NeurIPS

Representative Social Choice: From Learning Theory to AI Alignment

Tianyi Qiu

机构 * Peking University（北京大学） ； UC Berkeley（加州大学伯克利分校） ； Center for Human-Compatible AI（人类兼容人工智能中心） 纠错

Comments Journal of Artificial Intelligence Research, in press. Best Paper at NeurIPS 2024 Pluralistic Alignment Workshop

EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting

Bohao Liao, Wei Zhai, Zengyu Wan, Zhixin Cheng, Wenfei Yang, Tianzhu Zhang, Yang Cao, Zheng-Jun Zha

机构 * University of Science and Technology of China（中国科学技术大学） 纠错

Comments Accepted to NeurIPS 2025,Project Page: https://lbh666.github.io/ef-3dgs/

Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning

Zhishuai Liu, Pan Xu

Comments 46 pages, 3 figures, 1 table. Published in Proc. of the 38th Conference on Advances in Neural Information Processing Systems (NeurIPS 2024)

Journal ref Advances in Neural Information Processing Systems, volume 37, pages 86602-86654, 2024

Accelerated Rates between Stochastic and Adversarial Online Convex Optimization

Sarah Sachs, Hedi Hadiji, Tim van Erven, Cristobal Guzman

Comments There is an unfixable mistake in the proof of Lemma 15, as kindly brought to our attention by Peng Zhao. The mistake is not present in the earlier NeurIPS 2022 conference version of the paper, which does not include this result

Scaling Image Geo-Localization to Continent Level

Philipp Lindenberger, Paul-Edouard Sarlin, Jan Hosang, Matteo Balice, Marc Pollefeys, Simon Lynen, Eduard Trulls

机构 * ETH Zurich（苏黎世联邦理工学院） ； Google（谷歌） ； Politecnico di Milano（米兰理工大学） 纠错

Comments NeurIPS 2025

HEIR: Learning Graph-Based Motion Hierarchies

Cheng Zheng, William Koch, Baiang Li, Felix Heide

机构 * Princeton University（普林斯顿大学） ； Torc Robotics（Torc机器人公司） 纠错

Comments Code link: https://github.com/princeton-computational-imaging/HEIR

Journal ref Advances in Neural Information Processing Systems 38 (NeurIPS 2025)

Pre-trained Forecasting Models: Strong Zero-Shot Feature Extractors for Time Series Classification

Andreas Auer, Daniel Klotz, Sebastinan Böck, Sepp Hochreiter

机构 * NXAI GmbH（NXAI公司） ； ELLIS Unit, LIT AI Lab, Institute for Machine Learning, JKU Linz（ELLIS单位、LIT AI实验室、机器学习研究所） ； Interdisciplinary Transformation University Austria（跨学科转型大学奥地利） 纠错

Comments NeurIPS 2025 Workshop on Recent Advances in Time Series Foundation Models (BERT2S)

Curly Flow Matching for Learning Non-gradient Field Dynamics

Katarina Petrović, Lazar Atanackovic, Viggo Moro, Kacper Kapuśniak, İsmail İlkan Ceylan, Michael Bronstein, Avishek Joey Bose, Alexander Tong

Comments Accepted to NeurIPS 2025

ORBIT -- Open Recommendation Benchmark for Reproducible Research with Hidden Tests

Jingyuan He, Jiongnan Liu, Vishan Vishesh Oberoi, Bolin Wu, Mahima Jagadeesh Patel, Kangrui Mao, Chuning Shi, I-Ta Lee, Arnold Overwijk, Chenyan Xiong

机构 * Language Technologies Institute, Carnegie Mellon University（语言技术研究所，卡内基梅隆大学） 纠错

Comments Accepted to NeurIPS 2025 Datasets & Benchmarks track

TinyTim: A Family of Language Models for Divergent Generation

Christopher J. Agostino

机构 * NPC Worldwide（NPC全球） 纠错

Comments 7 pages, 3 figures, accepted to NeurIPS Creative AI track, models available at https://hf.co/npc-worldwide/

