NeurIPS

In the Eye of MLLM: Benchmarking Egocentric Video Intent Understanding with Gaze-Guided Prompting

Taiying Peng, Jiacheng Hua, Miao Liu, Feng Lu

机构 * State Key Laboratory of VR Technology and Systems, School of CSE, Beihang University（虚拟现实技术与系统国家重点实验室，北京航空航天大学计算机科学与工程学院） ； College of AI, Tsinghua University（清华大学人工智能学院） 纠错

Comments Accepted to NeurIPS 2025

BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models

Peiyan Li, Yixiang Chen, Hongtao Wu, Xiao Ma, Xiangnan Wu, Yan Huang, Liang Wang, Tao Kong, Tieniu Tan

机构 * CASIA（中国科学院自动化研究所） ； ByteDance Seed（字节跳动种子实验室） ； UCAS（中国科学院大学） ； FiveAges ； NJU（南京大学） 纠错

Comments NeurIPS 2025

DefenderBench: A Toolkit for Evaluating Language Agents in Cybersecurity Environments

Chiyu Zhang, Marc-Alexandre Cote, Michael Albada, Anush Sankaran, Jack W. Stokes, Tong Wang, Amir Abdi, William Blum, Muhammad Abdul-Mageed

机构 * Microsoft（微软公司） ； The University of British Columbia（不列颠哥伦比亚大学） 纠错

Comments Accepted by NeurIPS 2025 Workshop Scaling Environments for Agents (SEA)

Protein Design with Dynamic Protein Vocabulary

Nuowei Liu, Jiahao Kuang, Yanting Liu, Tao Ji, Changzhi Sun, Man Lan, Yuanbin Wu

机构 * School of Computer Science and Technology, East China Normal University（东华师范大学计算机科学与技术学院） ； College of Foreign Languages and Literatures, Fudan University（复旦大学外国语言文学学院） ； Institute of Artificial Intelligence (TeleAI), China Telecom（中国电信人工智能研究所） 纠错

Comments Accepted to NeurIPS 2025 (Spotlight)

MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems

Xuanming Zhang, Yuxuan Chen, Samuel Yeh, Sharon Li

机构 * Tsinghua University（清华大学） 纠错

Comments NeurIPS 2025 Spotlight

Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval

Siting Li, Xiang Gao, Simon Shaolei Du

Comments NeurIPS 2025; 27 pages, 6 figures

VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning

Qi Wang, Yanrui Yu, Ye Yuan, Rui Mao, Tianfei Zhou

机构 * Beijing Institute of Technology（北京理工大学） ； Shenzhen University（深圳大学） 纠错

Comments Accepted by NeurIPS 2025. Code: https://github.com/QiWang98/VideoRFT

Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language Navigation

Shuo Wang, Yongcai Wang, Wanting Li, Xudong Cai, Yucheng Wang, Maiyue Chen, Kaihui Wang, Zhizhong Su, Deying Li, Zhaoxin Fan

机构 * Renmin University of China（中国人民大学） ； Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing（北京未来区块链与隐私计算先进创新中心） ； Horizon Robotics（地平线机器人） 纠错

Journal ref NeurIPS 2025

Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking

Changlun Li, Yao Shi, Chen Wang, Qiqi Duan, Runke Ruan, Weijie Huang, Haonan Long, Lijun Huang, Nan Tang, Yuyu Luo

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港理工大学（广州）） ； Paradoox AI Research（Paradoox AI研究院） 纠错

Comments NeurIPS 2025 Datasets and Benchmarks Track

Mind the (Data) Gap: Evaluating Vision Systems in Small Data Applications

Samuel Stevens, S M Rayeed, Jenna Kline

机构 * The Ohio State University（俄亥俄州立大学） ； Rensselaer Polytechnic Institute（拉特格斯理工学院） 纠错

Comments 5 pages (main text), 3 figures. Accepted at the Imageomics Workshop at NeurIPS 2025

OpenLex3D: A Tiered Evaluation Benchmark for Open-Vocabulary 3D Scene Representations

