NeurIPS

Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection

Chengcan Wu, Zeming Wei, Huanran Chen, Yinpeng Dong, Meng Sun

机构 * Peking University（北京大学） ； Tsinghua University（清华大学） 纠错

Comments 10 pages, 9 figures, Under review as a full paper at AAAI 2026. A preliminary version is under review at the NeurIPS 2025 Workshop on Reliable ML from Unreliable Data

Democratic AI is Possible. The Democracy Levels Framework Shows How It Might Work

Aviv Ovadya, Kyle Redman, Luke Thorburn, Quan Ze Chen, Oliver Smith, Flynn Devine, Andrew Konya, Smitha Milli, Manon Revel, K. J. Kevin Feng, Amy X. Zhang, Bilva Chandra, Michiel A. Bakker, Atoosa Kasirzadeh

Comments 31 pages. Accepted to the position paper track at ICML 2025. A previous version was presented at the Pluralistic Alignment Workshop at NeurIPS 2024. For ongoing work, see: https://democracylevels.org

Geometry-aware training of factorized layers in tensor Tucker format

Emanuele Zangrando, Steffen Schotthöfer, Gianluca Ceruti, Jonas Kusch, Francesco Tudisco

机构 * School of Mathematics, Gran Sasso Science Institute（格兰萨索科学研究所数学系） ； Computer Science and Mathematics Division, Oak Ridge National Laboratory（橡树岭国家实验室计算机科学与数学部） ； Department of Mathematics, University of Innsbruck（因斯布鲁克大学数学系） ； Department of Data Science, Norwegian University of Life Sciences（挪威生命科学大学数据科学系） ； School of Mathematics and Maxwell Institute, University of Edinburgh（爱丁堡大学数学系和麦克斯韦研究所） 纠错

Journal ref Proceedings NeurIPS 2024

SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models

Jianyi Zhang, Da-Cheng Juan, Cyrus Rashtchian, Chun-Sung Ferng, Heinrich Jiang, Yiran Chen

机构 * Duke University（杜克大学） ； Google Research（谷歌研究） 纠错

Comments Accepted at NeurIPS 2024; project page is available at https://jayzhang42.github.io/sled_page/

Goal-Directedness is in the Eye of the Beholder

Nina Rajcic, Anders Søgaard

机构 * University of Copenhagen, Department of Philosophy（哥本哈根大学哲学系） ； University of Copenhagen, Department of Computer Science（哥本哈根大学计算机科学系） 纠错

Comments Submitted to Conference and Workshop on Neural Information Processing Systems 2025

Generative Modeling of Full-Atom Protein Conformations using Latent Diffusion on Graph Embeddings

Aditya Sengar, Ali Hariri, Daniel Probst, Patrick Barth, Pierre Vandergheynst

机构 * Signal Processing Laboratory (LTS2), EPFL, Lausanne, Switzerland（信号处理实验室（LTS2），瑞士洛桑联邦理工学院） ； Institute of Bioengineering, EPFL, Lausanne, Switzerland（生物工程研究所，瑞士洛桑联邦理工学院） ； Bioinformatics Group, University & Research Wageningen, The Netherlands（生物信息学组，荷兰瓦赫宁根大学及研究学院） ； Ludwig Institute for Cancer Research, Lausanne, Switzerland（癌症研究路易斯研究所，瑞士洛桑） 纠错

Comments 10 pages (main text), 4 figures, 2 tables. Submitted to NeurIPS 2025. Code and data are publicly available

Large Language Models Must Be Taught to Know What They Don't Know

Sanyam Kapoor, Nate Gruver, Manley Roberts, Katherine Collins, Arka Pal, Umang Bhatt, Adrian Weller, Samuel Dooley, Micah Goldblum, Andrew Gordon Wilson

机构 * New York University（纽约大学） ； Abacus AI ； Cambridge University（剑桥大学） ； Columbia University（哥伦比亚大学） 纠错

Comments NeurIPS 2024 Camera Ready

N-Agent Ad Hoc Teamwork

Caroline Wang, Arrasy Rahman, Ishan Durugkar, Elad Liebman, Peter Stone

机构 * Sony AI（索尼人工智能） 纠错

Journal ref Proceedings of the 38th International Conference on Neural Information Processing Systems (NIPS '24), Vol. 37 (2024), Article 3551, 111832-111862

Every 28 Days the AI Dreams of Soft Skin and Burning Stars: Scaffolding AI Agents with Hormones and Emotions