Controlling Thinking Speed in Reasoning Models

Zhengkai Lin, Zhihang Fu, Ze Chen, Chao Chen, Liang Xie, Wenxiao Wang, Deng Cai, Zheng Wang, Jieping Ye

机构 * State Key Lab of CAD&CG（CAD&CG状态重点实验室） ； Alibaba Cloud（阿里云） ； College of Computer Science and Technology（计算机科学与技术学院） ； School of Software Technology（软件技术学院） 纠错

Comments NeurIPS 2025 Spotlight

C-LoRA: Contextual Low-Rank Adaptation for Uncertainty Estimation in Large Language Models

Amir Hossein Rahmati, Sanket Jantre, Weifeng Zhang, Yucheng Wang, Byung-Jun Yoon, Nathan M. Urban, Xiaoning Qian

机构 * Texas A&M University（德克萨斯A&M大学） ； Brookhaven National Laboratory（布鲁克海文国家实验室） 纠错

Comments Conference on Neural Information Processing Systems (NeurIPS 2025)

Curriculum Abductive Learning

Wen-Chao Hu, Qi-Jie Li, Lin-Han Jia, Cunjing Ge, Yu-Feng Li, Yuan Jiang, Zhi-Hua Zhou

机构 * National Key Laboratory for Novel Software Technology, Nanjing University, China（南京大学新型软件技术国家重点实验室） ； School of Artificial Intelligence, Nanjing University, China（南京大学人工智能学院） 纠错

Comments Accepted by NeurIPS 2025, 22 pages, 6 figures

Hybrid Physical-Neural Simulator for Fast Cosmological Hydrodynamics

Arne Thomsen, Tilman Tröster, François Lanusse

机构 * ETH Zürich（苏黎世联邦理工学院） ； Université Paris-Saclay（巴黎-萨克雷大学） ； CEA（欧洲核子研究中心） ； CNRS（法国国家科学研究中心） ； AIM（原子分子影像研究所） 纠错

Comments Accepted to the NeurIPS 2025 Workshop on Machine Learning and the Physical Sciences

The Structure of Relation Decoding Linear Operators in Large Language Models

Miranda Anna Christ, Adrián Csiszárik, Gergely Becsó, Dániel Varga

机构 * Fazekas Mihály High School（法泽卡米哈伊高中） ； HUN-REN Alfréd Rényi Insititute of Mathematics（HUN-REN阿弗雷德·雷尼数学研究所） ； Eötvös Loránd University（欧多布查伊·劳尔大学） 纠错

Comments NeurIPS 2025 (Spotlight)

Model Inversion with Layer-Specific Modeling and Alignment for Data-Free Continual Learning

Ruilin Tong, Haodong Lu, Yuhang Liu, Dong Gong

Comments Accepted in NeurIPS 2025

Revisiting Generative Infrared and Visible Image Fusion Based on Human Cognitive Laws

Lin Guo, Xiaoqing Luo, Wei Xie, Zhancheng Zhang, Hui Li, Rui Wang, Zhenhua Feng, Xiaoning Song

机构 * School of Artificial Intelligence and Computer Science, Jiangnan University（江南大学人工智能与计算机科学学院） 纠错

Comments NeurIPS 2025 spotlight

Angular Steering: Behavior Control via Rotation in Activation Space

Hieu M. Vu, Tan M. Nguyen

机构 * Torilab ； Department of Mathematics National University of Singapore（数学系，新加坡国立大学） 纠错

Comments NeurIPS 2025 (Spotlight)

Don't Let It Fade: Preserving Edits in Diffusion Language Models via Token Timestep Allocation

Woojin Kim, Jaeyoung Do

机构 * AIDAS Laboratory（AIDAS实验室） ； ECE（电子工程系） ； APAI（人工智能院） 纠错

Comments Accepted in NeurIPS 2025

ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts

Jinho Choi, Hyesu Lim, Steffen Schneider, Jaegul Choo

机构 * KAIST AI（韩国科学技术院人工智能研究所） ； Helmholtz Munich（慕尼黑海德堡研究所） ； Institute of Computational Biology（计算生物学研究所） ； Computational Health Center（计算健康中心） ； Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心） 纠错

