-for-developing-speech-ai-applications/","text":"Learn more"}],"title":"Introducing NVIDIA Riva: A GPU-Accelerated SDK for Developing Speech AI Applications","excerpt":"Learn about the Riva SDK and its use in developing speech AI applications. We also discuss Riva’s architecture, key features, and components for building speech AI...","featured":false,"products":["Riva","TensorRT","Triton Inference Server","Dynamo"],"sort_key":"2|introducing nvidia riva: a gpu-accelerated sdk for developing speech ai applications","created_at":1670513839,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/low-code-building-blocks-for-speech-ai-robotics/","text":"Learn more"}],"title":"Low-Code Building Blocks for Speech AI Robotics","excerpt":"Learn how to add speech AI skills, like speech-to-text (STT) and text-to-speech (TTS), to your intelligent robotics application using low-code building blocks.","featured":false,"products":["Jetson Orin","Riva"],"sort_key":"2|low-code building blocks for speech ai robotics","created_at":1663846380,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/building-custom-atomistic-simulation-workflows-for-chemistry-and-materials-science-with-nvidia-alchemi-toolkit/","text":"Learn more"}],"title":"Building Custom Atomistic Simulation Workflows for Chemistry and Materials Science with NVIDIA ALCHEMI Toolkit","excerpt":"For decades, computational chemistry has faced a tug-of-war between accuracy and speed. Ab initio methods like density functional theory (DFT) provide high…","featured":false,"products":["NIM","PhysicsNeMo"],"sort_key":"2|building custom atomistic simulation workflows for chemistry and materials science with nvidia alchemi toolkit","created_at":1776159000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/nvidia-ising-introduces-ai-powered-workflows-to-build-fault-tolerant-quantum-systems/","text":"Learn more"}],"title":"NVIDIA Ising Introduces AI-Powered Workflows to Build Fault-Tolerant Quantum Systems","excerpt":"NVIDIA Ising is the world’s first family of open AI models for building quantum processors, launching with two model domains: Ising Calibration and Ising…","featured":false,"products":["CUDA-Q","cuQuantum","NIM"],"sort_key":"2|nvidia ising introduces ai-powered workflows to build fault-tolerant quantum systems","created_at":1776150956,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/24-7-simulation-loops-how-agentic-ai-keeps-subsurface-engineering-moving/","text":"Learn more"}],"title":"24/7 Simulation Loops: How Agentic AI Keeps Subsurface Engineering Moving","excerpt":"The subsurface industry is at a critical point in its digital evolution. For decades, unlocking reservoir potential has relied on experts performing essential…","featured":false,"products":["NeMo","NeMo Retriever","Nemotron","NIM"],"sort_key":"2|24/7 simulation loops: how agentic ai keeps subsurface engineering moving","created_at":1777363200,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/model-quantization-post-training-quantization-using-nvidia-model-optimizer/","text":"Learn more"}],"title":"Model Quantization: Post-Training Quantization Using NVIDIA Model Optimizer","excerpt":"This post is the second of a three-part series. See also Model Quantization: Concepts, Methods, and Why It Matters and Model Quantization: Turn FP8 Checkpoints…","featured":false,"products":["RTX GPU","TensorRT"],"sort_key":"2|model quantization: post-training quantization using nvidia model optimizer","created_at":1778163486,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/nvidia-blackwell-sets-stac-ai-record-for-llm-inference-in-finance/","text":"Learn more"}],"title":"NVIDIA Blackwell Sets STAC-AI Record for LLM Inference in Finance","excerpt":"Large language models (LLMs) are revolutionizing the financial trading landscape by enabling sophisticated analysis of vast amounts of unstructured data to…","featured":false,"products":["Blackwell","GB200","Hopper","NVLink","TensorRT","TensorRT-LLM"],"sort_key":"2|nvidia blackwell sets stac-ai record for llm inference in finance","created_at":1779886800,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/optimize-supply-chain-decision-systems-using-nvidia-cuopt-agent-skills/","text":"Learn more"}],"title":"Optimize Supply Chain Decision Systems Using NVIDIA cuOpt Agent Skills","excerpt":"Modern supply chains operate under the constant pressures of fluctuating demand, volatile costs, constrained capacity, and interdependent decision-making.","featured":false,"products":["CUDA","cuOpt"],"sort_key":"2|optimize supply chain decision systems using nvidia cuopt agent skills","created_at":1777902905,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/building-token-metered-ai-services-on-telco-ai-factories/","text":"Learn more"}],"title":"Building Token‑Metered AI Services on Telco AI Factories","excerpt":"Telcos around the world are building sovereign AI factories based on the NVIDIA Cloud Partner (NCP) reference architecture, giving