Our accepted papers featured a range of groundbreaking research. From domain-adversarial training to denoising diffusion generative adversarial networks (GANs), explore the exceptional work we brought to the ICLR community.
Check out the AI breakthroughs that NVIDIA researchers introduced at this year’s International Conference on Learning Representations (ICLR).
NVIDIA Research at ICLR
Virtual Presentations
Low-Budget Active Learning via Wasserstein Distance: An Integer Programming Approach
Rafid Mahmood · Sanja Fidler · Marc T. Law | Paper
Domain-Adversarial Training: A Game Perspective
David Acuna · Marc T. Law · Guojun Zhang · Sanja Fidler | Paper
Efficient Token Mixing for Transformers via Adaptive Fourier Neural Operators
John Guibas · Morteza Mardani · Zongyi Li · Andrew Tao · Anima Anandkumar · Bryan Catanzaro | Paper
RelViT: Concept-Guided Vision Transformer for Visual Relational Reasoning
Xiaojian Ma · Weili Nie · Zhiding Yu · Huaizu Jiang · chaowei Xiao · Yuke Zhu · Song-Chun Zhu · Anima Anandkumar | Paper
Score-Based Generative Modeling with Critically Damped Langevin Diffusion
Tim Dockhorn · Arash Vahdat · Karsten Kreis | Paper
Tackling the Generative Learning Trilemma with Denoising Diffusion GANs
Zhisheng Xiao · Karsten Kreis · Arash Vahdat | Paper
Learning Continuous Environment Fields via Implicit Functions
Xueting Li · Sifei Liu · Shalini De Mello · Xiaolong Wang · Ming-Hsuan Yang · Jan Kautz | Paper
Training and Resources
NVIDIA Developer Program
The NVIDIA Developer Program provides access to the advanced tools and training you need to successfully build applications on all NVIDIA technology platforms.
Unlock Your Startup’s Potential
NVIDIA Inception nurtures cutting-edge technology startups that are revolutionizing industries. The program offers go-to-market support, expertise, and technology—all tailored to a business’s evolution, no matter what size or funding stage they’re at.
NVIDIA Applied Research Accelerator Program
The NVIDIA Applied Research Accelerator Program supports research projects that have the potential to make a real-world impact through deployment into GPU-accelerated applications adopted by commercial and government organizations.
Accelerate 3D Deep Learning Research with Kaolin and Omniverse Kaolin App
The NVIDIA Omniverse™ Kaolin app is a powerful visualization tool that simplifies and accelerates 3D deep learning research using NVIDIA’s Kaolin PyTorch library. The Kaolin app leverages the Omniverse platform, Universal Scene Description (USD) format, and NVIDIA RTX™ rendering to visualize 3D outputs of any deep learning model as it’s training. Kaolin inspects 3D datasets to find inconsistencies, gain intuition, and render large synthetic datasets from collections of 3D data.
Explore AI, Omniverse, and Beyond at the GTC Keynote
At GTC 2022, NVIDIA CEO Jensen Huang unveiled NVIDIA’s new computing platforms, robotics advances, and breakthroughs in virtual collaboration that are transforming every industry.
Featured Demos
Your Most
Brilliant Work
Starts Here
The Developer Conference for the Era of AI
Sign up to receive the latest news from NVIDIA.