Christina Kassab, Sacha Morin, Martin Büchner, Matías Mattamala, Kumaraditya Gupta, Abhinav Valada, Liam Paull, Maurice Fallon

Comments NeurIPS 2025

ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization

Zechun Liu, Changsheng Zhao, Hanxian Huang, Sijia Chen, Jing Zhang, Jiawei Zhao, Scott Roy, Lisa Jin, Yunyang Xiong, Yangyang Shi, Lin Xiao, Yuandong Tian, Bilge Soran, Raghuraman Krishnamoorthi, Tijmen Blankevoort, Vikas Chandra

机构 * Meta AI 纠错

Comments NeurIPS 2025. Model weights are available at https://huggingface.co/collections/facebook/mobilellm-6722be18cb86c20ebe113e95

ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference

Xiang Liu, Zhenheng Tang, Peijie Dong, Zeyu Li, Yue Liu, Bo Li, Xuming Hu, Xiaowen Chu

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）） ； CSE, The Hong Kong University of Science and Technology（香港科学与技术大学计算机科学与工程系） ； Guangzhou HKUST Fok Ying Tung Research Institute（广州HKUST福 Ying Tung研究 institute） ； Terminus Technologies 纠错

Comments NeurIPS 2025

Evaluating multiple models using labeled and unlabeled data

Divya Shanmugam, Shuvom Sadhuka, Manish Raghavan, John Guttag, Bonnie Berger, Emma Pierson

机构 * Department of Computer Science, Cornell University（康奈尔大学计算机科学系） ； Department of Electrical Engineering & Computer Science, MIT（麻省理工学院电子工程与计算机科学系） ； Sloan School of Management, MIT（麻省理工学院斯隆管理学院） ； Department of Electrical Engineering & Computer Sciences, UC Berkeley（伯克利大学电子工程与计算机科学系） 纠错

Comments To appear at NeurIPS 2025

Go With the Flow: Fast Diffusion for Gaussian Mixture Models

George Rapakoulias, Ali Reza Pedram, Fengjiao Liu, Lingjiong Zhu, Panagiotis Tsiotras

机构 * Georgia Institute of Technology（佐治亚理工学院） ； University of Oklahoma（俄克拉荷马大学） ； FAMU-FSU College of Engineering（佛罗里达大学-佛罗里达州立大学工程学院） ； Florida State University（佛罗里达州立大学） 纠错

Comments NIPS 2025 (spotlight)

Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning

Yuqi Jia, Minghong Fang, Hongbin Liu, Jinghuai Zhang, Neil Zhenqiang Gong

Comments Conference on Neural Information Processing Systems (NeurIPS) 2025

ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training

Adel Nabli, Louis Fournier, Pierre Erbacher, Louis Serrano, Eugene Belilovsky, Edouard Oyallon

Journal ref The Thirty-ninth Annual Conference on Neural Information Processing Systems, Dec 2025, San diego (Californie), United States

When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers

Divij Handa, Zehua Zhang, Amir Saeidi, Shrinidhi Kumbhar, Md Nayem Uddin, Aswin RRV, Chitta Baral

机构 * Arizona State University（亚利桑那州立大学） 纠错

Comments Published in Reliable ML from Unreliable Data workshop @ NeurIPS 2025

Competitive Advantage Attacks to Decentralized Federated Learning

Yuqi Jia, Minghong Fang, Neil Zhenqiang Gong

Comments Conference on Neural Information Processing Systems (NeurIPS) 2025

Replicable Clustering

Hossein Esfandiari, Amin Karbasi, Vahab Mirrokni, Grigoris Velegkas, Felix Zhou

Comments to be published in NeurIPS 2023

Scaling Language-Centric Omnimodal Representation Learning

Chenghao Xiao, Hou Pong Chan, Hao Zhang, Weiwen Xu, Mahani Aljunied, Yu Rong

机构 * DAMO Academy, Alibaba Group（达摩院，阿里巴巴集团） 纠错

Comments NeurIPS 2025

FACE: Faithful Automatic Concept Extraction

Dipkamal Bhusal, Michael Clifford, Sara Rampazzi, Nidhi Rastogi

机构 * Rochester Institute of Technology（罗切斯特理工大学） ； Toyota InfoTech Labs（丰田信息科技实验室） ； University of Florida（佛罗里达大学） 纠错