governments, enterprises…","featured":false,"products":["Blackwell","GB200","H100","Hopper","InfiniBand","NeMo","NIM","NVLink"],"sort_key":"2|building token-metered ai services on telco ai factories","created_at":1779352200,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-to-accelerate-protein-structure-prediction-at-proteome-scale/","text":"Learn more"}],"title":"How to Accelerate Protein Structure Prediction at Proteome-Scale","excerpt":"Proteins rarely function in isolation as individual monomers. Most biological processes are governed by proteins interacting with other proteins…","featured":false,"products":["CUDA","DGX","NIM","TensorRT"],"sort_key":"2|how to accelerate protein structure prediction at proteome-scale","created_at":1775721600,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-to-eliminate-pipeline-friction-in-ai-model-serving/","text":"Learn more"}],"title":"How to Eliminate Pipeline Friction in AI Model Serving","excerpt":"The path from a trained AI model to production should be smooth, but rarely is. Many teams invest weeks fine-tuning models, only to discover that exporting to a…","featured":false,"products":["TensorRT"],"sort_key":"2|how to eliminate pipeline friction in ai model serving","created_at":1778583600,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/deploy-long-context-reasoning-and-agentic-workflows-with-minimax-m3-on-nvidia-accelerated-infrastructure/","text":"Learn more"}],"title":"Deploy Long-Context Reasoning and Agentic Workflows with MiniMax M3 on NVIDIA Accelerated Infrastructure","excerpt":"As enterprise AI adoption scales, developers are increasingly forced to stitch together fragmented pipelines—separate models for text, vision…","featured":false,"products":["Blackwell","Dynamo","NeMo","TensorRT-LLM"],"sort_key":"2|deploy long-context reasoning and agentic workflows with minimax m3 on nvidia accelerated infrastructure","created_at":1781250197,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/inside-nvidia-halos-for-robotics-a-full-stack-functional-safety-system-for-physical-ai/","text":"Learn more"}],"title":"Inside NVIDIA Halos for Robotics: A Full-Stack Functional Safety System for Physical AI","excerpt":"Physical AI—robots working autonomously alongside people in factories, warehouses, hospitals, and homes—is arriving faster than most expected.","featured":false,"products":["Blueprint","DRIVE","Holoscan","IGX","Isaac Sim","Metropolis"],"sort_key":"2|inside nvidia halos for robotics: a full-stack functional safety system for physical ai","created_at":1782108000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/build-an-ai-scientist-for-life-science-discovery-with-nvidia-bionemo-agent-toolkit/","text":"Learn more"}],"title":"Build an AI Scientist for Life Science Discovery with NVIDIA BioNeMo Agent Toolkit","excerpt":"AI scientists are emerging as a new interface for scientific computing. These agents can read papers, write code, generate hypotheses, call APIs, inspect files…","featured":false,"products":["BioNeMo","NIM"],"sort_key":"2|build an ai scientist for life science discovery with nvidia bionemo agent toolkit","created_at":1782196200,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/build-speech-ai-in-multiple-languages-and-train-large-language-models-with-the-latest-from-riva-and-nemo-megatron/","text":"Learn more"}],"title":"Build Speech AI in Multiple Languages and Train Large Language Models with the Latest from Riva and NeMo Framework","excerpt":"Read a recap of conversational AI announcements from NVIDIA GTC.","featured":false,"products":["NeMo Framework","Riva"],"sort_key":"2|build speech ai in multiple languages and train large language models with the latest from riva and nemo framework","created_at":1648458000,"content_type":"Blog","learning_levels":[]},{"links":[{"url":"https://developer.nvidia.com/blog/run-diffusiongemma-on-nvidia-for-developer-ready-high-throughput-text-generation/","text":"Learn more"}],"title":"Run DiffusionGemma on NVIDIA for Developer-Ready, High-Throughput Text Generation","excerpt":"Developers building real-time AI—such as chat assistants, copilots, and agentic workflows—are often constrained by token-by-token generation speed.","featured":false,"products":["DGX","H100","NIM","RTX GPU"],"sort_key":"2|run diffusiongemma on nvidia for developer-ready, high-throughput text generation","created_at":1781265394,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-to-post-train-autonomous-vehicle-models-in-closed-loop-with-nvidia-alpamayo/","text":"Learn more"}],"title":"How to Post-Train Autonomous Vehicle Models in Closed-Loop with NVIDIA Alpamayo","excerpt":"Developing autonomous vehicle (AV) policies requires bridging an important gap between training and deployment. Vision-language-action (VLA) models that can…","featured":false,"products":["Cosmos"],"sort_key":"2|how to post-train autonomous vehicle models in closed-loop with nvidia