NeurIPS

Rethinking Evaluation of Infrared Small Target Detection

Youwei Pang, Xiaoqi Zhao, Lihe Zhang, Huchuan Lu, Georges El Fakhri, Xiaofeng Liu, Shijian Lu

机构 * Dalian University of Technology（大连理工大学） ； Yale University（耶鲁大学） ； Nanyang Technological University（南洋理工大学） 纠错

Comments NeurIPS 2025; Evaluation Toolkit: https://github.com/lartpang/PyIRSTDMetrics; Correct a few typos

Large Language Models as End-to-end Combinatorial Optimization Solvers

Xia Jiang, Yaoxin Wu, Minshuo Li, Zhiguang Cao, Yingqian Zhang

机构 * Eindhoven University of Technology（埃因霍温理工大学） ； Singapore Management University（新加坡管理学院） 纠错

Journal ref The 39th Annual Conference on Neural Information Processing Systems (NeurIPS 2025)

Foresight: Adaptive Layer Reuse for Accelerated and High-Quality Text-to-Video Generation

Muhammad Adnan, Nithesh Kurella, Akhil Arunkumar, Prashant J. Nair

机构 * The University of British Columbia（不列颠哥伦比亚大学） ； d-Matrix 纠错

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

In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer

Zechuan Zhang, Ji Xie, Yu Lu, Zongxin Yang, Yi Yang

机构 * ReLER, CCAI, Zhejiang University（研发实验室、中国人工智能学会、浙江大学） ； DBMI, HMS, Harvard University（生物医学信息研究所、哈佛医学院、哈佛大学） 纠错

Comments Accepted by NeurIPS 2025, there will be future updates for camera ready version. Code: https://github.com/River-Zhang/ICEdit

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning

Mingyang Chen, Linzhuang Sun, Tianpeng Li, Haoze Sun, Yijie Zhou, Chenzheng Zhu, Haofen Wang, Jeff Z. Pan, Wen Zhang, Huajun Chen, Fan Yang, Zenan Zhou, Weipeng Chen

机构 * Baichuan Inc.（北川公司） ； University of Chinese Academy of Sciences（中国科学院大学） ； Tongji University（同济大学） ； The University of Edinburgh（爱丁堡大学） ； Zhejiang University（浙江大学） 纠错

Comments Accepted to NeurIPS 2025

Least squares variational inference

Yvann Le Fay, Nicolas Chopin, Simon Barthelmé

Comments NeurIPS 2025, 41 pages, 8 figures

Language Models Can Predict Their Own Behavior

Dhananjay Ashok, Jonathan May

机构 * Information Sciences Institute（信息科学研究所） ； University of Southern California（南加州大学） 纠错

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

SparseDiT: Token Sparsification for Efficient Diffusion Transformer

Shuning Chang, Pichao Wang, Jiasheng Tang, Fan Wang, Yi Yang

机构 * Zhejiang University（浙江大学） ； Damo Academy, Alibaba Group（阿里达摩院） ； Hupan Lab（虎斑实验室） 纠错

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

DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction

Bowen Song, Jason Hu, Zhaoxu Luo, Jeffrey A. Fessler, Liyue Shen

Journal ref Neural Information Processing Systems (NeurIPS), 2024

Learning Image Priors through Patch-based Diffusion Models for Solving Inverse Problems

Jason Hu, Bowen Song, Xiaojian Xu, Liyue Shen, Jeffrey A. Fessler

机构 * Department of Electrical and Computer Engineering University of Michigan（电气与计算机工程系 华盛顿大学） 纠错

Journal ref Neural Information Processing Systems (NeurIPS), 2024

Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers

Chaehyun Kim, Heeseong Shin, Eunbeen Hong, Heeji Yoon, Anurag Arnab, Paul Hongsuck Seo, Sunghwan Hong, Seungryong Kim

机构 * KAIST AI（韩国科学技术院人工智能研究所） ； Korea University（韩国大学） ； ETH Zürich（苏黎世联邦理工学院） 纠错

