Best Paper Awards

​

2025

• Every Bit Helps: Achieving the Optimal Distortion with a Few Queries — Soroush Ebadian, Nisarg Shah — Outstanding Paper
• Efficient Rectification of Neuro-Symbolic Reasoning Inconsistencies by Abductive Reflection — Wen-Chao Hu, Wang-Zhou Dai, et al. — Outstanding Paper
• Revelations: A Decidable Class of POMDPs with Omega-Regular Objectives — Marius Belly, Nathanael Fijalkow, et al. — Outstanding Paper
• DivShift: Exploring Domain-Specific Distribution Shifts in Large-Scale Biodiversity Datasets — Elena Sierra, Lauren Gillespie, Moises Exposito Alonso — Outstanding Paper
• BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and RL — Artem Zholus, Maksim Kuznetsov, et al. — Outstanding Paper

​

2024

• Reliable Conflictive Multi-view Learning — Cai Xu, Jiajun Si, et al. — Outstanding Paper
• Proportional Aggregation of Preferences for Sequential Decision Making — Nikhil Chandak, Shashwat Goel, Dominik Peters — Outstanding Paper

​

2023

• Misspecification in Inverse Reinforcement Learning — Joar Skalse, Alessandro Abate — Outstanding Paper
• Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation — Yulu Gan, Yan Bai, et al. — Outstanding Student Paper

​

2022

• Certified Symmetry and Dominance Breaking for Combinatorial Optimisation — Bart Bogaerts, Stephan Gocht, et al. — Distinguished Paper
• Sampling-Based Robust Control of Autonomous Systems with Non-Gaussian Noise — Thom S. Badings, Alessandro Abate, et al. — Distinguished Paper

​

2021

• Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting — Haoyi Zhou, Shanghang Zhang, et al. — Outstanding Paper
• Exploration-Exploitation in Multi-Agent Learning: Catastrophe Theory Meets Game Theory — Stefanos Leonardos, Georgios Piliouras — Outstanding Paper

​

2025

• Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention — Jingyang Yuan, Huazuo Gao, et al. (DeepSeek/PKU) — Best Paper
• Fairness through Difference Awareness: Measuring Desired Group Discrimination in LLMs — Angelina Wang, Michelle Phan, et al. — Best Paper
• Language Models Resist Alignment: Evidence From Data Compression — Jiaming Ji, Kaile Wang, et al. — Best Paper
• AfriMed-QA: A Pan-African, Multi-Specialty, Medical QA Benchmark — Charles Nimo, Tobi Olatunji, et al. — Best Paper

​

2024

• Mission: Impossible Language Models — Julie Kallini, Isabel Papadimitriou, et al. — Best Paper
• Semisupervised Neural Proto-Language Reconstruction — Liang Lu, Peirong Xie, David R. Mortensen — Best Paper
• Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model — Ahmet Ustun, Viraat Aryabumi, et al. — Best Paper
• Deciphering Oracle Bone Language with Diffusion Models — Haisu Guan, Huanxin Yang, et al. — Best Paper

​

2023

• Do Androids Laugh at Electric Sheep? Humor “Understanding” Benchmarks from The New Yorker Caption Contest — Jack Hessel, Ana Marasovic, et al. — Best Paper

​

2022

• Learned Incremental Representations for Parsing — Nikita Kitaev, Thomas Lu, Dan Klein — Best Paper

​

2021

• Vocabulary Learning via Optimal Transport for Neural Machine Translation — Jingjing Xu, Hao Zhou, et al. — Best Paper

​

2025

• VGGT: Visual Geometry Grounded Transformer — Jianyuan Wang, Minghao Chen, et al. — Best Paper
• Neural Inverse Rendering from Propagating Light — Anagh Malik, Benjamin Attal, et al. — Best Student Paper
• Navigation World Models — Amir Bar, Gaoyue Zhou, et al. — Honorable Mention
• MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos — Zhengqi Li, Richard Tucker, et al. — Honorable Mention