alpamayo","created_at":1780264155,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/develop-physical-ai-reasoning-world-and-action-models-with-nvidia-cosmos-3/","text":"Learn more"}],"title":"Develop Physical AI Reasoning, World, and Action Models with NVIDIA Cosmos 3","excerpt":"Physical AI systems must understand the real world before they can act within it. Robots, autonomous vehicles, and smart spaces need to understand what’s…","featured":false,"products":["Cosmos"],"sort_key":"2|develop physical ai reasoning, world, and action models with nvidia cosmos 3","created_at":1780263838,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/build-your-own-transaction-foundation-model-for-financial-intelligence/","text":"Learn more"}],"title":"Build Your Own Transaction Foundation Model for Financial Intelligence","excerpt":"Every swipe, transfer, and payment on a modern financial network encodes a pattern of human behavior. Transaction data is one of the richest signals an…","featured":false,"products":["CUDA","NeMo","RAPIDS"],"sort_key":"2|build your own transaction foundation model for financial intelligence","created_at":1781616608,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/enable-real-time-ai-for-high-speed-data-acquisition-with-daqiri/","text":"Learn more"}],"title":"Enable Real-Time AI for High-Speed Data Acquisition with DAQIRI","excerpt":"When AlphaFold2 revolutionized drug discovery in 2020, its success relied entirely on the roughly 170,000 protein structures collected by scientists since 1971…","featured":false,"products":["ConnectX","DGX","Holoscan","TensorRT"],"sort_key":"2|enable real-time ai for high-speed data acquisition with daqiri","created_at":1782115200,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/scaling-ai-inference-across-multiple-gpus-using-nvidia-tensorrt-with-multi-device-inference-support/","text":"Learn more"}],"title":"Scaling AI Inference Across Multiple GPUs Using NVIDIA TensorRT with Multi-Device Inference Support","excerpt":"Generative AI workloads are rapidly outgrowing the memory and compute budget of single GPUs. For inference developers building media generation pipelines…","featured":false,"products":["TensorRT"],"sort_key":"2|scaling ai inference across multiple gpus using nvidia tensorrt with multi-device inference support","created_at":1782380628,"content_type":"Blog","learning_levels":["Advanced"]},{"links":[{"url":"https://developer.nvidia.com/blog/build-next-gen-physical-ai-with-edge%e2%80%91first-llms-for-autonomous-vehicles-and-robotics/","text":"Learn more"}],"title":"Build Next-Gen Physical AI with Edge‑First LLMs for Autonomous Vehicles and Robotics","excerpt":"Physical AI is rapidly evolving, from next-generation software-defined autonomous vehicles (AVs) to humanoid robots. The challenge is no longer how to run a…","featured":false,"products":["Cosmos","DRIVE","Jetson","Nemotron","TensorRT","TensorRT-LLM"],"sort_key":"2|build next-gen physical ai with edge-first llms for autonomous vehicles and robotics","created_at":1773306000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/spotlight-naver-place-optimizes-slm-based-vertical-services-with-nvidia-tensorrt-llm/","text":"Learn more"}],"title":"Spotlight: NAVER Place Optimizes SLM-Based Vertical Services with NVIDIA TensorRT-LLM","excerpt":"NAVER is a popular South Korean search engine company that offers Naver Place, a geo-based service that provides detailed information about millions of…","featured":false,"products":["Hopper","TensorRT","TensorRT-LLM"],"sort_key":"2|spotlight: naver place optimizes slm-based vertical services with nvidia tensorrt-llm","created_at":1740736669,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/optimizing-inference-for-long-context-and-large-batch-sizes-with-nvfp4-kv-cache/","text":"Learn more"}],"title":"Optimizing Inference for Long Context and Large Batch Sizes with NVFP4 KV Cache","excerpt":"Quantization is one of the strongest levers for large-scale inference. By reducing the precision of weights, activations, and KV cache, we can reduce the memory…","featured":false,"products":["Blackwell","TensorRT"],"sort_key":"2|optimizing inference for long context and large batch sizes with nvfp4 kv cache","created_at":1765184400,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/optimizing-transformer-based-diffusion-models-for-video-generation-with-nvidia-tensorrt/","text":"Learn more"}],"title":"Optimizing Transformer-Based Diffusion Models for Video Generation with NVIDIA TensorRT","excerpt":"State-of-the-art image diffusion models take tens of seconds to process a single image. This makes video diffusion even more challenging…","featured":false,"products":["TensorRT"],"sort_key":"2|optimizing transformer-based diffusion models for video generation with nvidia tensorrt","created_at":1745235878,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/accelerating-bev-pooling-on-nvidia-gpus-for-physical-ai-applications/","text":"Learn more"}],"title":"Accelerating BEV Pooling on NVIDIA