Comments NeurIPS 2025. Project page: https://cvlab-kaist.github.io/Seg4Diff/

DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving

Shuyao Shang, Yuntao Chen, Yuqi Wang, Yingyan Li, Zhaoxiang Zhang

机构 * NLPR, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所神经网络与模式识别实验室） ； University of Chinese Academy of Sciences（中国科学院大学） 纠错

Comments NeurIPS 2025

SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning

Yiting Wang, Wanghao Ye, Ping Guo, Yexiao He, Ziyao Wang, Bowei Tian, Shwai He, Guoheng Sun, Zheyu Shen, Sihan Chen, Ankur Srivastava, Qingfu Zhang, Gang Qu, Ang Li

机构 * University of Maryland, College Park（马里兰大学科帕克分校） ； City University of Hong Kong（香港城市大学） ； University of Southern California（南加州大学） 纠错

Comments NeurIPS 2025

SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models

Pingyi Chen, Yujing Lou, Shen Cao, Jinhui Guo, Lubin Fan, Yue Wu, Lin Yang, Lizhuang Ma, Jieping Ye

机构 * Zhejiang University（浙江大学） ； Westlake University（西湖大学） ； Alibaba Cloud Computing（阿里云 computing） ； Shanghai Jiao Tong University（上海交通大学） 纠错

Comments Accepted by NeurIPS 2025

Table2LaTeX-RL: High-Fidelity LaTeX Code Generation from Table Images via Reinforced Multimodal Language Models

Jun Ling, Yao Qi, Tao Huang, Shibo Zhou, Yanqin Huang, Jiang Yang, Ziqi Song, Ying Zhou, Yang Yang, Heng Tao Shen, Peng Wang

机构 * School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院） ； Research Center for Scientific Data Hub, Zhejiang Lab, Hangzhou, China（浙江实验室科学数据中心研究中心） ； School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院） 纠错

Comments NeurIPS 2025

$i$MIND: Insightful Multi-subject Invariant Neural Decoding

Zixiang Yin, Jiarui Li, Zhengming Ding

Comments The Thirty-Ninth Annual Conference on Neural Information Processing Systems

Probabilistic Token Alignment for Large Language Model Fusion

Runjia Zeng, James Chenhao Liang, Cheng Han, Zhiwen Cao, Jiahao Liu, Xiaojun Quan, Yingjie Victor Chen, Lifu Huang, Tong Geng, Qifan Wang, Dongfang Liu

机构 * Rochester Institute of Technology（罗切斯特理工学院） ； U.S. Naval Research Laboratory（美国海军研究实验室） ； University of Missouri-Kansas City（密苏里大学-Kansas城分校） ； Adobe（Adobe公司） ； Meituan（美团） ； Sun Yat-sen University（孙中山大学） ； Purdue University（普渡大学） ； UC Davis（加州大学戴维斯分校） ； University of Rochester（罗切斯特大学） ； Rice University（莱斯大学） ； Meta AI 纠错

Comments NeurIPS 2025

Machine Learning for Campus Energy Resilience: Clustering and Time-Series Forecasting in Intelligent Load Shedding

Salim Oyinlola, Peter Olabisi Oluseyi

Comments Submitted for the NeurIPS 2025 Climata Change AI Workshop in San Diego, USA

Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points

Naoya Yamamoto, Juno Kim, Taiji Suzuki

Comments 45 pages, 2 figures. Accepted for publication at NeurIPS 2025

Preference Distillation via Value based Reinforcement Learning

Minchan Kwon, Junwon Ko, Kangil Kim, Junmo Kim

机构 * Korea Advanced Institute of Science and Technology (KAIST)（韩国先进科学技术研究院） ； Gwangju Institute of Science and Technology (GIST)（全州科学技术院） 纠错

Comments 20 page

Journal ref NIPS 2025 Poster

Differential Privacy for Euclidean Jordan Algebra with Applications to Private Symmetric Cone Programming

Zhao Song, Jianfei Xue, Lichen Zhang

机构 * University of California, Berkeley（加州大学伯克利分校） ； New York University（纽约大学） ； Massachusetts Institute of Technology（麻省理工学院） 纠错

Comments NeurIPS 2025

The Complexity of Finding Local Optima in Contrastive Learning

Jingming Yan, Yiyuan Luo, Vaggos Chatziafratis, Ioannis Panageas, Parnian Shahkar, Stelios Stavroulakis