Comments Published in the Thirty-Ninth Conference on Neural Information Processing Systems (NeurIPS 2025)

ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio-Language Models

Weifei Jin, Yuxin Cao, Junjie Su, Minhui Xue, Jie Hao, Ke Xu, Jin Song Dong, Derui Wang

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； National University of Singapore（新加坡国立大学） ； CSIRO’s Data61（CSIRO数据61） ； Responsible AI Research (RAIR) Centre, The University of Adelaide（负责任人工智能研究（RAIR）中心，阿德莱德大学） ； Tsinghua University（清华大学） 纠错

Comments Accepted to NeurIPS 2025

Dynamic VLM-Guided Negative Prompting for Diffusion Models

Hoyeon Chang, Seungjin Kim, Yoonseok Choi

机构 * KAIST（韩国科学技术院） 纠错

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: The First Workshop on Generative and Protective AI for Content Creation

Enhancing Temporal Understanding in Video-LLMs through Stacked Temporal Attention in Vision Encoders

Ali Rasekh, Erfan Bagheri Soula, Omid Daliran, Simon Gottschalk, Mohsen Fayyaz

机构 * Leibniz University Hannover（莱比锡大学汉诺威分校） ； L3S Research Center（L3S研究中心） ； Microsoft（微软公司） 纠错

Comments Accepted to NeurIPS 2025

Dual Mixture-of-Experts Framework for Discrete-Time Survival Analysis

Hyeonjun Lee, Hyungseob Shin, Gunhee Nam, Hyeonsoo Lee

机构 * Lunit Inc.（Lunit公司） 纠错

Comments Accepted to NeurIPS 2025 workshop Learning from Time Series for Health (TS4H)

Infrequent Exploration in Linear Bandits

Harin Lee, Min-hwan Oh

机构 * University of Washington（华盛顿大学） ； Seoul National University（首尔国立大学） 纠错

Comments NeurIPS 2025 camera-ready version

SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing

Sung-Hoon Yoon, Minghan Li, Gaspard Beaudouin, Congcong Wen, Muhammad Rafay Azhar, Mengyu Wang

机构 * Harvard AI and Robotics Lab, Harvard University（哈佛人工智能与机器人实验室，哈佛大学） ； École des Ponts, Institut Polytechnique de Paris（巴黎高等工业学院） ； New York University Abu Dhabi（纽约大学阿布扎克分校） ； Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University（哈佛大学自然与人工智能研究学院） 纠错

Comments Camera-ready version for NeurIPS 2025, 10 pages (main paper)

ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusion

Sungho Koh, SeungJu Cha, Hyunwoo Oh, Kwanyoung Lee, Dong-Jin Kim

机构 * Hanyang University（翰阳大学） 纠错

Comments NeurIPS 2025. Code: https://github.com/KSH00906/ScaleDiff

Multimodal Bandits: Regret Lower Bounds and Optimal Algorithms

William Réveillard, Richard Combes

机构 * Division of Decision and Control Systems（决策与控制系统系） ； KTH Royal Institute of Technology（皇家理工学院） ； Laboratoire des signaux et systèmes（信号与系统实验室） ； Université Paris-Saclay, CNRS, CentraleSupélec（巴黎萨克雷大学、国家科学研究中心、中央理工-巴黎高等理工学院） 纠错

Comments 31 pages; NeurIPS 2025

PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs

Jaewon Chu, Seunghun Lee, Hyunwoo J. Kim

机构 * Korea University（韩国大学） ； KAIST（韩国科学技术院） 纠错

Comments Accepted to NeurIPS 2025

MemEIC: A Step Toward Continual and Compositional Knowledge Editing

Jin Seong, Jiyun Park, Wencke Liermann, Hongseok Choi, Yoonji Nam, Hyun Kim, Soojong Lim, Namhoon Lee

机构 * Electronics and Telecommunications Research Institute, Republic of Korea（韩国电子电信研究院） ； POSTECH ； Sungkyunkwan University（全南大学） 纠错

Comments NeurIPS 2025, 38 pages, 8 figures