GPUs for Physical AI Applications","excerpt":"An increasingly common design pattern for autonomous vehicles (AVs), robotics, and spatial AI systems is bird’s-eye-view (BEV) perception.","featured":false,"products":["Blackwell","CUDA","Nsight Tools - Compute","RTX GPU","TensorRT"],"sort_key":"2|accelerating bev pooling on nvidia gpus for physical ai applications","created_at":1782293400,"content_type":"Blog","learning_levels":["Advanced"]},{"links":[{"url":"https://developer.nvidia.com/blog/double-pytorch-inference-speed-for-diffusion-models-using-torch-tensorrt/","text":"Learn more"}],"title":"Double PyTorch Inference Speed for Diffusion Models Using Torch-TensorRT","excerpt":"NVIDIA TensorRT is an AI inference library built to optimize machine learning models for deployment on NVIDIA GPUs. TensorRT targets dedicated hardware in…","featured":false,"products":["Blackwell","TensorRT"],"sort_key":"2|double pytorch inference speed for diffusion models using torch-tensorrt","created_at":1753362817,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/hardware-rooted-ai-security-that-wont-slow-you-down/","text":"Learn more"}],"title":"Hardware-Rooted AI Security That Won't Slow You Down","excerpt":"AI has transformed how organizations operate, driving unprecedented levels of productivity and innovation. However, AI adoption can be impeded by concerns…","featured":false,"products":["Blackwell","Dynamo","NVLink","TensorRT"],"sort_key":"2|hardware-rooted ai security that won't slow you down","created_at":1783002342,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/llm-benchmarking-fundamental-concepts/","text":"Learn more"}],"title":"LLM Inference Benchmarking: Fundamental Concepts","excerpt":"This is the first post in the large language model latency-throughput benchmarking series, which aims to instruct developers on common metrics used for LLM…","featured":false,"products":["NIM","TensorRT-LLM"],"sort_key":"2|llm inference benchmarking: fundamental concepts","created_at":1743588000,"content_type":"Blog","learning_levels":["Beginner","Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/nvidia-tensorrt-llm-multiblock-attention-boosts-throughput-by-more-than-3x-for-long-sequence-lengths-on-nvidia-hgx-h200/","text":"Learn more"}],"title":"NVIDIA TensorRT-LLM Multiblock Attention Boosts Throughput by More Than 3x for Long Sequence Lengths on NVIDIA HGX H200","excerpt":"Generative AI models are advancing rapidly. Every generation of models comes with a larger number of parameters and longer context windows. The Llama 2 series…","featured":false,"products":["HGX","TensorRT","TensorRT-LLM"],"sort_key":"2|nvidia tensorrt-llm multiblock attention boosts throughput by more than 3x for long sequence lengths on nvidia hgx h200","created_at":1732207998,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/building-an-analysis-ai-agent-for-industrial-alarm-management-with-nvidia-nemotron/","text":"Learn more"}],"title":"Building an Analysis AI Agent for Industrial Alarm Management with NVIDIA Nemotron","excerpt":"Industrial machinery generates more alarms than technicians can triage. For each important alarm requiring follow-up, the technician pulls historical context…","featured":false,"products":["Blueprint","CUDA","cuDF","NeMo Retriever","Nemotron","NIM"],"sort_key":"2|building an analysis ai agent for industrial alarm management with nvidia nemotron","created_at":1783418400,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/nvidia-tensorrt-llm-now-supports-recurrent-drafting-for-optimizing-llm-inference/","text":"Learn more"}],"title":"NVIDIA TensorRT-LLM Now Supports Recurrent Drafting for Optimizing LLM Inference","excerpt":"Recurrent drafting (referred to as ReDrafter) is a novel speculative decoding technique developed and open-sourced by Apple for large language model (LLM)…","featured":false,"products":["AI Foundation Models","TensorRT","TensorRT-LLM"],"sort_key":"2|nvidia tensorrt-llm now supports recurrent drafting for optimizing llm inference","created_at":1734514261,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/optimizing-qwen2-5-coder-throughput-with-nvidia-tensorrt-llm-lookahead-decoding/","text":"Learn more"}],"title":"Optimizing Qwen2.5-Coder Throughput with NVIDIA TensorRT-LLM Lookahead Decoding","excerpt":"Large language models (LLMs) that specialize in coding have been steadily adopted into developer workflows. From pair programming to self-improving AI agents…","featured":false,"products":["DGX","H100","H200","NIM","TensorRT-LLM"],"sort_key":"2|optimizing qwen2.5-coder throughput with nvidia tensorrt-llm lookahead decoding","created_at":1739528377,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/optimize-ai-inference-performance-with-nvidia-full-stack-solutions/","text":"Learn more"}],"title":"Optimize AI Inference Performance with NVIDIA Full-Stack Solutions","excerpt":"The explosion of AI-driven applications has placed unprecedented demands on both developers, who