NeurIPS

VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set

Shufan Shen, Junshu Sun, Qingming Huang, Shuhui Wang

机构 * Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS（智能信息处理重点实验室，计算技术研究所，中国科学院） ； University of Chinese Academy of Sciences（中国科学院大学） 纠错

Comments Accepted by NeurIPS 2025

Seemingly Redundant Modules Enhance Robust Odor Learning in Fruit Flies

Haiyang Li, Liao Yu, Qiang Yu, Yunliang Zang

机构 * Academy of Medical Engineering and Translational Medicine, Tianjin University（天津大学医学工程与转化医学研究院） ； School of Mathematical Sciences, Beihang University（北航大学数学科学学院） ； School of Artificial Intelligence, Tianjin University（天津大学人工智能学院） ； Xiamen Intretech Inc（厦门Intretech有限公司） 纠错

Comments 10page,Accepted by NeurIPS

FineRS: Fine-grained Reasoning and Segmentation of Small Objects with Reinforcement Learning

Lu Zhang, Jiazuo Yu, Haomiao Xiong, Ping Hu, Yunzhi Zhuge, Huchuan Lu, You He

机构 * Dalian University of Technology（大连理工大学） ； University of Electronic Science and Technology of China（电子科技大学） ； Tsinghua Shenzhen International Graduate School（清华大学深圳国际graduate school） 纠错

Comments Accepted to NeurIPS 2025

Towards Reliable Code-as-Policies: A Neuro-Symbolic Framework for Embodied Task Planning

Sanghyun Ahn, Wonje Choi, Junyong Lee, Jinwoo Park, Honguk Woo

Comments Accepted at NeurIPS 2025 Spotlight

Relieving the Over-Aggregating Effect in Graph Transformers

Junshu Sun, Wanxing Chang, Chenxue Yang, Qingming Huang, Shuhui Wang

机构 * Institute of Computing Technology, CAS（中国科学院计算技术研究所） ； University of Chinese Academy of Sciences（中国科学院大学） ； DAMO Academy, Alibaba Group（阿里巴巴集团大模型研究院） ； Agriculture Information Institute, CAAS（中国农业科学院农业信息研究所） 纠错

Comments Accepted by NeurIPS 2025

Correlation Dimension of Auto-Regressive Large Language Models

Xin Du, Kumiko Tanaka-Ishii

机构 * Waseda University（早稻田大学） 纠错

Comments Accepted at NeurIPS 2025

Improved Training Technique for Shortcut Models

Anh Nguyen, Viet Nguyen, Duc Vu, Trung Dao, Chi Tran, Toan Tran, Anh Tran

机构 * Qualcomm AI Research（高通人工智能研究） 纠错

Comments Accepted at NeurIPS 2025

Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models

Xiyuan Zhang, Danielle C. Maddix, Junming Yin, Nick Erickson, Abdul Fatir Ansari, Boran Han, Shuai Zhang, Leman Akoglu, Christos Faloutsos, Michael W. Mahoney, Cuixiong Hu, Huzefa Rangwala, George Karypis, Bernie Wang

Comments NeurIPS 2025. We released both classifier (autogluon/mitra-classifier) and regressor (autogluon/mitra-regressor) model weights on HuggingFace

Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency

Yukun Jiang, Mingjie Li, Michael Backes, Yang Zhang

Comments Accepted in NeurIPS 2025

Towards Physics-informed Spatial Intelligence with Human Priors: An Autonomous Driving Pilot Study

Guanlin Wu, Boyan Su, Yang Zhao, Pu Wang, Yichen Lin, Hao Frank Yang

机构 * Johns Hopkins University（约翰霍普金斯大学） 纠错

Comments NeurIPS 2025 (Spotlight)

Distributionally Robust Feature Selection

Maitreyi Swaroop, Tamar Krishnamurti, Bryan Wilder

机构 * Machine Learning Department（机器学习系） ； Division of General Internal Medicine（内科医学部） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

Comments Accepted at NeurIPS 2025

PhysVLM-AVR: Active Visual Reasoning for Multimodal Large Language Models in Physical Environments

