NeurIPS

Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physics

Jonas Spinner, Victor Bresó, Pim de Haan, Tilman Plehn, Jesse Thaler, Johann Brehmer

机构 * Heidelberg University（海德堡大学） ； MIT（麻省理工学院） ； IAIFI ； Qualcomm AI Research（高通人工智能研究） 纠错

Comments 10+12 pages, 5+2 figures, 2 tables. v2: extended acknowledgements, added link to github repo. v3: improved results, matches NeurIPS camera-ready version

Journal ref Advances in Neural Information Processing Systems 38 (NeurIPS 2024)

GUI-Robust: A Comprehensive Dataset for Testing GUI Agent Robustness in Real-World Anomalies

Jingqi Yang, Zhilong Song, Jiawei Chen, Mingli Song, Sheng Zhou, linjun sun, Xiaogang Ouyang, Chun Chen, Can Wang

机构 * Zhejiang University（浙江大学） ； Intelligence Indeed（智能实在） 纠错

Comments 10 pages, 4 figures, submitted to NIPS 2025

ResNets Are Deeper Than You Think

Christian H. X. Ali Mehmeti-Göpel, Michael Wand

机构 * Department of Computer Science Johannes-Gutenberg University Mainz, Germany（计算机科学系格鲁特伯爵大学马因茨德国） 纠错

Comments NeurIPS 2025 Submission

When are dynamical systems learned from time series data statistically accurate?

Jeongjin Park, Nicole Yang, Nisha Chandramoorthy

机构 * Georgia Tech（佐治亚理工学院） ； Emory University（埃默里大学） ； University of Chicago（芝加哥大学） 纠错

Comments in NeuRIPS 2024

HEAR: Holistic Evaluation of Audio Representations

Joseph Turian, Jordie Shier, Humair Raj Khan, Bhiksha Raj, Björn W. Schuller, Christian J. Steinmetz, Colin Malloy, George Tzanetakis, Gissel Velarde, Kirk McNally, Max Henry, Nicolas Pinto, Camille Noufi, Christian Clough, Dorien Herremans, Eduardo Fonseca, Jesse Engel, Justin Salamon, Philippe Esling, Pranay Manocha, Shinji Watanabe, Zeyu Jin, Yonatan Bisk

Comments to appear in Proceedings of Machine Learning Research (PMLR): NeurIPS 2021 Competition Track

Journal ref Proceedings of Machine Learning Research (PMLR): NeurIPS 2021 Competition Track

Consistency of Neural Causal Partial Identification

Jiyuan Tan, Jose Blanchet, Vasilis Syrgkanis

机构 * Stanford University（斯坦福大学） 纠错

Comments 60 pages, 8 figures, accepted by Neurips 2024

NSW-EPNews: A News-Augmented Benchmark for Electricity Price Forecasting with LLMs

Zhaoge Bi, Linghan Huang, Haolin Jin, Qingwen Zeng, Huaming Chen

机构 * The University of Sydney（悉尼大学） 纠错

Comments 9 pages' main texts. Submitted to NeurIPS 2025 Datasets and Benchmarks Track

Ad Auctions for LLMs via Retrieval Augmented Generation

MohammadTaghi Hajiaghayi, Sébastien Lahaie, Keivan Rezaei, Suho Shin

机构 * University of Maryland（马里兰大学） ； Google Research（谷歌研究院） 纠错

Comments NeurIPS 2024

DiffTORI: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learning

Weikang Wan, Ziyu Wang, Yufei Wang, Zackory Erickson, David Held

Comments NeurIPS 2024 (Spotlight)

Equivariant Neural Diffusion for Molecule Generation

François Cornet, Grigory Bartosh, Mikkel N. Schmidt, Christian A. Naesseth

机构 * Technical University of Denmark（丹麦技术大学） ； University of Amsterdam（阿姆斯特丹大学） 纠错

Comments 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

The 2025 PNPL Competition: Speech Detection and Phoneme Classification in the LibriBrain Dataset

