NeurIPS - arXivDaily 期刊&会议

2510.13768 2025-10-16 cs.CV cs.AI q-bio.NC

Scaling Vision Transformers for Functional MRI with Flat Maps

Connor Lane, Daniel Z. Kaplan, Tanishq Mathew Abraham, Paul S. Scotti

机构 * Baylor College of Medicine（贝勒医学院）； University of Florida（佛罗里达大学）

Comments NeurIPS 2025 Workshop, Foundation Models for the Brain and Body; Code: https://github.com/MedARC-AI/fmri-fm; Discord: https://discord.gg/tVR4TWnRM9

2507.07136 2025-10-16 cs.CV cs.GR

LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS

Wanhua Li, Yujie Zhao, Minghan Qin, Yang Liu, Yuanhao Cai, Chuang Gan, Hanspeter Pfister

机构 * Harvard University（哈佛大学）； University of Chinese Academy of Sciences（中国科学院大学）； Tsinghua University（清华大学）； Johns Hopkins University（约翰霍普金斯大学）； MIT-IBM Watson AI Lab（MIT-IBM Watson人工智能实验室）； UMass Amherst（马萨诸塞大学阿姆赫斯特分校）

Comments Accepted by NeurIPS 2025. Project Page: https://langsplat-v2.github.io

2510.13451 2025-10-16 cs.CR

Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts

Li Bai, Qingqing Ye, Xinwei Zhang, Sen Zhang, Zi Liang, Jianliang Xu, Haibo Hu

Comments To appear in NeurIPS 2025

2510.13438 2025-10-16 stat.ML cs.LG

Near-Optimality of Contrastive Divergence Algorithms

Pierre Glaser, Kevin Han Huang, Arthur Gretton

Comments 54 pages

Journal ref Neurips 2024

2510.12966 2025-10-16 cs.CL

3-Model Speculative Decoding

Sanghyun Byun, Mohanad Odema, Jung Ick Guack, Baisub Lee, Jacob Song, Woo Seong Chung

机构 * LG Electronics USA（LG电子美国公司）

Comments Accepted at NeurIPS SPIGM 2025

2510.12931 2025-10-16 cs.CV cs.CL

Unifying Vision-Language Latents for Zero-label Image Caption Enhancement

Sanghyun Byun, Jung Ick Guack, Mohanad Odema, Baisub Lee, Jacob Song, Woo Seong Chung

机构 * LG Electronics USA（LG电子美国公司）

Comments Accepted to PMLR and NeurIPS 2025 UniReps

2510.09710 2025-10-16 cs.CL cs.AI

SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG

Xiaonan Si, Meilin Zhu, Simeng Qin, Lijia Yu, Lijun Zhang, Shuaitong Liu, Xinfeng Li, Ranjie Duan, Yang Liu, Xiaojun Jia

机构 * Institute of Software Chinese Academy of Sciences Beijing China（中国科学院软件研究所）； Key Laboratory of System Software (Chinese Academy of Sciences) and State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China（中国科学院系统软件重点实验室和计算机科学国家重点实验室）； University of Chinese Academy of Sciences, Beijing, China（中国科学院大学）； Northeast University China（东北大学）； Institute of Ai For industries Nanjing China（人工智能产业研究院）； Southwest University China（西南大学）； Nanyang Technological University Singapore（新加坡南洋理工大学）； Alibaba China（阿里巴巴（中国））

Comments Accepted at NeurIPS 2025

2510.07575 2025-10-16 cs.AI cs.LG

Benchmarking is Broken -- Don't Let AI be its Own Judge

Zerui Cheng, Stella Wohnig, Ruchika Gupta, Samiul Alam, Tassallah Abdullahi, João Alves Ribeiro, Christian Nielsen-Garcia, Saif Mir, Siran Li, Jason Orender, Seyed Ali Bahrainian, Daniel Kirste, Aaron Gokaslan, Mikołaj Glinka, Carsten Eickhoff, Ruben Wolff

机构 * Princeton University（普林斯顿大学）； CISPA Helmholtz Center for Information Security（CISPA海德堡信息安全中心）； Michigan State University（密歇根州立大学）； Ohio State University（俄亥俄州立大学）； Brown University（布朗大学）； Massachusetts Institute of Technology（麻省理工学院）； University of California, Los Angeles（加州大学洛杉矶分校）； University of Tübingen（图宾根大学）； Old Dominion University（旧 Dominion 大学）； Technical University of Munich（慕尼黑技术大学）； Cornell University（康奈尔大学）； Forest AI（森林AI）

