neurips-logo

NVIDIA at NeurIPS 2020

At the forefront of AI innovation, NVIDIA continues to push the boundaries of technology in machine learning, self-driving cars, robotics, graphics, and more. NVIDIA researchers will present 28 papers at NeurIPS from December 6 to December 12, 2020. Join us to see the latest advancements in research.

Introducing the NVIDIA Applied Research Acceleration Program

NVIDIA Applied Research Acceleration Program

Accelerating Applied Research and Innovation Together

The NVIDIA Applied Research Accelerator Program promotes innovation by supporting research with technical guidance, hardware, and funding grants for projects with the potential to make a real-world impact through deployment into GPU-accelerated applications.

LEARN MORE ›

LIKE NO PLACE
YOU’VE EVER WORKED

When you work at NVIDIA, you have the opportunity to solve some of the world’s hardest problems and discover never-before-seen ways to improve the quality of life for people everywhere. From healthcare to robots. Self-driving cars to blockbuster movies. And a growing list of new opportunities every single day. 

Explore all of our job openings, including internships and new college graduate positions, or join us for a live session to meet with our managers.

Register
Calling All Students

Calling All Students

Join the NVIDIA Developer Program and Enter Our NeurIPS Contest for a Chance to Win a GPU.

Excited about NeurIPS? Tweet the paper, workshop, or demo you’re most interested in checking out, tag @NVIDIAAI, and include #NeurIPS2020—you could win an NVIDIA® TITAN RTX™ GPU. The contest runs December 4–12 and is open to all students who have registered for the NVIDIA Developer Program with a verified university (.edu) email address. See full contest terms and conditions.

Not a member yet? JOIN NOW ›

Demos

AI Training Emulates Artwork with Limited Datasets

AI Training Emulates Artwork with Limited Datasets

The latest AI model uses generative adversarial networks to study images and emulate rare artwork using a small dataset from the Metropolitan Museum of Art. 

WATCH DEMO ›

NVIDIA Maxine Brings AI to Video Conferencing

NVIDIA Maxine Brings AI to Video Conferencing

New AI breakthroughs in video conferencing slash bandwidth use while making it possible to reanimate faces, correct gaze, and animate characters for immersive and engaging meetings.

WATCH DEMO ›

Real-Time Conversational AI at Scale

Real-Time Conversational AI at Scale

NVIDIA Jarvis offers state-of-the-art deep learning models and delivers intelligent, human-like responses in real time. Jarvis running at scale on GPUs is 2X faster and one-third the cost compared to models running on CPUs.

WATCH DEMO ›

The Factory of the Future

The Factory of the Future

NVIDIA Isaac™ accelerates the process of robotics development, simulation, and deployment. Watch robots demonstrate perception and keen motor skills in the factory.  

WATCH DEMO ›

NVIDIA DRIVE Sim Software Built on NVIDIA Omniverse

NVIDIA DRIVE Sim Software Built on NVIDIA Omniverse

NVIDIA DRIVE Sim™ software, now built on NVIDIA Omniverse™, shows how software-defined cars with AI cockpits and autonomous driving capabilities will transform transportation.

WATCH DEMO ›

NVIDIA Clara Guardian Virtual Patient Assistant

NVIDIA Clara Guardian Virtual Patient Assistant

The NVIDIA Clara™ Guardian virtual patient assistant uses conversational AI pre-trained models and NVIDIA Fleet Command™ to increase operational efficiency and improve patient satisfaction in smart hospitals. 

WATCH DEMO ›

Accepted Papers

Spotlights

NVAE: A Deep Hierarchical Variational Autoencoder

Arash Vahdat, Jan Kautz  |  Paper

A Causal View of Compositional Zero-Shot Recognition

Yuval Atzmon, Felix Kreuk, Uri Shalit, Gal Chechik​​  |  Paper

Curriculum by Smoothing​​​​​

Samarth Sinha, Animesh Garg, Hugo Larochelle​​​​​​  |  Paper

BONGARD-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning​

Weili Nie, Zhiding Yu, Lei Mao, Ankit Patel, Yuke Zhu, Anima Anandkumar​​​​​​​  |  Paper

ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks​

Shuxuan Guo, Jose M. Alvarez,  Mathieu Salzmann​​​​​​​  |  Paper

Training Generative Adversarial Networks with Limited Data​

Tero Karras, Miika Aittala, Janne Hellsten, Samuli Laine, Jaakko Lehtinen, Timo Aila​  |  Paper

