NeurIPS

TopoFR: A Closer Look at Topology Alignment on Face Recognition

Jun Dan, Yang Liu, Jiankang Deng, Haoyu Xie, Siyuan Li, Baigui Sun, Shan Luo

机构 * Zhejiang University（浙江大学） ； FaceChain Community（FaceChain社区） ； King’s College London（伦敦国王学院） ； Imperial College London（伦敦帝国学院） ； Alibaba Group（阿里巴巴集团） 纠错

Comments Accepted by NeurIPS 2024

Spatial-Aware Decision-Making with Ring Attractors in Reinforcement Learning Systems

Marcos Negre Saura, Richard Allmendinger, Wei Pan, Theodore Papamarkou

机构 * The University of Manchester（曼彻斯特大学） ； PolyShape 纠错

Comments Accepted at NeurIPS 2025

Disentangling Latent Shifts of In-Context Learning with Weak Supervision

Josip Jukić, Jan Šnajder

机构 * TakeLab Faculty of Electrical Engineering and Computing University of Zagreb（TakeLab 电子工程与计算学院 霍尔扎布大学） 纠错

Comments Accepted at NeurIPS 2025

Efficient Fairness-Performance Pareto Front Computation

Mark Kozdoba, Binyamin Perets, Shie Mannor

机构 * Technion - Israel Institute of Technology（技术离子-以色列理工学院） ； NVIDIA（英伟达） 纠错

Comments 10 pages, contain link to package. Neurips 2025

ESCORT: Efficient Stein-variational and Sliced Consistency-Optimized Temporal Belief Representation for POMDPs

Yunuo Zhang, Baiting Luo, Ayan Mukhopadhyay, Gabor Karsai, Abhishek Dubey

机构 * Vanderbilt University（范德比大学） 纠错

Comments Proceeding of the 39th Conference on Neural Information Processing Systems (NeurIPS'25). Code would be available at https://github.com/scope-lab-vu/ESCORT

DictPFL: Efficient and Private Federated Learning on Encrypted Gradients

Jiaqi Xue, Mayank Kumar, Yuzhang Shang, Shangqian Gao, Rui Ning, Mengxin Zheng, Xiaoqian Jiang, Qian Lou

机构 * University of Central Florida（佛罗里达中央大学） ； Florida State University（佛罗里达州立大学） ； Old Dominion University（旧 Dominion 大学） ； University of Texas Health Science Center at Houston（德克萨斯大学健康科学中心休斯顿分校） 纠错

Comments Accepted by NeurIPS 2025

Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data

Hancheng Min, Zhihui Zhu, René Vidal

机构 * Institute of Natural Sciences & School of Mathematical Sciences, Shanghai Jiao Tong University（上海交通大学自然科学研究院与数学科学学院） ； Computer Science and Engineering, Ohio State University（俄亥俄州立大学计算机科学与工程系） ； Electrical and Systems Engineering & Department of Radiology, University of Pennsylvania（宾夕法尼亚大学电气与系统工程系及放射学系） 纠错

Comments NeurIPS 2025

The Virtues of Brevity: Avoid Overthinking in Parallel Test-Time Reasoning

Raul Cavalcante Dinardi, Bruno Yamamoto, Anna Helena Reali Costa, Artur Jordao

机构 * Instituto de Matemática, Estatística e Ciência da Computação, Universidade de São Paulo（圣保罗大学数学、统计与计算机科学研究所） ； Escola Politécnica, Universidade de São Paulo（圣保罗大学理工学院） 纠错

Comments Accepted at NeurIPS 2025 Workshop on Efficient Reasoning

Customizing Open Source LLMs for Quantitative Medication Attribute Extraction across Heterogeneous EHR Systems

Zhe Fei, Mehmet Yigit Turali, Shreyas Rajesh, Xinyang Dai, Huyen Pham, Pavan Holur, Yuhui Zhu, Larissa Mooney, Yih-Ing Hser, Vwani Roychowdhury

机构 * Department of Statistics, UC Riverside（统计学系，加州大学河滨分校） ； Department of Electrical and Computer Engineering, UCLA（电气与计算机工程系，加州大学洛杉矶分校） ； Department of Psychiatry and Biobehavioral Sciences, UCLA（精神病学与生物行为科学系，加州大学洛杉矶分校） 纠错

Comments NeurIPS 2025: The Second Workshop on GenAI for Health: Potential, Trust, and Policy Compliance

CIPHER: Scalable Time Series Analysis for Physical Sciences with Application to Solar Wind Phenomena