Weijie Zhou, Xuantang Xiong, Yi Peng, Manli Tao, Chaoyang Zhao, Honghui Dong, Ming Tang, Jinqiao Wang

机构 * Beijing Jiaotong University（北京交通大学） ； Tencent Robotics X & Futian Laboratory, Shenzhen（腾讯机器人X及福田实验室，深圳） ； Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences（基础模型研究中心，中国科学院自动化研究所） ； ObjectEye Inc（ObjectEye公司） 纠错

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

Confounding Robust Deep Reinforcement Learning: A Causal Approach

Mingxuan Li, Junzhe Zhang, Elias Bareinboim

机构 * Columbia University（哥伦比亚大学） ； Syracuse University（Syracuse大学） 纠错

Comments NeurIPS 2025

Addressing Mark Imbalance in Integration-free Neural Marked Temporal Point Processes

Sishun Liu, Ke Deng, Yongli Ren, Yan Wang, Xiuzhen Zhang

机构 * RMIT University（皇家墨尔本理工大学） ； Macquarie University（麦考瑞大学） 纠错

Comments NeurIPS 2025 poster

Exploration via Feature Perturbation in Contextual Bandits

Seouh-won Yi, Min-hwan Oh

机构 * Seoul National University（首尔国立大学） 纠错

Comments Accepted at NeurIPS 2025 (spotlight)

Axial Neural Networks for Dimension-Free Foundation Models

Hyunsu Kim, Jonggeon Park, Joan Bruna, Hongseok Yang, Juho Lee

机构 * KAIST（韩国科学技术院） ； New York University（纽约大学） 纠错

Journal ref NeurIPS 2025

E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization

Wenpu Li, Bangyan Liao, Yi Zhou, Qi Xu, Pian Wan, Peidong Liu

机构 * Westlake University（西拉丘市大学） ； Zhejiang University（浙江大学） ； Hunan University（湖南大学） ； Wuhan University（武汉大学） ； Georgia Institute of Technology（佐治亚理工学院） 纠错

Comments The Thirty-Ninth Annual Conference on Neural Information Processing Systems(NeurIPS 2025)

Domain Knowledge Infused Conditional Generative Models for Accelerating Drug Discovery

Bing Hu, Jong-Hoon Park, Helen Chen, Young-Rae Cho, Anita Layton

Comments 17 pages, The NeurIPS 2025 Workshop on AI Virtual Cells and Instruments: A New Era in Drug Discovery and Development (AI4D3 2025), San Diego, California, USA, 2025

Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement

Yidi Liu, Xueyang Fu, Jie Huang, Jie Xiao, Dong Li, Wenlong Zhang, Lei Bai, Zheng-Jun Zha

机构 * University of Science and Technology of China（中国科学技术大学） ； Shanghai AI Laboratory（上海人工智能实验室） 纠错

Comments Accepted by NeurIPS 2025

SegMASt3R: Geometry Grounded Segment Matching

Rohit Jayanti, Swayam Agrawal, Vansh Garg, Siddharth Tourani, Muhammad Haris Khan, Sourav Garg, Madhava Krishna

机构 * IIIT Hyderabad（海得拉巴印度理工学院） ； University of Heidelberg（海德堡大学） ； MBZUAI 纠错

Comments Accepted to The 39th Annual Conference on Neural Information Processing Systems (NeurIPS 2025) as a Spotlight (top 3.5%)

Photorealistic Inpainting for Perturbation-based Explanations in Ecological Monitoring

Günel Aghakishiyeva, Jiayi Zhou, Saagar Arya, Julian Dale, James David Poling, Holly R. Houliston, Jamie N. Womble, Gregory D. Larsen, David W. Johnston, Brinnae Bent

机构 * Duke University（杜克大学） ； University of Agder（阿格德大学） ； University of Cambridge（剑桥大学） ； U.S. National Park Service Department of Interior（美国国家公园管理局） ； Alaska Spatial Science（阿拉斯加空间科学） 纠错