​

2024

• Generative Image Dynamics — Zhengqi Li, Richard Tucker, et al. — Best Paper
• Rich Human Feedback for Text-to-Image Generation — Youwei Liang, Junfeng He, et al. — Best Paper
• Mip-Splatting: Alias-free 3D Gaussian Splatting — Zehao Yu, Anpei Chen, et al. — Best Student Paper
• BioCLIP: A Vision Foundation Model for the Tree of Life — Samuel Stevens, Jiaman Wu, et al. — Best Student Paper

​

2023

• Planning-oriented Autonomous Driving (UniAD) — Yihan Hu, Jiazhi Yang, et al. — Best Paper
• Visual Programming: Compositional Visual Reasoning without Training — Tanmay Gupta, Aniruddha Kembhavi — Best Paper

​

2022

• Learning to Solve Hard Minimal Problems — Petr Hruby, Timothy Duff, et al. — Best Paper
• EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points — Hansheng Chen, Pichao Wang, et al. — Best Student Paper
• Dual-Shutter Optical Vibration Sensing — Mark Sheinin, Dorian Chan, et al. — Honorable Mention

​

2021

• GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields — Michael Niemeyer, Andreas Geiger — Best Paper

​

2024

• Minimalist Vision with Freeform Pixels — Jeremy Klotz, Shree Nayar — Best Paper
• Rasterized Edge Gradients: Handling Discontinuities Differentially — Stanislav Pidhorskyi, Tomas Simon, et al. — Honorable Mention
• Concept Arithmetics for Circumventing Concept Inhibition in Diffusion Models — Vitali Petsiuk, Kate Saenko — Honorable Mention

​

2022

• On the Versatile Uses of Partial Distance Correlation in Deep Learning — Xingjian Zhen, Zihang Meng, et al. — Best Paper
• Pose-NDF: Modelling Human Pose Manifolds with Neural Distance Fields — Garvita Tiwari, Dimitrije Antic, et al. — Honorable Mention

​

2025

• Infini-gram mini: Exact n-gram Search at the Internet Scale with FM-Index — Hao Xu, Jiacheng Liu, et al. — Best Paper
• LingGym: How Far Are LLMs from Thinking Like Field Linguists? — Freda Shi, Changbing Yang, et al. — Outstanding Paper

​

2024

• Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method — Weichao Zhang, et al. — Best Paper
• An Image Speaks a Thousand Words, but Can Everyone Listen? On Image Transcreation for Cultural Relevance — Simran Khanuja, et al. — Best Paper
• KidLM: Advancing Language Models for Children — Mir Tafseer Nayeem, Davood Rafiei — Best Resource Paper

​

2023

• Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs Through a Global Prompt Hacking Competition — Sander V. Schulhoff, et al. — Best Paper

​

2022

• Abstract Visual Reasoning with Tangram Shapes — Anya Ji, Noriyuki Kojima, et al. — Best Paper

​

2021

• Visually Grounded Reasoning across Languages and Cultures — Fangyu Liu, Emanuele Bugliarello, et al. — Best Long Paper

​

2025

• BrickGPT: Generating Physically Stable and Buildable Brick Structures from Text — Ava Pun, Kangle Deng, et al. — Best Paper (Marr Prize)

​

2023

• Adding Conditional Control to Text-to-Image Diffusion Models (ControlNet) — Lvmin Zhang, Anyi Rao, Maneesh Agrawala — Best Paper (Marr Prize)
• Passive Ultra-Wideband Single-Photon Imaging — Mian Wei, Sotiris Nousias, et al. — Best Paper (Marr Prize)
• Segment Anything — Alexander Kirillov, Eric Mintun, et al. (Meta) — Honorable Mention
• Tracking Everything Everywhere All At Once — Qianqian Wang, Yen-Yu Chang, et al. — Honorable Mention

​

2021

• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows — Ze Liu, Yutong Lin, et al. — Best Paper (Marr Prize)

​

2025

• Safety Alignment Should be Made More Than Just a Few Tokens Deep — Xiangyu Qi, Ashwinee Panda, et al. — Outstanding Paper
• Learning Dynamics of LLM Finetuning — Yi Ren, Danica J. Sutherland — Outstanding Paper
• SAM 2: Segment Anything in Images and Videos — Nikhila Ravi, Valentin Gabeur, et al. (Meta) — Outstanding Paper
• Data Shapley in One Training Run — Jiachen T. Wang, Prateek Mittal, et al. — Honorable Mention