Leigh Levinson, Christopher J. Agostino

机构 * Indiana University（印第安纳大学） ； NPC Worldwide（NPC全球） 纠错

Comments 9 pages, 1 figure, submitted to NeurIPS Creative AI track

Improved Regularization and Robustness for Fine-tuning in Neural Networks

Dongyue Li, Hongyang R. Zhang

机构 * Northeastern University（东北大学） 纠错

Comments 22 pages. Appeared in NeurIPS'21

SpeechForensics: Audio-Visual Speech Representation Learning for Face Forgery Detection

Yachao Liang, Min Yu, Gang Li, Jianguo Jiang, Boquan Li, Feng Yu, Ning Zhang, Xiang Meng, Weiqing Huang

机构 * Institute of Information Engineering（信息工程研究所） ； Chinese Academy of Sciences（中国科学院） ； School of Cyber Security University of Chinese Academy of Sciences（中国科学院网络安全学院） ； Deakin University（德肯大学） ； Harbin Engineering University（哈尔滨工程大学） ； Institute of Computing Technology Chinese Academy of Sciences（中国科学院计算技术研究所） ； Institute of Forensic Science Ministry of Public Security（公安部刑事科学技术研究所） 纠错

Comments Accepted by NeurIPS 2024

Journal ref Advances in Neural Information Processing Systems, Volume 37, Pages 86124-86144, Year 2024

Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning

Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Taiji Suzuki, Qingfu Zhang, Hau-San Wong

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

From Dark Matter to Galaxies with Convolutional Neural Networks

Jacky H. T. Yip, Xinyue Zhang, Yanfang Wang, Wei Zhang, Yueqiu Sun, Gabriella Contardo, Francisco Villaescusa-Navarro, Siyu He, Shy Genel, Shirley Ho

Comments 5 pages, 2 figures. Accepted to the Second Workshop on Machine Learning and the Physical Sciences (NeurIPS 2019)

Improving Multimodal Large Language Models Using Continual Learning

Shikhar Srivastava, Md Yousuf Harun, Robik Shrestha, Christopher Kanan

机构 * University of Rochester（罗切斯特大学） ； Rochester Institute of Technology（罗切斯特理工学院） 纠错

Comments CoLLAs 2025 and Scalable Continual Learning for Lifelong Foundation Models, NeurIPS 2024

Hi-fi functional priors by learning activations

Marcin Sendera, Amin Sorkhei, Tomasz Kuśmierczyk

机构 * Jagiellonian University（雅盖隆大学） ； Mila（Mila研究院） ； Université de Montréal（蒙特利尔大学） 纠错

Comments Published in Workshop on Bayesian Decision-making and Uncertainty, 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

EMPATHIA: Multi-Faceted Human-AI Collaboration for Refugee Integration

Mohamed Rayan Barhdadi, Mehmet Tuncel, Erchin Serpedin, Hasan Kurban

机构 * Texas A&M University（德克萨斯A&M大学） ； Istanbul Technical University（伊斯坦布尔技术大学） ； Hamad Bin Khalifa University（哈利法大学） 纠错

Comments 19 pages, 3 figures (plus 6 figures in supplementary), 2 tables, 1 algorithm. Submitted to NeurIPS 2025 Creative AI Track: Humanity

SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection

Yuxuan Li, Xiang Li, Weijie Li, Qibin Hou, Li Liu, Ming-Ming Cheng, Jian Yang

机构 * PCA Lab, VCIP, College of Computer Science, Nankai University（南开大学计算机科学学院） 纠错

Comments Accepted at NeurIPS 2024. Spotlight. Project page: (https://github.com/zcablii/SARDet_100K)[https://github.com/zcablii/SARDet_100K]

Measuring Dependencies between Biological Signals with Self-supervision, and its Limitations

Evangelos Sariyanidi, John D. Herrington, Lisa Yankowitz, Pratik Chaudhari, Theodore D. Satterthwaite, Casey J. Zampella, Robert T. Schultz, Russell T. Shinohara, Birkan Tunc

机构 * The Children’s Hospital of Philadelphia（费城儿童医院） ； University of Pennsylvania（宾夕法尼亚大学） 纠错

Comments To be submitted to NeurIPS 2025 AI for Science Workshop

Show, Don't Tell: Uncovering Implicit Character Portrayal using LLMs

Brandon Jaipersaud, Zining Zhu, Frank Rudzicz, Elliot Creager

Journal ref NeurIPS 2024 Creativity and Generative AI Workshop

AbbIE: Autoregressive Block-Based Iterative Encoder for Efficient Sequence Modeling