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

SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction

Wenyue Chen, Peng Li, Wangguandong Zheng, Chengfeng Zhao, Mengfei Li, Yaolong Zhu, Zhiyang Dou, Ronggang Wang, Yuan Liu

机构 * PKU（北京大学） ； HKUST（香港科技大学） ； SEU（上海师范大学） ； HKU（香港大学） 纠错

Comments NeurIPS 2025 https://xishuxishu.github.io/SyncHuman.github.io/

Trust Region Reward Optimization and Proximal Inverse Reward Optimization Algorithm

Yang Chen, Menglin Zou, Jiaqi Zhang, Yitan Zhang, Junyi Yang, Gael Gendron, Libo Zhang, Jiamou Liu, Michael J. Witbrock

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； University of Auckland（奥克兰大学） ； Chongqing University（重庆大学） 纠错

Comments Accepted to NeurIPS 2025. Title used at submission and review: PIRO: Toward Stable Reward Learning for Inverse RL via Monotonic Policy Divergence Reduction

InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition

Yijie Zheng, Weijie Wu, Qingyun Li, Xuehui Wang, Xu Zhou, Aiai Ren, Jun Shen, Long Zhao, Guoqing Li, Xue Yang

机构 * Aerospace Information Research Institute, Chinese Academy of Sciences（航天信息研究所，中国科学院） ； University of Chinese Academy of Sciences（中国科学院大学） ； Harbin Institute of Technology（哈尔滨工业大学） ； Shanghai Jiao Tong University（上海交通大学） ； University of Wollongong（沃林戈大学） ； SAIS, Shanghai Jiao Tong University（上海交通大学国际关系学院） 纠错

Comments Accepted to NeurIPS 2025

Breaking the Compression Ceiling: Data-Free Pipeline for Ultra-Efficient Delta Compression

Xiaohui Wang, Peng Ye, Chenyu Huang, Shenghe Zheng, Bo Zhang, Lei Bai, Wanli Ouyang, Tao Chen

机构 * Fudan University（复旦大学） ； Shanghai AI Laboratory（上海人工智能实验室） ； Shanghai Innovation Institute（上海创新研究院） ； The Chinese University of Hong Kong（香港中文大学） 纠错

Comments Accepted at NeurIPS 2025

Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model

Ruiping Liu, Junwei Zheng, Yufan Chen, Zirui Wang, Kunyu Peng, Kailun Yang, Jiaming Zhang, Marc Pollefeys, Rainer Stiefelhagen

机构 * Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院） ； Hunan University（湖南大学） ； ETH Zurich（苏黎世联邦理工学院） 纠错

Comments Accepted to NeurIPS 2025 Datasets and Benchmarks Track. Dataset and Code: https://github.com/RuipingL/Situat3DChange

Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks

Xuan Tang, Han Zhang, Yuan Cao, Difan Zou

机构 * School of Computing & Data Science, The University of Hong Kong（计算与数据科学学院，香港大学） 纠错

Comments 71 pages, 12 figures, NeurIPS 2025

Nonlinearly Preconditioned Gradient Methods: Momentum and Stochastic Analysis

Konstantinos Oikonomidis, Jan Quan, Panagiotis Patrinos

Comments NeurIPS 2025 poster

Test-Time Adaptation by Causal Trimming

Yingnan Liu, Rui Qiao, Mong Li Lee, Wynne Hsu

机构 * School of Computing, National University of Singapore（新加坡国立大学计算机学院） ； Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究所） ； Singapore-MIT Alliance for Research and Technology（新加坡-麻省理工联合研究技术联盟） 纠错

Comments Accepted to the Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025); Code is available at https://github.com/NancyQuris/TACT