must balance delivering cutting-edge performance with managing…","featured":false,"products":["GB200","NIM","NVLink","NVSwitch","TensorRT","TensorRT-LLM"],"sort_key":"2|optimize ai inference performance with nvidia full-stack solutions","created_at":1737705600,"content_type":"Blog","learning_levels":["Beginner","Intermediate","Advanced"]},{"links":[{"url":"https://developer.nvidia.com/blog/llama-3-2-full-stack-optimizations-unlock-high-performance-on-nvidia-gpus/","text":"Learn more"}],"title":"Llama 3.2 Full-Stack Optimizations Unlock High Performance on NVIDIA GPUs","excerpt":"Meta recently released its Llama 3.2 series of vision language models (VLMs), which come in 11B parameter and 90B parameter variants.","featured":false,"products":["Hopper","Jetson","NIM","NVSwitch","TensorRT","TensorRT-LLM"],"sort_key":"2|llama 3.2 full-stack optimizations unlock high performance on nvidia gpus","created_at":1732003200,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/r2d2-improving-robot-manipulation-with-simulation-and-language-models/","text":"Learn more"}],"title":"R²D²: Improving Robot Manipulation with Simulation and Language Models","excerpt":"Robot manipulation systems struggle with changing objects, lighting, and contact dynamics when they move into dynamic real-world environments. On top of this…","featured":false,"products":["Cosmos"],"sort_key":"2|r2d2: improving robot manipulation with simulation and language models","created_at":1765530000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/nvidia-nim-1-4-ready-to-deploy-with-2-4x-faster-inference/","text":"Learn more"}],"title":"NVIDIA NIM 1.4 Ready to Deploy with 2.4x Faster Inference","excerpt":"The demand for ready-to-deploy high-performance inference is growing as generative AI reshapes industries. NVIDIA NIM provides production-ready microservice…","featured":false,"products":["NIM","TensorRT","TensorRT-LLM"],"sort_key":"2|nvidia nim 1.4 ready to deploy with 2.4x faster inference","created_at":1731688914,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://nvda.ws/40TBiFT#new_tab","text":"Learn more"}],"title":"Just Released: Tripy, a Python Programming Model For TensorRT","excerpt":"Experience high-performance inference, usability, intuitive APIs, easy debugging with eager mode, clear error messages, and more.","featured":false,"products":["TensorRT"],"sort_key":"2|just released: tripy, a python programming model for tensorrt","created_at":1739178520,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/accelerating-end-to-end-co-folding-performance-with-nvidia-bionemo-agent-toolkit/","text":"Learn more"}],"title":"Accelerating End-to-End Co-Folding Performance with NVIDIA BioNeMo Agent Toolkit","excerpt":"Biomolecular structure prediction and co-folding with models like OpenFold3 are now mainstream, large-scale workloads powering drug discovery and protein design.","featured":false,"products":["AI Enterprise","BioNeMo","CUDA","GB200","H100","NGC","NIM","TensorRT"],"sort_key":"2|accelerating end-to-end co-folding performance with nvidia bionemo agent toolkit","created_at":1783663200,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/make-long-running-nvidia-tensorrt-engine-builds-observable-and-cancelable-in-python-or-c/","text":"Learn more"}],"title":"Make Long-Running NVIDIA TensorRT Engine Builds Observable and Cancelable in Python or C++","excerpt":"A TensorRT engine build can take seconds to many minutes. Large strongly typed models, deep tactic search, and a cold timing cache on a brand-new GPU SKU can…","featured":false,"products":["TensorRT"],"sort_key":"2|make long-running nvidia tensorrt engine builds observable and cancelable in python or c++","created_at":1784712904,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/deploy-a-production-ready-nvidia-ai-q-blueprint-on-oracle-cloud-infrastructure/","text":"Learn more"}],"title":"Deploy a Production-Ready NVIDIA AI-Q Blueprint on Oracle Cloud Infrastructure","excerpt":"AI agents have changed a lot in the last two years. The first could only answer one question at a time. Then came multi-turn chat, where the model could keep…","featured":false,"products":["Blueprint"],"sort_key":"2|deploy a production-ready nvidia ai-q blueprint on oracle cloud infrastructure","created_at":1782475245,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/build-a-video-search-and-summarization-agent-with-nvidia-ai-blueprint/","text":"Learn more"}],"title":"Build a Video Search and Summarization Agent with NVIDIA AI Blueprint","excerpt":"This post was originally published July 29, 2024 but has been extensively revised with NVIDIA AI Blueprint information. Traditional video analytics applications…","featured":false,"products":["Cosmos","Nemotron","NIM"],"sort_key":"2|build a video search and summarization agent with nvidia ai blueprint","created_at":1736194800,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/synthetic-data-generation-for-financial-ai-research-with-nvidia-nemo/","text":"Learn