NeurIPS

Angular Constraint Embedding via SpherePair Loss for Constrained Clustering

Shaojie Zhang, Ke Chen

机构 * Department of Computer Science, The University of Manchester（计算机科学系，曼彻斯特大学） 纠错

Comments Accepted by NeurIPS 2025, 6 Figures and 1 Table in Main text, 18 Figures and 5 Tables in Appendices

A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Masking

Gal Fadlon, Idan Arbiv, Nimrod Berman, Omri Azencot

Comments Accepted to NeurIPS 2025; The first two authors contributed equally and are co-leading authors

Latent Representation Learning in Heavy-Ion Collisions with MaskPoint Transformer

Jing-Zong Zhang, Shuang Guo, Li-Lin Zhu, Lingxiao Wang, Guo-Liang Ma

机构 * Institute of Modern Physics, Fudan University（复旦大学现代物理研究所） ； Shanghai Research Center for Theoretical Nuclear Physics（上海理论核物理研究中心） ； NSFC and Fudan University（国家自然科学基金委员会和复旦大学） ； Department of Physics, Sichuan University（四川大学物理系） ； RIKEN Interdisciplinary Theoretical and Mathematical Sciences (iTHEMS)（理化学研究所 interdisciplinary theoretical and mathematical sciences (iTHEMS)） 纠错

Comments 10 pages, 5 figures, accepted at the NeurIPS 2025 workshop "Machine Learning and the Physical Sciences"

Text-to-Image Models Leave Identifiable Signatures: Implications for Leaderboard Security

Ali Naseh, Anshuman Suri, Yuefeng Peng, Harsh Chaudhari, Alina Oprea, Amir Houmansadr

机构 * University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校） ； Northeastern University（东北大学） 纠错

Comments Accepted at Lock-LLM Workshop, NeurIPS 2025

Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Tasks

Wentao Deng, Jiahuan Pei, Zhiwei Xu, Zhaochun Ren, Zhumin Chen, Pengjie Ren

机构 * Shandong University（山东大学） ； VU Amsterdam（阿姆斯特丹自由大学） ； Leiden University（莱顿大学） 纠错

Comments This paper has been accepted by NeurIPS 2025

Scalable In-context Ranking with Generative Models

Nilesh Gupta, Chong You, Srinadh Bhojanapalli, Sanjiv Kumar, Inderjit Dhillon, Felix Yu

机构 * UT Austin（得克萨斯大学） ； Google（谷歌） 纠错

Journal ref Neurips 2025

Robust Neural Rendering in the Wild with Asymmetric Dual 3D Gaussian Splatting

Chengqi Li, Zhihao Shi, Yangdi Lu, Wenbo He, Xiangyu Xu

机构 * McMaster University（麦斯特大学） ； Xi’an Jiaotong University（西安交通大学） 纠错

Comments NeurIPS 2025 Spotlight; Project page: https://steveli88.github.io/AsymGS/

HoPE: Hybrid of Position Embedding for Long Context Vision-Language Models

Haoran Li, Yingjie Qin, Baoyuan Ou, Lai Xu, Ruiwen Xu

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Xiaohongshu Inc.（小红书公司） 纠错

Comments NeurIPS 2025

MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding

Yuxiang Wei, Yanteng Zhang, Xi Xiao, Tianyang Wang, Xiao Wang, Vince D. Calhoun

机构 * University of Alabama at Birmingham（阿拉巴马大学伯明翰分校） ； Oak Ridge National Laboratory（橡树岭国家实验室） 纠错

Comments Accepted to NeurIPS 2025

FlowKV: Enhancing Multi-Turn Conversational Coherence in LLMs via Isolated Key-Value Cache Management

Xiang Liu, Hong Chen, Xuming Hu, Xiaowen Chu

机构 * The Hong Kong University of Science and Technology(Guangzhou)（香港科技大学（广州）） 纠错

Comments NeurIPS 2025 Workshop on Multi-Turn Interactions in Large Language Models