​

2024

• Generalization in Diffusion Models Arises from Geometry-Adaptive Harmonic Representations — Zahra Kadkhodaie, Florentin Guth, et al. — Outstanding Paper
• Learning Interactive Real-World Simulators — Sherry Yang, Yilun Du, et al. — Outstanding Paper
• Vision Transformers Need Registers — Timothee Darcet, Maxime Oquab, et al. — Outstanding Paper
• Protein Discovery with Discrete Walk-Jump Sampling — Nathan C. Frey, Dan Berenberg, et al. — Outstanding Paper

​

2023

• DreamFusion: Text-to-3D using 2D Diffusion — Ben Poole, Ajay Jain, et al. — Outstanding Paper
• Emergence of Maps in the Memories of Blind Navigation Agents — Erik Wijmans, Manolis Savva, et al. — Outstanding Paper
• Rethinking the Expressive Power of GNNs via Graph Biconnectivity — Bohang Zhang, Shengjie Luo, et al. — Outstanding Paper

​

2022

• Efficiently Modeling Long Sequences with Structured State Spaces (S4) — Albert Gu, Karan Goel, Christopher Re — Outstanding Paper
• Analytic-DPM: An Analytic Estimate of the Optimal Reverse Variance in Diffusion Models — Fan Bao, Chongxuan Li, et al. — Outstanding Paper
• Neural Collapse Under MSE Loss — X.Y. Han, Vardan Papyan, David L. Donoho — Outstanding Paper

​

2021

• Score-Based Generative Modeling through Stochastic Differential Equations — Yang Song, Jascha Sohl-Dickstein, et al. — Outstanding Paper
• Learning Mesh-Based Simulation with Graph Networks — Tobias Pfaff, Meire Fortunato, et al. — Outstanding Paper
• EigenGame: PCA as a Nash Equilibrium — Ian Gemp, Brian McWilliams, et al. — Outstanding Paper

​

2025

• CollabLLM: From Passive Responders to Active Collaborators — Shirley Wu, Michel Galley, et al. — Outstanding Paper
• Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions — Jaeyeon Kim, Kulin Shah, et al. — Outstanding Paper
• Roll the Dice & Look Before You Leap: Going Beyond the Creative Limits of Next-Token Prediction — Vaishnavh Nagarajan, Chen Wu, et al. — Outstanding Paper
• Score Matching with Missing Data — Josh Givens, Song Liu, Henry Reeve — Outstanding Paper
• Conformal Prediction as Bayesian Quadrature — Jake Snell, Thomas Griffiths — Outstanding Paper

​

2024

• Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution — Aaron Lou, Chenlin Meng, Stefano Ermon — Best Paper
• Considerations for Differentially Private Learning with Large-Scale Public Pretraining — Florian Tramer, Gautam Kamath, Nicholas Carlini — Best Paper

​

2023

• Learning-Rate-Free Learning by D-Adaptation — Aaron Defazio, Konstantin Mishchenko — Outstanding Paper
• A Watermark for Large Language Models — John Kirchenbauer, Jonas Geiping, et al. — Outstanding Paper
• Adapting to Game Trees in Zero-Sum Imperfect Information Games — Come Fiegel, Pierre Menard, et al. — Outstanding Paper

​

2022

• Understanding Dataset Difficulty with V-Usable Information — Kawin Ethayarajh, Yejin Choi, Swabha Swayamdipta — Outstanding Paper
• Monarch: Expressive Structured Matrices for Efficient and Accurate Training — Tri Dao, et al. — Outstanding Paper
• Learning Inverse Folding from Millions of Predicted Structures — Chloe Hsu, Robert Verkuil, et al. — Outstanding Paper