Comments NeurIPS 2025 Imageomics Workshop

S$^2$NN: Sub-bit Spiking Neural Networks

Wenjie Wei, Malu Zhang, Jieyuan Zhang, Ammar Belatreche, Shuai Wang, Yimeng Shan, Hanwen Liu, Honglin Cao, Guoqing Wang, Yang Yang, Haizhou Li

机构 * University of Electronic Science and Technology of China（电子科学与技术大学） ； Shenzhen Loop Area Institute（深圳河套学院） ； Northumbria University（北诺姆布里亚大学） ； Liaoning Technical University（辽宁技术大学） ； The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen)（香港中文大学（深圳）） 纠错

Comments 29 pages, 6 figures

Journal ref NeurIPS 2025

Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data

Zi Liang, Qingqing Ye, Xuan Liu, Yanyun Wang, Jianliang Xu, Haibo Hu

机构 * The Hong Kong Polytechnic University（香港理工大学） ； University of California, San Diego（加州大学圣地亚哥分校） ； The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）） ； Hong Kong Baptist University（香港 Baptist 大学） ； PolyU Research Centre for Privacy and Security Technologies in Future Smart Systems（PolyU 未来智能系统隐私与安全技术研究中心） 纠错

Comments Camera Ready of NeurIPS 2025 Spotlight. Source code: https://github.com/liangzid/VirusInfectionAttack

RLGF: Reinforcement Learning with Geometric Feedback for Autonomous Driving Video Generation

Tianyi Yan, Wencheng Han, Xia Zhou, Xueyang Zhang, Kun Zhan, Cheng-zhong Xu, Jianbing Shen

机构 * SKL-IOTSC, Computer and Information Science, University of Macau（澳门大学计算机与信息科学学院） ； Li Auto Inc（利汽车公司） 纠错

Comments NeurIPS 2025

On Optimal Steering to Achieve Exact Fairness

Mohit Sharma, Amit Jayant Deshpande, Chiranjib Bhattacharyya, Rajiv Ratn Shah

机构 * Department of Computer Science IIIT Delhi, India（印度德里IIIT计算机科学系） ； Microsoft Research India（微软印度研究院） ； Department of Computer Science and Automation Indian Institute of Science, Bengaluru, India（印度班加罗尔印度科学学院计算机科学与自动化系） 纠错

Comments Accepted for Presentation at Neurips 2025

PolyJuice Makes It Real: Black-Box, Universal Red Teaming for Synthetic Image Detectors

Sepehr Dehdashtian, Mashrur M. Morshed, Jacob H. Seidman, Gaurav Bharaj, Vishnu Naresh Boddeti

机构 * Michigan State University（密歇根州立大学） ； Reality Defender 纠错

Comments Accepted as NeurIPS 2025 poster

Adaptive Algorithms with Sharp Convergence Rates for Stochastic Hierarchical Optimization

Xiaochuan Gong, Jie Hao, Mingrui Liu

Comments NeurIPS 2025

Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning

Yeongbin Seo, Dongha Lee, Jaehyung Kim, Jinyoung Yeo

机构 * Department of Artificial Intelligence（人工智能系） ； Yonsei University（延世大学） 纠错

Comments NeurIPS 2025 spotlight

Magical: Medical Lay Language Generation via Semantic Invariance and Layperson-tailored Adaptation

Weibin Liao, Tianlong Wang, Yinghao Zhu, Yasha Wang, Junyi Gao, Liantao Ma

机构 * National Engineering Research Center For Software Engineering, Peking University（软件工程国家工程研究中心，北京大学） ； School of Computer Science, Peking University（北京大学计算机学院） ； School of Computing and Data Science, The University of Hong Kong（香港大学计算科学与数据科学学院） ； Centre for Medical Informatics, University of Edinburgh（爱丁堡大学医学信息中心） ； Health Data Research UK（英国健康数据研究） 纠错

Comments Accepted by NeurIPS 2025

Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown

Emile Anand, Sarah Liaw

机构 * Georgia Institute of Technology（佐治亚理工学院） ； Havard University School of Engineeering and Applied Sciences（哈佛大学工程与应用科学学院） 纠错

Comments 41 pages. Accepted at NeurIPS 2025