Posters

Online Adaptation for Consistent Mesh Reconstruction in the Wild

Xueting Li, Sifei Liu, Shalini De Mello, Kihwan Kim, Xiaolong Wang, Ming-Hsuan Yang, Jan Kautz  |  Paper

Self-Learning Transformations for Improving Gaze and Head Redirection​

Yufeng Zheng, Seonwook Park, Xucong Zhang, Shalini De Mello, Otmar Hilliges  |  Paper

Convolutional Tensor-Train LSTM for Spatio-Temporal Learning

Jiahao Su, Wonmin Byeon, Jean Kossaifi, Furong Huang, Jan Kautz, Anima Anandkumar  |  Paper

Generative View Synthesis: From Single-View Semantics to Novel-View Images

Tewodros Habtegebrial, Varun Jampani, Orazio Gallo, Didier Stricker  |  Paper

On the Distance Between Two Neural Networks and the Stability of Learning

Jeremy Bernstein, Arash Vahdat, Yisong Yue, Ming-Yu Liu​  |  Paper

Accelerating Reinforcement Learning Through GPU Atari Emulation

Steven Dalton, Iuri Frosio, Michael Garland​  |  Paper

Neural FFTs for Universal Texture Image Synthesis​

Morteza Mardani, Guilin Liu, Aysegul Dundar, Edward (Shiqiu) Liu, Andrew Tao, Bryan Catanzaro​  |  Paper link coming soon

Set2Graph: Learning Graphs from Sets​​

Hadar Serviansky, Nimrod Segol, Jonathan Shlomi, Kyle Cranmer, Eilam Gross, Haggai Maron, Yaron Lipman​​​​  |  Paper

Online Planning with Lookahead Policies /​ Multi-Step Greedy and Approximate Real-Time Dynamic Programming​​​

Yonathan Efroni, Mohammad Ghavamzadeh, Shie Mannor​​​​​  |  Paper

Causal Discovery in Physical Systems from Videos​​​

Yunzhu Li, Antonio Torralba, Animashree Anandkumar, Dieter Fox, Animesh Garg​​​​​  |  Paper

Counterfactual Data Augmentation Using Locally Factored Dynamics​​​​

Silviu Pitis, Elliot Creager, Animesh Garg​​​​​​  |  Paper

Sparse Spectrum Warped Input Measures for Nonstationary Kernel Learning

Anthony Tompkins, Rafael Oliveira, Fabio Ramos​​​​​​​  |  Paper

Can Q-Learning with Graph Networks Learn a Generalizable Branching Heuristic for a SAT Solver?​

Vitaly Kurin, Saad Godil, Shimon Whitestone, Bryan Catanzaro​​​​​​​  |  Paper

Neural Networks with Recurrent Generative Feedback

Yujia Huang , James Gornet, Sihui Dai, Zhiding Yu, Tan Nguyen, Doris Tsao, Anima Anandkumar​​​​​​​  |  Paper

Learning Compositional Functions via Multiplicative Weight Updates

Jeremy Bernstein, Jiawei Zhao, Markus Meister, Ming-Yu Liu, Anima Anandkumar, Yisong Yue​​​​​​​  |  Paper

Learning Deformable Tetrahedral Meshes for 3D Reconstruction​

Jun Gao, Wenzheng Chen, Tommy Xiang, Alec Jacobson, Morgan McGuire, Sanja Fidler​​​​​​​  |  Paper

Variational Amodal Object Completion for Interactive Scene Editing​

Huan Ling, David Acuna, Karsten Kreis, Seung Kim, Sanja Fidler​​​​​​​  |  Paper link coming soon

Ultrahyperbolic Representation Learning

Marc Law, Jos Stam​​​​​​​  |  Paper

Self-Supervised​ Generative Adversarial Compression​

Chong Yu, Jeff Pool​​​​​​​  |  Paper

Multipole Graph Neural Operator for Parametric Partial Differential Equations

Zongyi Li ,Nikola Kovachki, Kamyar Azizzadenesheli, Burigede Liu, Andrew Stuart, Kaushik Bhattacharya, Anima Anandkumar​  |  Paper