more"}],"title":"Synthetic Data Generation for Financial AI Research with NVIDIA NeMo","excerpt":"Fine-tuning LLMs for financial natural language processing (NLP) is constrained by limited, imbalanced data. Real-world financial news overrepresents earnings…","featured":false,"products":["NeMo","NeMo Curator","Nemotron"],"sort_key":"2|synthetic data generation for financial ai research with nvidia nemo","created_at":1783600837,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/integrating-context-aware-video-ai-agents-into-enterprise-workflows/","text":"Learn more"}],"title":"Integrating Context-Aware Video AI Agents Into Enterprise Workflows","excerpt":"A video analytics AI agent that can perceive, reason, and act based on massive amounts of video footage must be integrated with existing workflows and…","featured":false,"products":["Blueprint","Metropolis"],"sort_key":"2|integrating context-aware video ai agents into enterprise workflows","created_at":1784192615,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-to-evaluate-general-purpose-robot-policies-for-real-world-deployment/","text":"Learn more"}],"title":"How to Evaluate General-Purpose Robot Policies for Real-World Deployment","excerpt":"Robotics foundation models have made remarkable progress. Today’s best systems can follow natural language instructions to pick, place, sort…","featured":false,"products":["Cosmos"],"sort_key":"2|how to evaluate general-purpose robot policies for real-world deployment","created_at":1783793297,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/post-train-nvidia-cosmos-3-in-one-day-using-agent-skills/","text":"Learn more"}],"title":"Post-Train NVIDIA Cosmos 3 in One Day Using Agent Skills","excerpt":"What if autonomous coding AI agents could push your vision reasoning models above 90% accuracy with almost no manual effort? When adapting vision reasoning…","featured":false,"products":["Cosmos","Metropolis","NIM","TAO Toolkit"],"sort_key":"2|post-train nvidia cosmos 3 in one day using agent skills","created_at":1784019600,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/ai-model-co-design-hardware-friendly-llm-design/","text":"Learn more"}],"title":"AI Model Co-Design: Hardware-Friendly LLM Design","excerpt":"AI performance comes down to three dimensions: Deployments must balance all three: High accuracy is wasted if responses are slow, and raw throughput means…","featured":false,"products":["Blackwell","TensorRT","TensorRT-LLM"],"sort_key":"2|ai model co-design: hardware-friendly llm design","created_at":1783676162,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/nvidia-ising-enables-fully-automated-quantum-computer-calibration-with-enhanced-in-context-learning/","text":"Learn more"}],"title":"NVIDIA Ising Enables Fully Automated Quantum Computer Calibration with Enhanced In-Context Learning","excerpt":"NVIDIA Ising Calibration is an open source vision language model (VLM) designed to interpret diagnostic outputs from quantum processors and determine how they…","featured":false,"products":["Blueprint"],"sort_key":"2|nvidia ising enables fully automated quantum computer calibration with enhanced in-context learning","created_at":1785142800,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/serve-qwen3-8-2-4t-a95b-a-2-4t-parameter-model-with-configurable-reasoning-on-nvidia-gb300-nvl72/","text":"Learn more"}],"title":"Serve Qwen3.8-2.4T-A95B, a 2.4T-Parameter Model, with Configurable Reasoning on NVIDIA GB300 NVL72","excerpt":"Alibaba released the open weights for Qwen3.8-2.4T-A95B (Qwen3.8-Max), its largest open-weight model, bringing near-frontier capabilities to the open ecosystem.","featured":false,"products":["Blackwell","Dynamo","NeMo"],"sort_key":"2|serve qwen3.8-2.4t-a95b, a 2.4t-parameter model, with configurable reasoning on nvidia gb300 nvl72","created_at":1786533793,"content_type":"Blog","learning_levels":["Beginner"]},{"links":[{"url":"https://developer.nvidia.com/blog/nvidia-vera-rubin-and-blackwell-set-a-new-standard-for-agentic-ai-performance-per-watt/","text":"Learn more"}],"title":"NVIDIA Vera Rubin and Blackwell Set a New Standard for Agentic AI Performance per Watt ","excerpt":"AI agents have expanded inference from single-turn interactions into multi-step workflows that reason, invoke tools, coordinate subagents…","featured":false,"products":["Blackwell","Dynamo","GB200","NeMo","Nemotron","TensorRT-LLM"],"sort_key":"2|nvidia vera rubin and blackwell set a new standard for agentic ai performance per watt","created_at":1787558405,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/generate-trajectories-reasoning-traces-and-auto-labels-with-nvidia-alpamayo-2-super/","text":"Learn more"}],"title":"Generate Trajectories, Reasoning Traces, and Auto-Labels with NVIDIA Alpamayo 2 Super","excerpt":"Autonomous vehicle (AV) development often relies on separate models for trajectory generation, high-level intent prediction, scene