Simulating Realistic Traffic Behavior with a Bi-Level Imitation Learning AI Model
From last-minute cut-ins to impromptu U-turns, human drivers can be incredibly unpredictable. This unpredictability stems from the complex nature of human...
Differentiable Slang easily integrates with existing codebases—from Python, PyTorch, and CUDA to HLSL—to aid multiple computer graphics tasks and enable...
Differentiable Slang: A Shading Language for Renderers That Learn
NVIDIA just released a SIGGRAPH Asia 2023 research paper, SLANG.D: Fast, Modular and Differentiable Shader Programming. The paper shows how a single language...
Accelerated Encrypted Execution of General Purpose Applications
The advent of cloud computing has ushered in a paradigm shift in our data storage and utilization practices. Businesses can bypass the complexities of managing...
Designing Deep Networks to Process Other Deep Networks
Deep neural networks (DNNs) are the go-to model for learning functions from data, such as image classifiers or language models. In recent years, deep models...
Modeling Earth’s Atmosphere with Spherical Fourier Neural Operators
Machine learning-based weather prediction has emerged as a promising complement to traditional numerical weather prediction (NWP) models. Models such as NVIDIA...
Recreate High-Fidelity Digital Twins with Neural Kernel Surface Reconstruction
Reconstructing a smooth surface from a point cloud is a fundamental step in creating digital twins of real-world objects and scenes. Algorithms for surface...
Neuralangelo by NVIDIA Research Reconstructs 3D Scenes from 2D Videos
A new model generates 3D reconstructions using neural networks, turns 2D video clips into detailed 3D structures — generating lifelike virtual replicas of...
Transferring Industrial Robot Assembly Tasks from Simulation to Reality
Simulation is an essential tool for robots learning new skills. These skills include perception (understanding the world from camera images), planning...
Towards Environment-specific Base Stations: AI/ML-driven Neural 5G NR Multi-user MIMO Receiver
At this year’s Mobile World Congress (MWC), NVIDIA showcased a neural receiver for a 5G New Radio (NR) uplink multi-user MIMO scenario, which could be seen...
AutoDMP Optimizes Macro Placement for Chip Design with AI and GPUs
Most modern digital chips integrate large numbers of macros in the form of memory blocks or analog blocks, like clock generators. These macros are often much...
Introducing NVIDIA Aerial Research Cloud for Innovations in 5G and 6G
NVIDIA introduced Aerial Research Cloud, the first fully programmable 5G and 6G network research sandbox, which enables researchers to rapidly simulate,...
Turn 2D Images into Immersive 3D Scenes with NVIDIA Instant NeRF in VR
Thousands of developers and content creators have built stunning 3D visuals with NVIDIA Instant NeRF, a rendering tool that turns a set of static images into a...