GANSpace: Discovering Interpretable GAN Controls​

Erik Härkönen, Aaron Hertzmann, Jaakko Lehtinen, Sylvain Paris​  |  Paper

Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems​​

Ali Sahin Lale,Kamyar Azizzadenesheli, Babak Hassibi,· Anima Anandkumar​​  |  Paper

GPU Accelerated Exhaustive Search for Optimal Ensemble of Black-Box Optimization Algorithms

Jiwei Liu, Bojan Tunguz, Gilberto Titericz | Paper

Workshops

Black in AI

Black in AI is a place for sharing ideas, fostering collaborations, and discussing initiatives to increase the presence of black people in the field of artificial intelligence. Our initiatives include an academic positions program, events at various conferences related to AI, advocacy, and community building.  |  Workshop December 7, 2020

LatinX in AI

​The LatinX in AI (LXAI) bridges communities, academics, industry, and politicians working to further AI innovation and resources for LatinX individuals globally. We host research workshops at AI academic conferences and drive and support research, development, and infrastructure programs to boost innovation and capabilities of Latin Americans working in artificial intelligence.  |  Workshop December 7, 2020

Queer in AI

Queer in AI’s mission to make the AI and machine learning community one that welcomes, supports, and values queer scientists. We accomplish this by building a visible community of queer and ally AI and machine learning scientists through meetups, poster sessions, mentoring, and other initiatives.  |  Workshop December 8, 2020

Women in Machine Learning

​Women in Machine Learning (WiML) works to increase awareness and appreciation of the achievements of women in machine learning. Our programs help women build their technical confidence and their voice, and our publicity efforts help ensure that women in machine learning and their achievements are known in the community.  |   Workshop December 9, 2020

SVHRM

The goal of the Shared Visual Representations in Human and Machine Intelligence (SVRHM) workshop is to disseminate relevant, parallel findings in the fields of computational neuroscience, psychology, and cognitive science that may inform modern machine learning methods.  |  Workshop ​December 12, 2020

See the Leading AI and Data Science Startups

Over 6,500 of the world’s leading AI and data science startups are accelerated by NVIDIA Inception, a program that provides go-to-market support, expertise, and technology for the next generation of visionaries. See the NVIDIA Inception members sponsoring NeurIPS 2020.

Deci

Deci

Deep learning platform that gears up your trained neural networks to become production-grade solutions on any hardware, at scale.

LEARN MORE ›

Element AI

Element AI

AI-based automation platform that  improves efficiencies in retail, insurance, logistics, manufacturing and more.

LEARN MORE ›

Helm.ai

Helm.ai

Licensed AI software throughout the L2-L4 autonomous driving stack: perception, intent modeling, path planning and vehicle control.

LEARN MORE ›

Scale

Scale

High quality training and validation data for AI applications

LEARN MORE ›

Sign up to receive the latest news from NVIDIA.

Subscribe

Win Exciting Prizes from NVIDIA. In connection with NVIDIA Developer Program: GPU for Edu Sweepstakes, NVIDIA Corporation, on behalf of itself and its affiliates ("NVIDIA") is conducting a giveaway, subject to the Sweepstakes Official Rules set forth below.

NVIDIA Developer Program: GPU for Edu Sweepstakes - Official Rules

NO PURCHASE OR PAYMENT OF ANY KIND IS NECESSARY TO ENTER OR WIN THIS PROMOTION. A PURCHASE WILL NOT IMPROVE YOUR CHANCES OF WINNING. THIS PROMOTION IS VOID WHERE PROHIBITED BY LAW. OPEN ONLY TO LEGAL RESIDENTS OF CANADA (EXCLUDING THE PROVINCE OF QUEBEC) AND THE UNITED STATES OF AMERICA (EXCLUDING PUERTO RICO AND ITS OTHER TERRITORIES AND POSSESSIONS).

1. You must be a legal resident of CANADA AND THE UNITED STATES OF AMERICA (EXCLUDING PUERTO RICO AND ITS OTHER TERRITORIES AND POSSESSIONS) and you must be eighteen (18) or older to be eligible to participate. You must be a full-time student with a verified .edu email address to enter. This promotion is open to individuals only. No team entries and no corporate or institutional entries are permitted in this promotion. Employees of Sponsor, its affiliates, and their respective contractors, service providers and professional advisors connected with this promotion, as well as members of their immediate families and/or households, are NOT eligible to enter. PO box addresses are not eligible for shipping.

