Join NVIDIA at NeurIPS 2024

December 10–15
Vancouver Convention Center
Vancouver, BC

Intro
Papers
Resources & Community

Intro
Papers
Resources & Community

Discover What’s Possible With NVIDIA AI

At the forefront of AI innovation, NVIDIA continues to push the boundaries of technology in machine learning, self-driving cars, robotics, graphics, simulation, and more.

NVIDIA Research at CoRL

Our accepted papers feature a range of groundbreaking research. From alias-free general adversarial networks (GANs) that create photorealistic images to semantic segmentation with transformers, explore the exceptional work we’re bringing to the NeurIPS community.

* Denotes equal contribution to the paper.

ESPACE: Dimensionality Reduction of Activations for Model Compression

Charbel Sakr, Brucek Khailany

Pricing and Competition for Generative AI

Rafid Mahmood

Molecule Generation With Fragment Retrieval Augmentation

Seul Lee · Karsten Kreis · Srimukh Veccham · Meng Liu · Danny Reidenbach · Saee Paliwal · Arash Vahdat · Weili Nie

L4GM: Large 4D Gaussian Reconstruction Model

Jiawei Ren · Cheng Xie · Ashkan Mirzaei · hanxue liang · xiaohui zeng · Karsten Kreis · Ziwei Liu · Antonio Torralba · Sanja Fidler · Seung Wook Kim · Huan Ling

SCube: Instant Large-Scale Scene Reconstruction Using VoxSplats

Xuanchi Ren · Yifan Lu · Hanxue Liang · Jay Zhangjie Wu · Huan Ling · Mike Chen · Sanja Fidler · Francis Williams · Jiahui Huang

AgentPoison: Red-Teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning

Zhaorun Chen · Zhen Xiang · Chaowei Xiao · Dawn Song · Bo Li

CosAE: Learnable Fourier Series for Image Restoration

Sifei Liu · Shalini De Mello · Jan Kautz

SpatialRGPT: Grounded Spatial Reasoning in Vision-Language Models

AnChieh Cheng · Hongxu Yin · Yang Fu · Qiushan Guo · Ruihan Yang · Jan Kautz · Xiaolong Wang · Sifei Liu

Compact Language Models via Pruning and Knowledge Distillation

Saurav Muralidharan · Sharath Turuvekere Sreenivas · Raviraj Joshi · Marcin Chochowski · Mostofa Patwary · Mohammad Shoeybi · Bryan Catanzaro · Jan Kautz · Pavlo Molchanov

MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models

Gongfan Fang · Hongxu Yin · Saurav Muralidharan · Greg Heinrich · Jeff Pool · Jan Kautz · Pavlo Molchanov · Xinchao Wang

QUEEN: QUantized Efficient ENcoding for Streaming Free-Viewpoint Videos

Sharath Girish · Tianye Li · Amrita Mazumdar · Abhinav Shrivastava · David Luebke · Shalini De Mello

DistillNeRF: Perceiving 3D Scenes From Single-Glance Images by Distilling Neural Fields and Foundation Model Features

Letian Wang · Seung Wook Kim · Jiawei Yang · Cunjun Yu · Boris Ivanovic · Steven Waslander · Yue Wang · Sanja Fidler · Marco Pavone · Peter Karkus

ChatQA: Surpassing GPT-4 on Conversational QA and RAG

Zihan Liu · Wei Ping · Rajarshi Roy · Peng Xu · Chankyu Lee · Mohammad Shoeybi · Bryan Catanzaro

RankRAG: Unifying Retrieval-Augmented Generation and Context Ranking in LLMs

Yue Yu · Wei Ping · Zihan Liu · Boxin Wang · Jiaxuan You · Chao Zhang · Mohammad Shoeybi · Bryan Catanzaro

Warped Diffusion: Solving Video Inverse Problems With Image Diffusion Models

Giannis Daras · Weili Nie · Karsten Kreis · Alex Dimakis · Morteza Mardani · Nikola Kovachki · Arash Vahdat

Aligning Target-Aware Molecule Diffusion Models With Exact Energy Optimization

Siyi Gu · Minkai Xu · Alexander Powers · Weili Nie · Tomas Geffner · Karsten Kreis · Jure Leskovec · Arash Vahdat · Stefano Ermon

Breaking the Multi-Task Barrier in Meta-Reinforcement Learning With Transformers

Jake Grigsby · Justin Sasek · Samyak Parajuli · Ikechukwu D. Adebi · Amy Zhang · Yuke Zhu