Jasmine R. Kobayashi, Daniela Martin, Valmir P Moraes Filho, Connor O'Brien, Jinsu Hong, Sudeshna Boro Saikia, Hala Lamdouar, Nathan D. Miles, Marcella Scoczynski, Mavis Stone, Sairam Sundaresan, Anna Jungbluth, Andrés Muñoz-Jaramillo, Evangelia Samara, Joseph Gallego

机构 * Southwest Research Institute（西南研究院） ； University of Delaware（德雷塞尔大学） ； Catholic University of America（天主教大学） ； Boston University（波士顿大学） ； Georgia State University（佐治亚州立大学） ； Universität Vienna（维也纳大学） ； University of Oxford（牛津大学） ； University of Colorado Boulder（科罗拉多大学博尔德分校） ； Universidade Tecnológica Federal do Paraná（巴西南里尤卡普斯技术联邦大学） ； Stanford University（斯坦福大学） ； Intel Labs（英特尔实验室） ； European Space Agency（欧洲航天局） ； NASA Goddard Space Flight Center（美国国家航空航天局戈达德飞行中心） ； Drexel University（德雷塞尔大学） 纠错

Comments 5 pages, 2 figures, Machine Learning and the Physical Sciences Workshop @ NeurIPS 2025

From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD

Konstantinos Christopher Tsiolis, Alireza Mousavi-Hosseini, Murat A. Erdogdu

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

Comments NeurIPS 2025

Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inference

Yuhong Luo, Austin Hoag, Xintong Wang, Philip S. Thomas, Przemyslaw A. Grabowicz

机构 * Rutgers University（罗格斯大学） ； Sony AI（索尼人工智能） ； University of Massachusetts Amherst（马萨诸塞大学阿姆赫斯特分校） ； University College Dublin（都柏林大学） ； University of Massachusetts（马萨诸塞大学） 纠错

Comments Accepted by NeurIPS 2025

Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation

Enshu Liu, Qian Chen, Xuefei Ning, Shengen Yan, Guohao Dai, Zinan Lin, Yu Wang

机构 * Tsinghua University（清华大学） ； Infinigence-AI ； Shanghai Jiaotong University（上海交通大学） ； Microsoft Research（微软研究院） 纠错

Comments Published at NeurIPS 2025

VESSA: Video-based objEct-centric Self-Supervised Adaptation for Visual Foundation Models

Jesimon Barreto, Carlos Caetano, André Araujo, William Robson Schwartz

机构 * Departamento de Ciência da Computação, Universidade Federal de Minas Gerais (UFMG)（巴西联邦大学矿务学院计算机科学系（UFMG）） ； Recod.ai, Instituto de Computação, Universidade Estadual de Campinas (UNICAMP)（Recod.ai，计算机学院，坎皮纳斯州立大学（UNICAMP）） ； Google DeepMind（谷歌DeepMind） 纠错

Comments Conference on Neural Information Processing Systems (NeurIPS 2025)

Scalable inference of functional neural connectivity at submillisecond timescales

Arina Medvedeva, Edoardo Balzani, Alex H Williams, Stephen L Keeley

Comments Accepted at NeurIPS 2025

SutureBot: A Precision Framework & Benchmark For Autonomous End-to-End Suturing

Jesse Haworth, Juo-Tung Chen, Nigel Nelson, Ji Woong Kim, Masoud Moghani, Chelsea Finn, Axel Krieger

机构 * Johns Hopkins University（约翰霍普金斯大学） ； NVIDIA（英伟达） ； Stanford University（斯坦福大学） ； University of Toronto（多伦多大学） 纠错

Comments 10 pages, 5 figures, 4 tables, NeurIPS 2025

Learning from Interval Targets

Rattana Pukdee, Ziqi Ke, Chirag Gupta

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Bloomberg（彭博） 纠错

Comments NeurIPS 2025

Information Theoretic Learning for Diffusion Models with Warm Start

Yirong Shen, Lu Gan, Cong Ling

机构 * Imperial College London（伦敦帝国学院） ； Brunel University of London（伦敦布鲁内尔大学） 纠错

Comments NeurIPS 2025

Preventing Shortcuts in Adapter Training via Providing the Shortcuts

Anujraaj Argo Goyal, Guocheng Gordon Qian, Huseyin Coskun, Aarush Gupta, Himmy Tam, Daniil Ostashev, Ju Hu, Dhritiman Sagar, Sergey Tulyakov, Kfir Aberman, Kuan-Chieh Jackson Wang

机构 * Snap Inc. 纠错

Comments Accepted to NeurIPS 2025, webpage: https://snap-research.github.io/shortcut-rerouting/

ROPES: Robotic Pose Estimation via Score-Based Causal Representation Learning

Pranamya Kulkarni, Puranjay Datta, Burak Varıcı, Emre Acartürk, Karthikeyan Shanmugam, Ali Tajer

