NeurIPS

Reinforcement Learning for Long-Horizon Multi-Turn Search Agents

Vivek Kalyan, Martin Andrews

机构 * Red Cat Labs, Singapore（红猫实验室（新加坡）） ； Singapore（新加坡） 纠错

Comments 4 pages plus references and appendices. Accepted into the First Workshop on Multi-Turn Interactions in Large Language Models at NeurIPS 2025

Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation

Kang Zhang, Trung X. Pham, Suyeon Lee, Axi Niu, Arda Senocak, Joon Son Chung

机构 * KAIST, South Korea（韩国釜山国立大学） ； NWPU, China（中国西北工业大学） ； UNIST, South Korea（韩国全南国立大学） 纠错

Comments accepted by NeurIPS 2025

Learning Parameterized Skills from Demonstrations

Vedant Gupta, Haotian Fu, Calvin Luo, Yiding Jiang, George Konidaris

机构 * Brown University（布朗大学） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

Comments Neurips 2025

Information-Theoretic Discrete Diffusion

Moongyu Jeon, Sangwoo Shin, Dongjae Jeon, Albert No

机构 * Department of Artificial Intelligence, Yonsei University（人工智能系，延世大学） ； Department of Computer Science, Yonsei University（计算机科学系，延世大学） 纠错

Comments Accepted at NeurIPS 2025

FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic

Kanghyun Choi, Hyeyoon Lee, SunJong Park, Dain Kwon, Jinho Lee

机构 * Department of Electrical and Computer Engineering（电气与计算机工程系） ； Seoul National University（首尔国立大学） 纠错

Comments NeurIPS 2025

Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models

Byeonghu Na, Mina Kang, Jiseok Kwak, Minsang Park, Jiwoo Shin, SeJoon Jun, Gayoung Lee, Jin-Hwa Kim, Il-Chul Moon

机构 * KAIST（韩国科学技术院） ； NAVER AI Lab（NAVER人工智能实验室） ； SNU AIIS（首尔国立大学人工智能研究所） 纠错

Comments Accepted at NeurIPS 2025

Mars-Bench: A Benchmark for Evaluating Foundation Models for Mars Science Tasks

Mirali Purohit, Bimal Gajera, Vatsal Malaviya, Irish Mehta, Kunal Kasodekar, Jacob Adler, Steven Lu, Umaa Rebbapragada, Hannah Kerner

机构 * School of Computing and Augmented Intelligence, Arizona State University（计算与增强智能学院，亚利桑那州立大学） ； School of Earth and Space Exploration, Arizona State University（地球与空间探索学院，亚利桑那州立大学） ； Jet Propulsion Laboratory, California Institute of Technology（喷气推进实验室，加州理工学院） 纠错

Comments Accepted at NeurIPS 2025

Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Models

Byeonghu Na, Minsang Park, Gyuwon Sim, Donghyeok Shin, HeeSun Bae, Mina Kang, Se Jung Kwon, Wanmo Kang, Il-Chul Moon

机构 * KAIST（韩国科学技术院） ； NAVER Cloud（NAVER云） 纠错

Comments Accepted at NeurIPS 2025

PlanarGS: High-Fidelity Indoor 3D Gaussian Splatting Guided by Vision-Language Planar Priors

Xirui Jin, Renbiao Jin, Boying Li, Danping Zou, Wenxian Yu

机构 * Shanghai Jiao Tong University（上海交通大学） ； Monash University（墨尔本大学） 纠错

Comments Accepted by NeurIPS 2025. Project page: https://planargs.github.io

Improving the Straight-Through Estimator with Zeroth-Order Information

Ningfeng Yang, Tor M. Aamodt

机构 * University of British Columbia（不列颠哥伦比亚大学） 纠错

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

Evaluating In Silico Creativity: An Expert Review of AI Chess Compositions

Vivek Veeriah, Federico Barbero, Marcus Chiam, Xidong Feng, Michael Dennis, Ryan Pachauri, Thomas Tumiel, Johan Obando-Ceron, Jiaxin Shi, Shaobo Hou, Satinder Singh, Nenad Tomašev, Tom Zahavy

机构 * Google DeepMind（谷歌DeepMind） ； University of Oxford（牛津大学） ； Mila, University of Montreal（蒙特利尔大学Mila） ； Google（谷歌） 纠错

Comments Accepted at the Creative AI Track, NeurIPS 2025

Multi-Environment POMDPs: Discrete Model Uncertainty Under Partial Observability

Eline M. Bovy, Caleb Probine, Marnix Suilen, Ufuk Topcu, Nils Jansen

机构 * Radboud University（拉德堡德大学） ； The University of Texas at Austin（德克萨斯大学奥斯汀分校） ； University of Antwerp（安特卫普大学） ； Ruhr-University Bochum（波鸿鲁尔大学） ； Radboud University Bochum（波鸿鲁尔大学） 纠错

Comments Accepted at NeurIPS 2025

In Search of the Unknown Unknowns: A Multi-Metric Distance Ensemble for Out of Distribution Anomaly Detection in Astronomical Surveys