机构 * University of California, Irvine（加州大学 Irvine 分校） ； University of California, Santa Cruz（加州大学 Santa Cruz 分校） ； Archimedes AI 纠错

Comments To appear as a conference paper in NeurIPS 2025

Redefining Experts: Interpretable Decomposition of Language Models for Toxicity Mitigation

Zuhair Hasan Shaik, Abdullah Mazhar, Aseem Srivastava, Md Shad Akhtar

机构 * IIIT Dharwad, India（印度IIIT达尔瓦德大学） ； IIIT Delhi, India（印度IIIT德里大学） ； FLaME-NLP Lab, IIIT Delhi（IIIT德里大学FLaME-NLP实验室） 纠错

Comments Accepted to the NeurIPS 2025 Research Track

SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Driving

Haiming Zhang, Yiyao Zhu, Wending Zhou, Xu Yan, Yingjie Cai, Bingbing Liu, Shuguang Cui, Zhen Li

机构 * FNii ； SSE, CUHK-Shenzhen（SSE，CUHK-Shenzhen） ； HKUST ； Huawei Noah’s Ark Lab（华为诺亚实验室） 纠错

Comments NeurIPS 2025 (Spotlight)

DCA: Graph-Guided Deep Embedding Clustering for Brain Atlases

Mo Wang, Kaining Peng, Jingsheng Tang, Hongkai Wen, Quanying Liu

机构 * SUSTech（南方科技大学） ； University of Warwick（沃里克大学） 纠错

Comments Accepted as a poster at NeurIPS 2025 with scores 5554

Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting

Kangjie Chen, Yingji Zhong, Zhihao Li, Jiaqi Lin, Youyu Chen, Minghan Qin, Haoqian Wang

机构 * Tsinghua University（清华大学） ； HKUST（香港科技大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） ； Harbin Institute of Technology（哈尔滨工业大学） 纠错

Comments Accepted by NeurIPS 2025. Project page: https://chenkangjie1123.github.io/Co-Adaptation-3DGS/, Code at: https://github.com/chenkangjie1123/Co-Adaptation-of-3DGS

The Cost of Compression: Tight Quadratic Black-Box Attacks on Sketches for $\ell_2$ Norm Estimation

Sara Ahmadian, Edith Cohen, Uri Stemmer

机构 * Google Research（谷歌研究） ； Tel Aviv University（特拉维夫大学） 纠错

Journal ref NeurIPS 2025

Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models

Zhentao He, Can Zhang, Ziheng Wu, Zhenghao Chen, Yufei Zhan, Yifan Li, Zhao Zhang, Xian Wang, Minghui Qiu

机构 * ByteDance（字节跳动） ； CASIA（中国科学院自动化研究所） ； RUC（中国人民大学） 纠错

Comments Accepted by NeurIPS 2025

Show-o2: Improved Native Unified Multimodal Models

Jinheng Xie, Zhenheng Yang, Mike Zheng Shou

机构 * Show Lab, National University of Singapore（新加坡国立大学Show实验室） ； ByteDance（字节跳动） 纠错

Comments NeurIPS 2025. (v3: update to include video understanding, OneIG, and more ablation study results)

From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring

Yang Li, Qiang Sheng, Yehan Yang, Xueyao Zhang, Juan Cao

机构 * Yang Li Media Synthesis and Forensics Lab, Institute of Computing Technology, Chinese Academy of Sciences University of Chinese Academy of Sciences（中国科学院计算技术研究所、中国科学院自动化研究所、中国科学院大学） ； Qiang Sheng Media Synthesis and Forensics Lab, Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所、中国科学院自动化研究所） ； Yehan Yang Media Synthesis and Forensics Lab, Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所、中国科学院自动化研究所） ； Xueyao Zhang The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； Juan Cao Media Synthesis and Forensics Lab, Institute of Computing Technology, Chinese Academy of Sciences University of Chinese Academy of Sciences（中国科学院计算技术研究所、中国科学院自动化研究所、中国科学院大学） 纠错

Comments NeurIPS 2025 Accepted Paper