Gilad Landau, Miran Özdogan, Gereon Elvers, Francesco Mantegna, Pratik Somaiya, Dulhan Jayalath, Luisa Kurth, Teyun Kwon, Brendan Shillingford, Greg Farquhar, Minqi Jiang, Karim Jerbi, Hamza Abdelhedi, Yorguin Mantilla Ramos, Caglar Gulcehre, Mark Woolrich, Natalie Voets, Oiwi Parker Jones

机构 * PNPL ； Google DeepMind（谷歌DeepMind） ； MetaAI ； Mila ； Université de Montréal（蒙特利尔大学） ； EPFL（苏黎世联邦理工学院） ； OHBA ； WIN N University of Oxford（WIN N 奥xford大学） 纠错

Journal ref NeurIPS 2025 Competition Track

DeepTraverse: A Depth-First Search Inspired Network for Algorithmic Visual Understanding

Bin Guo, John H. L. Hansen

Comments NeurIPS 2025

Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge

Weihua Du, Qiushi Lyu, Jiaming Shan, Zhenting Qi, Hongxin Zhang, Sunli Chen, Andi Peng, Tianmin Shu, Kwonjoon Lee, Behzad Dariush, Chuang Gan

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Peking University（北京大学） ； University of California, Santa Barbara（加州大学圣芭芭拉分校） ； Harvard University（哈佛大学） ； University of Massachusetts Amherst（马萨诸塞大学阿姆赫斯特分校） ； MIT（麻省理工学院） ； Johns Hopkins University（约翰霍普金斯大学） ； Honda Research Institute USA（本田美国研究院） 纠错

Comments NeurIPS 2024 Dataset and Benchmark Track. The first two authors contributed equally. Project Website at https://umass-embodied-agi.github.io/CHAIC/

Incentivizing Quality Text Generation via Statistical Contracts

Eden Saig, Ohad Einav, Inbal Talgam-Cohen

机构 * Technion – Israel Institute of Technology（技术ion–以色列理工学院） ； Tel Aviv University（特拉维夫大学） 纠错

Comments NeurIPS 2024

Learning-based Motion Planning in Dynamic Environments Using GNNs and Temporal Encoding

Ruipeng Zhang, Chenning Yu, Jingkai Chen, Chuchu Fan, Sicun Gao

Journal ref 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples

Baiqi Li, Zhiqiu Lin, Wenxuan Peng, Jean de Dieu Nyandwi, Daniel Jiang, Zixian Ma, Simran Khanuja, Ranjay Krishna, Graham Neubig, Deva Ramanan

机构 * Carnegie Mellon University（卡内基梅隆大学） ； University of Washington（华盛顿大学） 纠错

Comments Accepted to NeurIPS 24; We open-source our dataset at: https://huggingface.co/datasets/BaiqiL/NaturalBench ; Project page at: https://linzhiqiu.github.io/papers/naturalbench/

How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis

Yushi Yang, Filip Sondej, Harry Mayne, Andrew Lee, Adam Mahdi

机构 * University of Oxford（牛津大学） ； Jagiellonian University（雅盖隆大学） ； Harvard University（哈佛大学） 纠错

Journal ref NeurIPS 2024 Workshop on Socially Responsible Language Modelling Research (SoLaR)

Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization

Mucong Ding, Chenghao Deng, Jocelyn Choo, Zichu Wu, Aakriti Agrawal, Avi Schwarzschild, Tianyi Zhou, Tom Goldstein, John Langford, Anima Anandkumar, Furong Huang

机构 * University of Maryland（马里兰大学） ； University of Waterloo（滑铁卢大学） ； Carnegie Mellon University（卡内基梅隆大学） ； California Institute of Technology（加州理工学院） ； Microsoft（微软） ； Capital One 纠错

Comments NeurIPS 2024 Datasets and Benchmarks Track

A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual Generation

Gwanghyun Kim, Alonso Martinez, Yu-Chuan Su, Brendan Jou, José Lezama, Agrim Gupta, Lijun Yu, Lu Jiang, Aren Jansen, Jacob Walker, Krishna Somandepalli

机构 * Seoul National University（首尔国立大学） ； Google DeepMind（谷歌DeepMind） ； Stanford University（斯坦福大学） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