understanding…","featured":false,"products":["Cosmos","DRIVE"],"sort_key":"2|generate trajectories, reasoning traces, and auto-labels with nvidia alpamayo 2 super","created_at":1785830400,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-to-self-host-a-validated-ai-coding-assistant-with-nvidia-nemo-guardrails/","text":"Learn more"}],"title":"How to Self-Host a Validated AI Coding Assistant with NVIDIA NeMo Guardrails","excerpt":"Deploying an AI coding assistant in a regulated, sovereign, or source-sensitive environment, often comes with challenges. Three common issues are: the source…","featured":false,"products":["AI Workbench","NeMo","NeMo Guardrails","NIM"],"sort_key":"2|how to self-host a validated ai coding assistant with nvidia nemo guardrails","created_at":1785318405,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-ai-coding-agents-can-unlock-materials-simulation-with-nvidia-alchemi-toolkit/","text":"Learn more"}],"title":"How AI Coding Agents Can Unlock Materials Simulation with NVIDIA ALCHEMI Toolkit","excerpt":"Atomistic simulation requires three things: knowledge of the science, compute-efficient implementation of simulations, and accessible interfaces to the…","featured":false,"products":["CUDA","H200","NIM"],"sort_key":"2|how ai coding agents can unlock materials simulation with nvidia alchemi toolkit","created_at":1787050800,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/developing-healthcare-robotics-with-gpu-native-medical-physics-simulation/","text":"Learn more"}],"title":"Developing Healthcare Robotics with GPU-Native Medical Physics Simulation","excerpt":"Unlike autonomous driving or industrial robotics, healthcare robotics can’t rely on internet-scale data collection or unlimited real-world experimentation.","featured":false,"products":["Cosmos"],"sort_key":"2|developing healthcare robotics with gpu-native medical physics simulation","created_at":1785246561,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/post-train-nvidia-cosmos-3-edge-for-on-device-robot-control/","text":"Learn more"}],"title":"Post-Train NVIDIA Cosmos 3 Edge for On-Device Robot Control","excerpt":"Robots need policies that can adapt to their sensors, environments, and tasks while running on onboard computing hardware. World models offer a foundation for…","featured":false,"products":["Cosmos","Isaac Lab","Isaac Sim","Jetson"],"sort_key":"2|post-train nvidia cosmos 3 edge for on-device robot control","created_at":1787130000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/beyond-vlas-how-world-action-models-reshape-robot-manipulation/","text":"Learn more"}],"title":"Beyond VLAs: How World Action Models Reshape Robot Manipulation","excerpt":"A central challenge in robotics is building policies that generalize beyond the demonstrations they’re trained on. A policy that succeeds in a training scene…","featured":false,"products":["Cosmos"],"sort_key":"2|beyond vlas: how world action models reshape robot manipulation","created_at":1785834000,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/simplifying-model-serving-across-multiple-gpus-with-nvidia-tensorrt-multi-device-integration-in-nvidia-dynamo-triton/","text":"Learn more"}],"title":"Simplifying Model Serving Across Multiple GPUs with NVIDIA TensorRT Multi-Device Integration in NVIDIA Dynamo-Triton","excerpt":"The compute and memory demands of generative AI increasingly exceed what a single GPU can provide. NVIDIA TensorRT multi-device inference is a new capability…","featured":false,"products":["Cosmos","Dynamo-Triton","TensorRT"],"sort_key":"2|simplifying model serving across multiple gpus with nvidia tensorrt multi-device integration in nvidia dynamo-triton","created_at":1790002266,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/deploy-an-open-model-from-checkpoint-to-inference-in-two-commands-with-nvidia-tensorrt-model-connect/","text":"Learn more"}],"title":"Deploy an Open Model from Checkpoint to Inference in Two Commands with NVIDIA TensorRT Model Connect","excerpt":"Open AI models are evolving faster than ever, but bringing them into native applications can still require model-specific conversion, preprocessing…","featured":false,"products":["TensorRT"],"sort_key":"2|deploy an open model from checkpoint to inference in two commands with nvidia tensorrt model connect","created_at":1787911588,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/tensorrt-edge-llm-completes-the-mlperf-edge-agentic-benchmark-6-4x-faster-on-jetson-agx-thor/","text":"Learn more"}],"title":"TensorRT Edge-LLM Completes the MLPerf Edge Agentic Benchmark 6.4x Faster on Jetson AGX Thor","excerpt":"AI agents are moving from cloud data centers to vehicles, robots, and other edge devices. Unlike a chatbot that answers a single prompt, an agent works through…","featured":false,"products":["Jetson","TensorRT","TensorRT-LLM"],"sort_key":"2|tensorrt edge-llm completes the mlperf edge agentic benchmark 6.4x faster on jetson agx