Ashish Sardana

Ashish Sardana is an applied machine learning engineer specializing in multimodal conversational and recommendation systems. His current research interests include mechanistic interpretability and preference alignment.

Posts by Ashish Sardana

Trustworthy AI / Cybersecurity Apr 09, 2025

Prevent LLM Hallucinations with the Cleanlab Trustworthy Language Model in NVIDIA NeMo Guardrails

As more enterprises integrate LLMs into their applications, they face a critical challenge: LLMs can generate plausible but incorrect responses, known as... 9 MIN READ

Conversational AI / NLP Oct 28, 2022

Making an NVIDIA Riva ASR Service for a New Language

Speech AI is the ability of intelligent systems to communicate with users using a voice-based interface, which has become ubiquitous in everyday life. People... 13 MIN READ

Trustworthy AI / Cybersecurity Oct 04, 2022

Optimizing Fraud Detection in Financial Services with Graph Neural Networks and NVIDIA GPUs

Fraud is a major problem for many financial services firms, costing billions of dollars each year, according to a recent Federal Trade Commission report.... 22 MIN READ

Computer Vision / Video Analytics Dec 02, 2021

Accelerating Inference Up to 6x Faster in PyTorch with Torch-TensorRT

I'm excited about Torch-TensorRT, the new integration of PyTorch with NVIDIA TensorRT, which accelerates the inference with one line of code. PyTorch is a... 8 MIN READ