机构 * Google DeepMind（谷歌DeepMind） ； Carnegie Mellon University（卡内基梅隆大学） ； Rensselaer Polytechnic Institute（伦塞拉尔理工学院） 纠错

Comments A preliminary version of this paper appeared at NeurIPS 2025 Workshop on Embodied World Models for Decision Making

Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization

Antônio H. Ribeiro, David Vävinggren, Dave Zachariah, Thomas B. Schön, Francis Bach

机构 * Uppsala University（乌普萨拉大学） ； PSL Research University / INRIA（巴黎-萨克雷研究大学 / INRIA） 纠错

Comments Accepted NeurIPS 2025

Multimodal Negative Learning

Baoquan Gong, Xiyuan Gao, Pengfei Zhu, Qinghua Hu, Bing Cao

机构 * School of Artificial Intelligence, Tianjin University（人工智能学院，天津大学） 纠错

Comments Published in NeurIPS 2025

MOBO-OSD: Batch Multi-Objective Bayesian Optimization via Orthogonal Search Directions

Lam Ngo, Huong Ha, Jeffrey Chan, Hongyu Zhang

机构 * School of Computing Technologies RMIT University（计算技术学院皇家墨尔本理工学院） ； School of Big Data and Software Engineering Chongqing University（大数据与软件工程学院重庆大学） 纠错

Comments Published at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

Cultural Alien Sampler: Open-ended art generation balancing originality and coherence

Alejandro H. Artiles, Hiromu Yakura, Levin Brinkmann, Mar Canet Sola, Hassan Abu Alhaija, Ignacio Serna, Nasim Rahaman, Bernhard Schölkopf, Iyad Rahwan

机构 * Max Planck Institute for Human Development（马克斯·普朗克人类发展研究所） ； Academy of Media Arts Cologne（科隆媒体艺术学院） ； Tiptree Systems（蒂普特里系统） ； NVIDIA（NVIDIA公司） ； BFM, Tallinn University（BFM，塔林大学） ； Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所） 纠错

Comments Proceedings of the 39th Conference on Neural Information Processing Systems (NeurIPS 2025). Creative AI Track. 26 pages, 24 figures

Rethinking the Simulation vs. Rendering Dichotomy: No Free Lunch in Spatial World Modelling

Dezhi Luo, Qingying Gao, Hokin Deng

Comments Accepted at NeurIPS 2025 Workshop on Space in Vision, Language, and Embodied AI

What Does It Take to Build a Performant Selective Classifier?

Stephan Rabanser, Nicolas Papernot

机构 * Princeton University（普林斯顿大学） ； University of Toronto（多伦多大学） ； Vector Institute（向量研究所） 纠错

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

Preference-driven Knowledge Distillation for Few-shot Node Classification

Xing Wei, Chunchun Chen, Rui Fan, Xiaofeng Cao, Sourav Medya, Wei Ye

机构 * College of Electronic and Information Engineering, Tongji University, China（同济大学电子与信息学院） ； Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University, China（上海智能自主系统研究院） ； National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, China（人机混合增强智能国家级重点实验室） ； School of Computer Science and Technology, Tongji University, China（同济大学计算机科学与技术学院） ； Department of Computer Science, University of Illinois Chicago, USA（伊利诺伊大学芝加哥分校计算机科学系） 纠错

Comments Accepted by NeurIPS 2025

Scaling can lead to compositional generalization

Florian Redhardt, Yassir Akram, Simon Schug

机构 * ETH Zurich（苏黎世联邦理工学院） ； Princeton University（普林斯顿大学） 纠错

Comments NeurIPS 2025 (Spotlight); Code available at https://github.com/smonsays/scale-compositionality

Risk-Averse Total-Reward Reinforcement Learning

Xihong Su, Jia Lin Hau, Gersi Doko, Kishan Panaganti, Marek Petrik

机构 * Department of Computer Science University of New Hampshire（计算机科学系新罕布什尔大学） ； Department of Computing & Mathematical Sciences California Institute of Technology（计算与数学科学系加州理工学院） ； Tencent AI Lab（腾讯AI实验室） 纠错

Comments The paper has been accepted by the Thirty-Ninth Annual Conference on Neural Information Processing Systems(NeurIPS 2025)

TAI3: Testing Agent Integrity in Interpreting User Intent

Shiwei Feng, Xiangzhe Xu, Xuan Chen, Kaiyuan Zhang, Syed Yusuf Ahmed, Zian Su, Mingwei Zheng, Xiangyu Zhang

机构 * Purdue University（普渡大学） 纠错

Comments Accepted to NeurIPS 2025