TIME: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenarios

Shaohang Wei, Wei Li, Feifan Song, Wen Luo, Tianyi Zhuang, Haochen Tan, Zhijiang Guo, Houfeng Wang

机构 * State Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机学院，北京大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） 纠错

Comments Accepted by NeurIPS 2025 (Spotlight)

AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMs

Lara Magdalena Lazier, Aritra Dhar, Vasilije Stambolic, Lukas Cavigelli

Comments Accepted in NeurIPS 2025

A-MEM: Agentic Memory for LLM Agents

Wujiang Xu, Zujie Liang, Kai Mei, Hang Gao, Juntao Tan, Yongfeng Zhang

机构 * Rutgers University（罗杰斯大学） 纠错

Comments Advances in Neural Information Processing Systems (NeurIPS 2025)

SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications

Gabriele Oliaro, Zhihao Jia, Daniel Campos, Aurick Qiao

机构 * Snowflake AI Research（Snowflake AI研究院） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

Comments NeurIPS 2025 (Spotlight)

Approximately Aligned Decoding

Daniel Melcer, Sujan Gonugondla, Pramuditha Perera, Haifeng Qian, Wen-Hao Chiang, Yanjun Wang, Nihal Jain, Pranav Garg, Xiaofei Ma, Anoop Deoras

机构 * Khoury College of Computer Sciences Northeastern University（科里学院计算机科学系东北大学） ； Meta Superintelligence Labs（Meta超智能实验室） ； AWS NGDE ； Nvidia 纠错

Comments NeurIPS 2025 version; 10 pages, 35 total

The Adversarial Consistency of Surrogate Risks for Binary Classification

Natalie Frank, Jonathan Niles-Weed

机构 * Courant Institute（Courant 院） ； New York University（纽约大学） 纠错

Comments 17 pages, published in NeurIps 2023. version 3: added acknowledgements, no other changes. version 2: reorganized Section 4 and added proofs of the approximate complimentary slackness theorems. arXiv admin note: text overlap with arXiv:2206.09099

Journal ref Advances in Neural Information Processing Systems 2023

Spatiotemporal Tile-based Attention-guided LSTMs for Traffic Video Prediction

Tu Nguyen

机构 * Daimler AG（戴姆勒集团） 纠错

Comments Neurips 2019 Traffic4Cast Challenge, v4: added formal proofs

The Valley of Code Reasoning: Scaling Knowledge Distillation of Large Language Models

Muyu He, Muhammad Ali Shafique, Anand Kumar, Tsach Mackey, Nazneen Rajani

Comments NeurIPS 2025 Workshop on Deep Learning for Code (DL4C), Project page: https://collinear.ai/valley-of-reasoning

When Thinking Drifts: Evidential Grounding for Robust Video Reasoning

Mi Luo, Zihui Xue, Alex Dimakis, Kristen Grauman

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校） ； UC Berkeley（伯克利大学） ； Bespoke Labs（Bespoke实验室） 纠错

Comments Accepted by NeurIPS 2025, Project page: https://vision.cs.utexas.edu/projects/video-ver/

Segment-Factorized Full-Song Generation on Symbolic Piano Music

Ping-Yi Chen, Chih-Pin Tan, Yi-Hsuan Yang

机构 * National Cheng Kung University（国立成功大学） ； National Taiwan University（国立台湾大学） 纠错

Comments Accepted to the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: AI for Music

How Foundational are Foundation Models for Time Series Forecasting?