Hierarchical Selective Classification

Shani Goren · Ido Galil · Ran El-Yaniv

GRANOLA: Adaptive Normalization for Graph Neural Networks

Moshe Eliasof · Beatrice Bevilacqua · Carola-Bibiane Schönlieb · Haggai Maron

A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening

Guy Bar-Shalom · Yam Eitan · Fabrizio Frasca · Haggai Maron

Fast Encoder-Based 3D From Casual Videos via Point Track Processing

Yoni Kasten · Wuyue Lu · Haggai Maron

The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof

Derek Lim · Theo Putterman · Robin Walters · Haggai Maron · Stefanie Jegelka

Diffusion-Reward Adversarial Imitation Learning

Chun-Mao Lai · Hsiang-Chun Wang · Ping-Chun Hsieh · Frank Wang · Min-Hung Chen · Shao-Hua Sun

Learning From Teaching Regularization: Generalizable Correlations Should be Easy to Imitate

Can Jin · Tong Che · Hongwu Peng · Yiyuan Li · Dimitris Metaxas · Marco Pavone

Training an Open-Vocabulary Monocular 3D Detection Model Without 3D Data

Rui Huang · Henry Zheng · Yan Wang · Marco Pavone · Gao Huang

NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking

Daniel Dauner · Marcel Hallgarten · Tianyu Li · Xinshuo Weng · Zhiyu Huang · Zetong Yang · Hongyang Li · Igor Gilitschenski · Boris Ivanovic · Marco Pavone · Andreas Geiger · Kashyap Chitta

Large Scene Model: Real-time Unposed Images to Semantic 3D

Zhiwen Fan · Jian Zhang · Wenyan Cong · Peihao Wang · Renjie Li · Kairun Wen · Shijie Zhou · Achuta Kadambi · Zhangyang Wang · Danfei Xu · Boris Ivanovic · Marco Pavone · Yue Wang

Memorize What Matters: Emergent Scene Decomposition From Multitraverse

Yiming Li · Zehong Wang · Yue Wang · Zhiding Yu · Zan Gojcic · Marco Pavone · Chen Feng · Jose M. Alvarez

DiffuBox: Refining 3D Object Detection With Point Diffusion

Xiangyu Chen · Zhenzhen Liu · Katie Luo · Siddhartha Datta · Adhitya Polavaram · Yan Wang · Yurong You · Boyi Li · Marco Pavone · Wei-Lun (Harry) Chao · Mark Campbell · Bharath Hariharan · Kilian Weinberger

WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

Seungju Han · Kavel Rao · Allyson Ettinger · Liwei Jiang · Bill Yuchen Lin · Nathan Lambert · Nouha Dziri · Yejin Choi

Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions

Jonathan Hayase · Alisa Liu · Yejin Choi · Sewoong Oh · Noah Smith

Unpacking DPO and PPO: Disentangling Best Practices for Learning From Preference Feedback

Hamish Ivison · Yizhong Wang · Jiacheng Liu · Zeqiu Wu · Valentina Pyatkin · Nathan Lambert · Noah Smith · Yejin Choi · Hannaneh Hajishirzi

WildVision: Evaluating Vision-Language Models in the Wild With Human Preferences

Yujie Lu · Dongfu Jiang · Wenhu Chen · William Yang Wang · Yejin Choi · Bill Yuchen Lin

The Art of Saying No: Contextual Noncompliance in Language Models

Faeze Brahman · Sachin Kumar · Vidhisha Balachandran · Pradeep Dasigi · Valentina Pyatkin · Abhilasha Ravichander · Sarah Wiegreffe · Nouha Dziri · Khyathi Chandu · Jack Hessel · Yulia Tsvetkov · Noah Smith · Yejin Choi · Hannaneh Hajishirzi

Towards Visual Text Design Transfer Across Languages

Yejin Choi · Jiwan Chung · Sumin Shim · Giyeong Oh · Youngjae Yu

WildTeaming at Scale: From in-the-Wild Jailbreaks to (Adversarially) Safer Language Models

Liwei Jiang · Kavel Rao · Seungju Han · Allyson Ettinger · Faeze Brahman · Sachin Kumar · Niloofar Mireshghallah · Ximing Lu · Maarten Sap · Nouha Dziri · Yejin Choi

MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset With One Trillion Tokens

Anas Awadalla · Le Xue · Oscar Lo · Manli Shu · Hannah Lee · Etash Guha · Sheng Shen · Mohamed Awadalla · Silvio Savarese · Caiming Xiong · Ran Xu · Yejin Choi · Ludwig Schmidt

ActionAtlas: A VideoQA Benchmark for Fine-Grained Action Recognition

Mohammadreza (Reza) Salehi · Jae Sung Park · Aditya Kusupati · Ranjay Krishna · Yejin Choi · Hannaneh Hajishirzi · Ali Farhadi

SGLang: Efficient Execution of Structured Language Model Programs

Lianmin Zheng · Liangsheng Yin · Zhiqiang Xie · Chuyue (Livia) Sun · Jeff Huang · Cody Hao Yu · Shiyi Cao · Christos Kozyrakis · Ion Stoica · Joseph Gonzalez · Clark Barrett · Ying Sheng

BitDelta: Your Fine-Tune May Only Be Worth One Bit

James Liu · Guangxuan Xiao · Kai Li · Jason Lee · Song Han · Tri Dao · Tianle Cai

QueST: Self-Supervised Skill Abstractions for Learning Continuous Control

Atharva Anil Mete · Haotian Xue · Albert Wilcox · Yongxin Chen · Animesh Garg

Personalizing Reinforcement Learning From Human Feedback With Variational Preference Learning

Sriyash Poddar · Yanming Wan · Hamish Ivison · Abhishek Gupta · Natasha Jaques

Transferable Reinforcement Learning via Generalized Occupancy Models

Chuning Zhu · Xinqi Wang · University Washington · Simon Du · Abhishek Gupta

Sim-to-Real Transfer Can Make Naive Exploration Efficient in Reinforcement Learning

Andrew Wagenmaker · Kevin Huang · Liyiming Ke · Kevin Jamieson · Abhishek Gupta

Learning to Cooperate With Humans Using Generative Agents

Yancheng Liang · Daphne Chen · Abhishek Gupta · Simon Du · Natasha Jaques

Pretraining Codomain Attention Neural Operators for Solving Multiphysics PDEs

Md Ashiqur Rahman · Robert Joseph George · Mogab Elleithy · Daniel Leibovici · Zongyi Li · Boris Bonev · Colin White · Julius Berner · Raymond A. Yeh · Jean Kossaifi · Kamyar Azizzadenesheli · Animashree Anandkumar

Unveiling the Power of Diffusion Features For Personalized Segmentation and Retrieval

Dvir Samuel · Rami Ben-Ari · Matan Levy · Nir Darshan · Gal Chechik

RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation

Jeongyeol Kwon · Shie Mannor · Constantine Caramanis · Yonathan Efroni

Load Less

NVIDIA Research

Discover our most recent AI research and the new capabilities deep learning brings to visual and audio applications. Explore the latest innovations and see how you can bring them into your own work.

Explore Here

NVIDIA Developer Resources and Community

Get Hands-on Training

Want to develop key skills in AI, OpenUSD, accelerated data science, or accelerated computing? Get hands-on instructor-led training from the NVIDIA Deep Learning Institute (DLI) and earn a certificate showcasing your subject-matter expertise.

See Workshops and Training

Access SDKs, Training, and Expert Events

Take advantage of 600+ SDKs, AI models, free training, forums, and tech resources to accelerate your work and advance your skills. For a limited time, we are offering a complimentary self-paced training course to new members of our NVIDIA Developer program. Seize this free opportunity to embrace the future of technology at our own pace. Join the Developer Program now and claim your course.

Join the NVIDIA Developer Program

NVIDIA Inception for Startups

NVIDIA Inception provides startups with access to the latest developer resources, preferred pricing on NVIDIA software and hardware, and exposure to the venture capital community. The program is free and available to tech startups of all stages.

Apply for the NVIDIA Inception Program

Autonomous Driving Solutions

The NVIDIA DRIVE® team is constantly innovating, developing end-to-end autonomous driving solutions that are transforming the industry

Check Out DRIVE Videos Check Out Chinese DRIVE Labs Videos

Like No Place You’ve Ever Worked

Working at NVIDIA, you’ll 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, you’ll experience it all. Plus, there’s a growing list of new opportunities every single day. Explore all of our open roles, including internships and new college graduate positions.

Learn more about our current job openings, as well as university jobs.

Explore Here