​

2021

• Understanding Self-Supervised Learning Dynamics without Contrastive Pairs — Yuandong Tian, Xinlei Chen, Surya Ganguli — Outstanding Paper
• Oops I Took A Gradient: Scalable Sampling for Discrete Distributions — Will Grathwohl, Kevin Swersky, et al. — Outstanding Paper

​

2024

• Online Combinatorial Optimization with Group Fairness Constraints — Negin Golrezaei, Rad Niazadeh, et al. — Distinguished Paper
• Online Learning of Capacity-Based Preference Models — Margot Herin, Patrice Perny, Nataliya Sokolovska — Distinguished Paper

​

2023

• Levin Tree Search with Context Models — Laurent Orseau, Marcus Hutter, Levi H. S. Lelis — Distinguished Paper
• SAT-Based PAC Learning of Description Logic Concepts — Balder ten Cate, Maurice Funk, et al. — Distinguished Paper

​

2022

• Plurality Veto: A Simple Voting Rule Achieving Optimal Metric Distortion — Fatih Kizilkaya, David Kempe — Distinguished Paper

​

2021

• Learning Generalized Unsolvability Heuristics for Classical Planning — Simon Stahlberg, Guillem Frances, Jendrik Seipp — Distinguished Paper

​

2025

• Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond) — Liwei Jiang, Yuanjun Chai, et al. — Best Paper
• Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free — Zihan Qiu, Zekun Wang, et al. (Alibaba Qwen) — Best Paper
• 1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities — Michal Bortkiewicz, et al. — Best Paper
• Why Diffusion Models Don’t Memorize: The Role of Implicit Dynamical Regularization — Tony Bonnaire, Raphael Urfin, et al. — Best Paper
• Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model? — Yang Yue, Zhiqi Chen, et al. — Best Paper Runner-Up
• Superposition Yields Robust Neural Scaling — Yizhou Liu, Ziming Liu, Jeff Gore — Best Paper Runner-Up

​

2024

• Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction — Keyu Tian, Yi Jiang, et al. — Best Paper
• Stochastic Taylor Derivative Estimator: Efficient Amortization for Arbitrary Differential Operators — Zekun Shi, Zheyuan Hu, et al. — Best Paper
• Rho-1: Not All Tokens Are What You Need — Zhenghao Lin, Zhibin Gou, et al. — Best Paper Runner-Up
• Guiding a Diffusion Model with a Bad Version of Itself — Tero Karras, Miika Aittala, et al. — Best Paper Runner-Up
• The PRISM Alignment Dataset — Hannah Rose Kirk, et al. — Best Paper (Datasets & Benchmarks)

​

2023

• Are Emergent Abilities of Large Language Models a Mirage? — Rylan Schaeffer, Brando Miranda, Sanmi Koyejo — Outstanding Paper
• Privacy Auditing with One (1) Training Run — Thomas Steinke, Milad Nasr, Matthew Jagielski — Outstanding Paper
• Direct Preference Optimization: Your Language Model is Secretly a Reward Model — Rafael Rafailov, et al. — Outstanding Paper Runner-Up
• Scaling Data-Constrained Language Models — Niklas Muennighoff, et al. — Outstanding Paper Runner-Up
• DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models — Boxin Wang, et al. — Outstanding Benchmark Paper

​

2022

• Elucidating the Design Space of Diffusion-Based Generative Models — Tero Karras, Miika Aittala, et al. — Outstanding Paper
• Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding (Imagen) — Chitwan Saharia, et al. (Google Brain) — Outstanding Paper
• Is Out-of-distribution Detection Learnable? — Zhen Fang, Yixuan Li, et al. — Outstanding Paper
• Gradient Descent: The Ultimate Optimizer — Kartik Chandra, Audrey Xie, et al. — Outstanding Paper

​

2021

• A Universal Law of Robustness via Isoperimetry — Sebastien Bubeck, Mark Sellke — Outstanding Paper
• Deep Reinforcement Learning at the Edge of the Statistical Precipice — Rishabh Agarwal, Max Schwarzer, et al. — Outstanding Paper
• MAUVE: Measuring the Gap Between Neural Text and Human Text — Krishna Pillutla, Swabha Swayamdipta, et al. — Outstanding Paper