Nouha Karaouli, Denis Coquenet, Elisa Fromont, Martial Mermillod, Marina Reyboz

机构 * Univ. Rennes（里昂大学） ； CNRS（法国国家科学研究中心） ； Inria（法国国家信息与自动化技术研究所） ； IRISA - UMR 6074（国际信息与自动化研究所） ； Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学） ； Univ. Savoie Mont Blanc（萨瓦伊-蒙布莱大学） ； LPNC（实验室） ； CEA（法国原子能委员会） ； LIST（法国国家信息与自动化技术研究所） 纠错

Comments Typo rectified in this v3 version. Accepted at NeurIPS 2025 Workshop on Recent Advances in Time Series Foundation Models (BERT2S)

FlowMoE: A Scalable Pipeline Scheduling Framework for Distributed Mixture-of-Experts Training

Yunqi Gao, Bing Hu, Mahdi Boloursaz Mashhadi, A-Long Jin, Yanfeng Zhang, Pei Xiao, Rahim Tafazolli, Merouane Debbah

Comments Accepted at NeurIPS 2025

When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding

Yan Shu, Hangui Lin, Yexin Liu, Yan Zhang, Gangyan Zeng, Yan Li, Yu Zhou, Ser-Nam Lim, Harry Yang, Nicu Sebe

机构 * University of Trento（特伦托大学） ； Hong Kong University of Science and Technology（香港科学与技术大学） ； University of International Relations（国际关系大学） ； Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所） ； School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院） ； Nanjing University of Science and Technology（南京理工大学） ； VCIP & TMCC & DISSec, College of Computer Science, Nankai University（南开大学计算机学院） ； University of Central Florida（佛罗里达中央大学） 纠错

Comments Accepted by NeurIPS 2025

Gemstones: A Model Suite for Multi-Faceted Scaling Laws

Sean McLeish, John Kirchenbauer, David Yu Miller, Siddharth Singh, Abhinav Bhatele, Micah Goldblum, Ashwinee Panda, Tom Goldstein

机构 * University of Maryland（马里兰大学） ； Columbia University（哥伦比亚大学） 纠错

Comments NeurIPS 2025

CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension

Rui Li, Zeyu Zhang, Xiaohe Bo, Zihang Tian, Xu Chen, Quanyu Dai, Zhenhua Dong, Ruiming Tang

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院） 纠错

Comments Accepted by NeurIPS 2025

Physics-Informed Neural Networks with Fourier Features and Attention-Driven Decoding

Rohan Arni, Carlos Blanco

机构 * High Technology High School（高科技高中） ； Institute for Gravitation and the Cosmos（引力与宇宙研究所） ； The Pennsylvania State University（宾夕法尼亚州立大学） ； Department of Physics（物理系） ； Princeton University（普林斯顿大学） 纠错

Comments 16 pages, 6 figures. Accepted at NeurIPS 2025 AI4Science workshop

A Data-Driven Prism: Multi-View Source Separation with Diffusion Model Priors

Sebastian Wagner-Carena, Aizhan Akhmetzhanova, Sydney Erickson

机构 * Center for Computational Astrophysics, Flatiron Institute（Flatiron Institute 计算天文中心） ； Center for Data Science, New York University（纽约大学数据科学中心） ； Department of Physics, Harvard University（哈佛大学物理系） ； Department of Physics, Stanford University（斯坦福大学物理系） 纠错

Comments Accepted to main conference of NeurIPS 2025. Code available at https://github.com/swagnercarena/ddprism

Domain-Adapted Granger Causality for Real-Time Cross-Slice Attack Attribution in 6G Networks

Minh K. Quan, Pubudu N. Pathirana

机构 * School of Engineering, Deakin University（工程学院，德肯大学） 纠错

Comments Accepted at NeurIPS 2025 Workshop on CauScien: Uncovering Causality in Science

Uncertainty-Guided Model Selection for Tabular Foundation Models in Biomolecule Efficacy Prediction

Jie Li, Andrew McCarthy, Zhizhuo Zhang, Stephen Young

机构 * AIML GSK 纠错

Comments Accepted by NeurIPS 2025 workshop: 2nd Workshop on Multi-modal Foundation Models and Large Language Models for Life Sciences

Supporting Creative Ownership through Deep Learning-Based Music Variation

Stephen James Krol, Maria Teresa Llano, Jon McCormack

机构 * Monash University（莫纳什大学） ； University of Sussex（Sussex大学） 纠错

Comments Paper Accepted NeurIPS Creative AI Track 2025