Preslav Aleksandrov, Meghdad Kurmanji, Fernando Garcia Redondo, David O'Shea, William Shen, Alex Iacob, Lorenzo Sani, Xinchi Qiu, Nicola Cancedda, Nicholas D. Lane

机构 * University of Cambridge（剑桥大学） ； Meta 纠错

Comments 14 pages and 6 figures. Submitted to NeurIPS 2025

DeMo++: Motion Decoupling for Autonomous Driving

Bozhou Zhang, Nan Song, Xiatian Zhu, Li Zhang

机构 * School of Data Science, Fudan University（复旦大学数据科学学院） ； University of Surrey（萨里大学） 纠错

Comments Journal extension of NeurIPS 2024. arXiv admin note: substantial text overlap with arXiv:2410.05982

From Text to Trajectory: Exploring Complex Constraint Representation and Decomposition in Safe Reinforcement Learning

Pusen Dong, Tianchen Zhu, Yue Qiu, Haoyi Zhou, Jianxin Li

机构 * Beihang University（北航大学） ； Zhongguancun Laboratory（中关村实验室） 纠错

Comments Accepted by NeurIPS 2024

Accurate and Interpretable Postmenstrual Age Prediction via Multimodal Large Language Model

Qifan Chen, Jin Cui, Cindy Duan, Yushuo Han, Yifei Shi

机构 * King’s College London（伦敦国王学院） ； Imperial College London（帝国理工学院） ； Columbia University（哥伦比亚大学） 纠错

Comments Submitted to the NeurIPS 2025 Workshop GenAI4Health. Conference website: https://aihealth.ischool.utexas.edu/GenAI4HealthNeurips2025/

PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for Recommendation

Weiqin Yang, Jiawei Chen, Xin Xin, Sheng Zhou, Binbin Hu, Yan Feng, Chun Chen, Can Wang

机构 * State Key Laboratory of Blockchain and Data Security, Zhejiang University（区块链与数据安全国家重点实验室，浙江大学） ； College of Computer Science and Technology, Zhejiang University（计算机科学与技术学院，浙江大学） 纠错

Journal ref Proceedings of the 38th International Conference on Neural Information Processing Systems (2024) 120974-121006

Interpreting Multi-band Galaxy Observations with Large Language Model-Based Agents

Zechang Sun, Yuan-Sen Ting, Yaobo Liang, Nan Duan, Song Huang, Zheng Cai

Comments Accepted at the NIPS ML4PS Workshop 2024. The journal version is in preparation. Code and data will be fully made public following the journal publication. We welcome any comments and feedback

Cooperative Perception: A Resource-Efficient Framework for Multi-Drone 3D Scene Reconstruction Using Federated Diffusion and NeRF

Massoud Pourmandi

Comments 15 pages, 3 figures, 1 table, 1 algorithm. Preprint based on NeurIPS 2024 template

Assessing Social Alignment: Do Personality-Prompted Large Language Models Behave Like Humans?

Ivan Zakazov, Mikolaj Boronski, Lorenzo Drudi, Robert West

机构 * EPFL（苏黎世联邦理工学院） 纠错

Comments Accepted to NeurIPS 2024 Workshop on Behavioral Machine Learning

Learning Zero-Shot Material States Segmentation, by Implanting Natural Image Patterns in Synthetic Data

Sagi Eppel, Jolina Li, Manuel Drehwald, Alan Aspuru-Guzik

机构 * Vector institute（向量研究所） ； University of Toronto（多伦多大学） 纠错

Journal ref Advances in Neural Information Processing Systems, vol. 37, pp. 60237-60259, 2024

Correlating Variational Autoencoders Natively For Multi-View Imputation

Ella S. C. Orme, Marina Evangelou, Ulrich Paquet

机构 * African Institute for Mathematical Sciences, South Africa（非洲数学科学研究所，南非） 纠错

Comments Accepted at 'UniReps: 2nd Edition of the Workshop on Unifying Representations in Neural Models', a workshop at NeurIPS 2024

Journal ref Proceedings of UniReps: the Second Edition of the Workshop on Unifying Representations in Neural Models, PMLR 285:181-193, 2024

Bubbleformer: Forecasting Boiling with Transformers

Sheikh Md Shakeel Hassan, Xianwei Zou, Akash Dhruv, Vishwanath Ganesan, Aparna Chandramowlishwaran

机构 * University of California, Irvine（加州大学尔湾分校） ； Argonne National Laboratory（阿贡国家实验室） ； UIUC（伊利诺伊大学香槟分校） 纠错

Comments 39 pages, 13 figures, Submitted to NeurIPS 2025