Comments 14 pages; Accepted to NeurIPS 2025. Link to poster: https://neurips.cc/virtual/2025/poster/121919; Link to project website: https://www.peerbench.ai/

2508.19972 2025-10-16 cs.CV cs.AI cs.CL

GLSim: Detecting Object Hallucinations in LVLMs via Global-Local Similarity

Seongheon Park, Sharon Li

机构 * Department of Computer Sciences University of Wisconsin-Madison（计算机科学系威斯康星大学麦迪逊分校）

Comments NeurIPS 2025

2507.10013 2025-10-16 cs.CV cs.CL

Cross-modal Associations in Vision and Language Models: Revisiting the Bouba-Kiki Effect

Tom Kouwenhoven, Kiana Shahrasbi, Tessa Verhoef

机构 * Leiden Institute of Advanced Computer Science（莱顿先进计算机科学研究所）； Leiden University（莱顿大学）

Comments Presented at the Thirty-Ninth Annual Conference on Neural Information Processing Systems (2025)

2506.10412 2025-10-16 cs.LG cs.AI cs.CL

Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Series

Ching Chang, Jeehyun Hwang, Yidan Shi, Haixin Wang, Wen-Chih Peng, Tien-Fu Chen, Wei Wang

机构 * University of California, Los Angeles（加州大学洛杉矶分校）； National Yang Ming Chiao Tung University（国立阳明交通大学）

Comments This paper has been accepted by the NeurIPS 2025 Datasets and Benchmarks Track

2505.22760 2025-10-16 math.OC cs.LG math.PR

Non-convex entropic mean-field optimization via Best Response flow

Razvan-Andrei Lascu, Mateusz B. Majka

机构 * RIKEN AIP（日本理化学研究所Advanced Institute for Priority Research）； Heriot-Watt University（赫瑞-瓦特大学）

Comments NeurIPS 2025

2505.18185 2025-10-16 eess.SP cs.LG

BrainOmni: A Brain Foundation Model for Unified EEG and MEG Signals

Qinfan Xiao, Ziyun Cui, Chi Zhang, Siqi Chen, Wen Wu, Andrew Thwaites, Alexandra Woolgar, Bowen Zhou, Chao Zhang

机构 * Shanghai Artificial Intelligence Laboratory, China（上海人工智能实验室）； Department of Electronic Engineering, Tsinghua University, China（清华大学电子工程系）； Department of Psychology, University of Cambridge, UK（剑桥大学心理学系）； Speech Hearing and Phonetic Sciences, University College London, UK（伦敦大学学院语音听力与语音科学系）； MRC Cognition and Brain Sciences Unit, University of Cambridge, UK（剑桥大学MRC认知与脑科学单位）

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

2504.04160 2025-10-16 cs.LG cs.MA

OrbitZoo: Real Orbital Systems Challenges for Reinforcement Learning

Alexandre Oliveira, Katarina Dyreby, Francisco Caldas, Cláudia Soares

机构 * NOVA LINCS

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

2411.08891 2025-10-16 cs.IR cs.AI

Reliable Decision Making via Calibration Oriented Retrieval Augmented Generation

Chaeyun Jang, Deukhwan Cho, Seanie Lee, Hyungi Lee, Juho Lee

机构 * KAIST（韩国科学技术院）； Kookmin University（韩国釜山大学）

Comments Accepted by NeurIPS 2025

2408.03459 2025-10-16 cs.LG

Can DPO Learn Diverse Human Values? A Theoretical Scaling Law

Shawn Im, Sharon Li

机构 * Department of Computer Sciences University of Wisconsin-Madison（计算机科学系威斯康星大学麦迪逊分校）

Comments NeurIPS 2025

2206.13464 2025-10-16 cs.LG cs.AI

When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning

Haoyi Niu, Shubham Sharma, Yiwen Qiu, Ming Li, Guyue Zhou, Jianming Hu, Xianyuan Zhan

机构 * Tsinghua University（清华大学）； Indian Institute of Technology（印度理工学院）； Shanghai Jiaotong University（上海交通大学）； Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）； Shanghai AI Laboratory（上海人工智能实验室）

Comments NeurIPS 2022 Spotlight

2206.02346 2025-10-16 math.OC cs.AI cs.LG cs.SY eess.SY

Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPs

Dongsheng Ding, Kaiqing Zhang, Jiali Duan, Tamer Başar, Mihailo R. Jovanović

机构 * University of Tennessee, Knoxville（田纳西大学）； University of Maryland, College Park（马里兰大学）； Apple Inc.（苹果公司）； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； University of Southern California（南加州大学）

Comments 76 pages, 4 figures, 2 tables; Journal version of the NeurIPS 2020 paper; Accepted to JMLR