thor","created_at":1789565827,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/lower-the-cost-of-building-and-running-visual-ai-agents-with-nvidia-vss-blueprint-3-3/","text":"Learn more"}],"title":"Lower the Cost of Building and Running Visual AI Agents with NVIDIA VSS Blueprint 3.3","excerpt":"Vision-language models have made it possible to build visual AI agents that understand video at production scale. The harder problem is turning that capability…","featured":false,"products":["Cosmos","Metropolis","Nemotron"],"sort_key":"2|lower the cost of building and running visual ai agents with nvidia vss blueprint 3.3","created_at":1790681709,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-full-stack-nim-optimizations-deliver-2-5x-more-users-on-nemotron-3-ultra/","text":"Learn more"}],"title":"How Full-Stack NIM Optimizations Deliver 2.5x More Users on Nemotron 3 Ultra","excerpt":"Deploying a large language model is only the first step toward production-ready serving. Production teams also need to serve as many concurrent users as…","featured":false,"products":["Nemotron","NIM"],"sort_key":"2|how full-stack nim optimizations deliver 2.5x more users on nemotron 3 ultra","created_at":1789034132,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/experiment-with-qwen3-8-flash-next-on-nvidia-gb300-nvl72-for-agentic-coding/","text":"Learn more"}],"title":"Experiment with Qwen3.8-Flash-Next on NVIDIA GB300 NVL72 for Agentic Coding","excerpt":"Alibaba released the model weights for Qwen3.8-Flash-Next as a preview of the upcoming Qwen4 architecture for developers to experiment with and evaluate.","featured":false,"products":["Blackwell","NeMo"],"sort_key":"2|experiment with qwen3.8-flash-next on nvidia gb300 nvl72 for agentic coding","created_at":1787738832,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/how-to-use-ai-agents-to-prepare-3d-scenes-for-simulation/","text":"Learn more"}],"title":"How to Use AI Agents to Prepare 3D Scenes for Simulation","excerpt":"Agentic AI workflows can be used to prepare and validate digital twins for physical AI systems. Agents can inspect 3D scenes, author simulation-relevant data in…","featured":false,"products":["Isaac Lab","Isaac Sim","NeMo","Nemotron","Omniverse"],"sort_key":"2|how to use ai agents to prepare 3d scenes for simulation","created_at":1789575633,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/benchmarking-llm-inference-at-scale-with-aiperf/","text":"Learn more"}],"title":"Benchmarking LLM Inference at Scale with AIPerf","excerpt":"You’re deploying a model on a system. It starts up, prompts are getting responses. Now the hard question: Is this fast? Your instincts might lead you to send…","featured":false,"products":["AGX","Jetson","TensorRT","TensorRT-LLM"],"sort_key":"2|benchmarking llm inference at scale with aiperf","created_at":1789733081,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://catalog.ngc.nvidia.com/orgs/nvidia/teams/riva/models/speechtotext_ar_ar_lm","text":"Learn more"}],"title":"Riva ASR Arabic LM","excerpt":"Base Arabic 4-gram LM","featured":false,"products":["Riva"],"sort_key":"2|riva asr arabic lm","created_at":1681842221,"content_type":"Model","learning_levels":["Advanced"]},{"links":[{"url":"https://developer.nvidia.com/blog/ai-native-by-design-lessons-learned-from-building-nvidia-tensorrt-model-connect/","text":"Learn more"}],"title":"AI Native by Design: Lessons Learned from Building NVIDIA TensorRT Model Connect","excerpt":"Parallel work, model-family isolation, reversible changes, and GPU-backed validation shaped an open source project designed around coding agents NVIDIA TensorRT…","featured":false,"products":["TensorRT"],"sort_key":"2|ai native by design: lessons learned from building nvidia tensorrt model connect","created_at":1790683851,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/fine-tuning-nvidia-nemotron-for-saudi-arabic-dialects-with-a-path-to-other-languages/","text":"Learn more"}],"title":"Fine-Tuning NVIDIA Nemotron for Saudi Arabic Dialects, with a Path to Other Languages","excerpt":"Automatic speech recognition must handle how people actually speak, not only the languages and styles that dominate pretraining data.","featured":false,"products":["A100","Blackwell","NeMo Curator"],"sort_key":"2|fine-tuning nvidia nemotron for saudi arabic dialects, with a path to other languages","created_at":1790805600,"content_type":"Blog","learning_levels":["Intermediate"]},{"links":[{"url":"https://developer.nvidia.com/blog/build-local-ai-apps-with-c-and-nvidia-tensorrt-rtx-samples/","text":"Learn more"}],"title":"Build Local AI Apps with C++ and NVIDIA TensorRT RTX Samples","excerpt":"Adding AI models to local applications requires a portable model format, a reliable runtime, and acceleration that works across target systems.","featured":false,"products":["TensorRT"],"sort_key":"2|build local ai apps with c++ and nvidia tensorrt rtx samples","created_at":1790852367,"content_type":"Blog","learning_levels":["Intermediate"]}]