2. The prize of this promotion consists of the following: Up to 3 instant winners will each win (a) Titan RTX worth $2499 USD (value may vary for countries outside of the USA); Odds of winning depend on the number of eligible entries received. The winner of each prize may not substitute the prize for its cash equivalent. NVIDIA reserves the right to substitute any of the prizes with any article or service of similar or greater value at its sole discretion. Prize(s) may not be assigned or transferred.

3. To enter this promotion, you must register for an NVIDIA developer account with an .edu email. Each entrant will be allowed one (1) direct entry. All entries must be received no later than between 9:00 AM on December 4th, 2020, Pacific Daylight Time and 5:00 PM on December 12th, 2020, Pacific Daylight Time. 

4. The winners will be randomly drawn by a representative of NVIDIA, whose decision will be final and binding in all respects, from all entries in a random drawing. The winners will be notified by private message or email within twenty four (24) hours after the drawing. Each winner must respond to the notification email within two (2) days from the time the notification message or email is sent, or prize will be forfeited and will be awarded to an alternate winner.

5. By entering this promotion you expressly consent to NVIDIA's collection, processing and use of your personal information that you provide in connection with this promotion (including, but not limited to, disclosure of your name and state of residence on a winners list and making such list available to the public) and under the terms of NVIDIA’s privacy policy, which can be accessed at http://www.nvidia.com/object/privacy_policy.html.

6. NVIDIA makes no warranty or representation as to any of the prizes and is not liable if you experience technical difficulties, due to reasons not attributable to NVIDIA, including but not limited to manufacture defects, model incompatibility, and restrictions imposed by the manufacturer.

7. NVIDIA reserves the right to terminate this promotion if fraud, technical failures or any other factor beyond NVIDIA's reasonable control impairs the integrity of the promotion as determined by NVIDIA in its sole discretion. Online entries made with multiple e-mail addresses, under multiple identities or through the use of any other device or artifice to enter multiple times will be deemed invalid. If the winner is an online entrant, the winning online entry will be deemed to have been submitted by the authorized account holder of the e-mail address from which the entry was made. The authorized email account holder is deemed as the natural person who is assigned to an e-mail address by an internet access provider, service provider or other organization that is responsible for assigning e-mail addresses or the domain associated with the submitted e-mail address. NVIDIA shall not be responsible for incorrect or inaccurate transcription of entry information, technical malfunctions, lost/delayed data transmission, omission, interruption, deletion, defect, line failures of any telephone network, computer equipment, software, inability to access any online service or web site, inability to submit the online entry form, or any other error or malfunction, or any injury or damage to entrant’s or any other person’s computer related to or resulting from participation or downloading any materials in this sweepstakes, or for late, lost, stolen, postage due, illegible or misdirected entries. If this sweepstakes or any web site associated therewith (or any portion thereof) becomes corrupted or otherwise does not permit entry in the sweepstakes, or if infection by computer virus, bugs, tampering, unauthorized intervention, actions by entrants, fraud, technical failures, or any other causes, in NVIDIA’s sole opinion, corrupt or affect the administration, security, fairness, integrity, or proper operation of this contest, NVIDIA reserves the right, at its sole discretion, to disqualify any individual implicated in such action, and/or to cancel, terminate, modify or suspend this sweepstakes or any portion thereof. Any attempt by an entrant or any other individual to deliberately damage any online service or web site or undermine the legitimate operation of this sweepstakes is a violation of criminal and civil laws and should such an attempt be made, NVIDIA reserves the right to seek damages and/or other remedies from any such person to the fullest extent permitted by law.

8. The winner of this promotion is solely responsible for any and all applicable taxes and government charges that result from his/her receipt and/or use of the prize. NVIDIA reserves the right to withhold and deduct such taxes and charges from the prize, and request necessary documentation if and to the extent required by law.

9. The sponsor of this promotion is NVIDIA Corporation on behalf of itself and its affiliates.

10. These rules are governed by the laws of the State of Delaware, United States of America, without giving effect to conflicts of law rules. Entrants submit themselves to the exclusive jurisdiction of the state and federal courts sitting in Santa Clara, CA.

NVIDIA Corporation (Nasdaq: NVDA) is the worldwide leader in programmable graphics processor technologies. Visit NVIDIA online at: http://www.nvidia.com.

Research at NVIDIA
More
NVIDIA
Platforms
Products
Developers
Corporate