Journal ref In Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

Path Integral Optimiser: Global Optimisation via Neural Schrödinger-Föllmer Diffusion

Max McGuinness, Eirik Fladmark, Francisco Vargas

机构 * University of Cambridge（剑桥大学） 纠错

Comments 6 pages. Presented at the OPT Workshop, NeurIPS 2024, Vancouver, CA

On Adversarial Robustness of Language Models in Transfer Learning

Bohdan Turbal, Anastasiia Mazur, Jiaxu Zhao, Mykola Pechenizkiy

机构 * Taras Shevchenko National University of Kyiv（基辅塔拉斯·谢甫琴科国立大学） ； Eindhoven University of Technology（埃因霍温理工大学） 纠错

Journal ref Socially Responsible Language Modelling Research (SoLaR) Workshop at NeurIPS 2024

Feint Behaviors and Strategies: Formalization, Implementation and Evaluation

Junyu Liu, Xiangjun Peng

机构 * Brown University（布朗大学） ； The Chinese University of Hong Kong（香港中文大学） 纠错

Comments Published in NeurIPS 2024

BOLD: Boolean Logic Deep Learning

Van Minh Nguyen, Cristian Ocampo, Aymen Askri, Louis Leconte, Ba-Hien Tran

机构 * Mathematical and Algorithmic Sciences Laboratory, Huawei Paris Research Center（华为巴黎研究中心数学与算法科学实验室） 纠错

Comments Published at NeurIPS 2024 main conference

Described Object Detection: Liberating Object Detection with Flexible Expressions

Chi Xie, Zhao Zhang, Yixuan Wu, Feng Zhu, Rui Zhao, Shuang Liang

Comments Accepted by NeurIPS 2023

CoFrNets: Interpretable Neural Architecture Inspired by Continued Fractions

Isha Puri, Amit Dhurandhar, Tejaswini Pedapati, Kartikeyan Shanmugam, Dennis Wei, Kush R. Varshney

机构 * Harvard University（哈佛大学） ； IBM Research（IBM研究院） 纠错

Journal ref Advances in Neural Information Processing Systems (NeurIPS) 2021, vol 34, pp 21668-21690

The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process

Florian Carichon, Aditi Khandelwal, Marylou Fauchard, Golnoosh Farnadi

Comments Preprint of NeurIPS 2025 Position Paper

Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks

Benjamin Leblanc, Mathieu Bazinet, Nathaniel D'Amours, Alexandre Drouin, Pascal Germain

Comments Accepted at ICML 2025 (also at the NeurIPS 2024 Workshop on Compression in Machine Learning)

AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment

Pankayaraj Pathmanathan, Udari Madhushani Sehwag, Michael-Andrei Panaitescu-Liess, Furong Huang

机构 * University of Maryland（马里兰大学） ； JPMorgan AI Research（摩根大通人工智能研究） ； University of Maryland Capital One（马里兰大学Capital One） 纠错

Comments Published at the Neurips Safe Generative AI Workshop 2024

Position: There Is No Free Bayesian Uncertainty Quantification

Ivan Melev, Goeran Kauermann

机构 * Department of Statistics LMU Munich（慕尼黑大学统计系） 纠错

Comments NeurIPS 2025 preprint, frequentist critique of Bayesian UQ

POLARIS: A High-contrast Polarimetric Imaging Benchmark Dataset for Exoplanetary Disk Representation Learning

Fangyi Cao, Bin Ren, Zihao Wang, Shiwei Fu, Youbin Mo, Xiaoyang Liu, Yuzhou Chen, Weixin Yao

机构 * UC Riverside（加州大学河滨分校） ； OCA/MPIA（天文台/马克斯·普朗克研究所） ； UT Chattanooga（田纳西大学查塔努加分校） ； MGH（麻省总医院） ； Harvard（哈佛大学） ； UC San Diego（加州大学圣地亚哥分校） ； Adobe（Adobe公司） 纠错

Comments 9 pages main text with 5 figures, 9 pages appendix with 9 figures. Submitted to NeurIPS 2025