Siddharth Chaini, Federica B. Bianco, Ashish Mahabal

机构 * University of Delaware（德雷塞尔大学） ； Rubin Observatory（鲁宾天文台） ； Caltech（加州理工学院） 纠错

Comments 9 pages, 5 figures, Accepted at the 2025 Machine Learning and the Physical Sciences (ML4PS) workshop at NeurIPS

VIKING: Deep variational inference with stochastic projections

Samuel G. Fadel, Hrittik Roy, Nicholas Krämer, Yevgen Zainchkovskyy, Stas Syrota, Alejandro Valverde Mahou, Carl Henrik Ek, Søren Hauberg

机构 * Technical University of Denmark（丹麦技术大学） ； University of Cambridge（剑桥大学） 纠错

Comments NeurIPS 2025 (poster)

DBLoss: Decomposition-based Loss Function for Time Series Forecasting

Xiangfei Qiu, Xingjian Wu, Hanyin Cheng, Xvyuan Liu, Chenjuan Guo, Jilin Hu, Bin Yang

机构 * East China Normal University（东华师范大学） 纠错

Comments Accepted by NeurIPS 2025

Structure-Aware Fusion with Progressive Injection for Multimodal Molecular Representation Learning

Zihao Jing, Yan Sun, Yan Yi Li, Sugitha Janarthanan, Alana Deng, Pingzhao Hu

Comments Accepted by NeurIPS 2025

Chain of Execution Supervision Promotes General Reasoning in Large Language Models

Nuo Chen, Zehua Li, Keqin Bao, Junyang Lin, Dayiheng Liu

机构 * Qwen Team, Alibaba（阿里巴巴通义实验室） ； Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； University of Science and Technology of China（中国科学技术大学） 纠错

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

Switchable Token-Specific Codebook Quantization For Face Image Compression

Yongbo Wang, Haonan Wang, Guodong Mu, Ruixin Zhang, Jiaqi Chen, Jingyun Zhang, Jun Wang, Yuan Xie, Zhizhong Zhang, Shouhong Ding

机构 * East China Normal University（东华师范大学） ； Tencent Youtu Lab（腾讯优图实验室） ； Tencent WeChat Pay Lab（腾讯微信支付实验室） 纠错

Comments NeurIPS 2025 accepted

Look and Tell: A Dataset for Multimodal Grounding Across Egocentric and Exocentric Views

Anna Deichler, Jonas Beskow

机构 * KTH Royal Institute of Technology（皇家理工学院） 纠错

Comments 10 pages, 6 figures, 2 tables. Accepted to the NeurIPS 2025 Workshop on SPACE in Vision, Language, and Embodied AI (SpaVLE). Dataset: https://huggingface.co/datasets/annadeichler/KTH-ARIA-referential

InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention

Qiang Xiang, Shuang Sun, Binglei Li, Dejia Song, Huaxia Li, Nemo Chen, Xu Tang, Yao Hu, Junping Zhang

Comments Accepted in NeurIPS 2025

PULSE: Practical Evaluation Scenarios for Large Multimodal Model Unlearning

Tatsuki Kawakami, Kazuki Egashira, Atsuyuki Miyai, Go Irie, Kiyoharu Aizawa

机构 * The University of Tokyo（东京大学） ； Tokyo University of Science（东京科学大学） 纠错

Comments Accepted at NeurIPS 2025 Workshop: Evaluating the Evolving LLM Lifecycle

From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes

Tianxu Wang, Zhuofan Zhang, Ziyu Zhu, Yue Fan, Jing Xiong, Pengxiang Li, Xiaojian Ma, Qing Li

机构 * State Key Laboratory of General Artificial Intelligence, BIGAI（通用人工智能国家重点实验室，BIGAI） ； Tsinghua University（清华大学） ； Peking University（北京大学） ； Beijing Institute of Technology（北京理工大学） 纠错

Comments Update v3 of the NeurIPS 2025 Datasets and Benchmarks paper (v2), including additional evaluations of state-of-the-art multimodal large language models. Project page: https://anywhere-3d.github.io/

RDB2G-Bench: A Comprehensive Benchmark for Automatic Graph Modeling of Relational Databases

Dongwon Choi, Sunwoo Kim, Juyeon Kim, Kyungho Kim, Geon Lee, Shinhwan Kang, Myunghwan Kim, Kijung Shin

机构 * Graduate School of AI, KAIST（人工智能研究生院，韩国科学技术院） 纠错

Comments Accepted at NeurIPS 2025 Datasets and Benchmarks Track

Two-Stage Learning of Stabilizing Neural Controllers via Zubov Sampling and Iterative Domain Expansion

Haoyu Li, Xiangru Zhong, Bin Hu, Huan Zhang

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

Comments NeurIPS 2025

Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation

Edward Fish, Richard Bowden

机构 * CVSSP, University of Surrey（CVSSP，萨里大学） 纠错

Comments Accepted to NeurIPS 2025

Practical Bayes-Optimal Membership Inference Attacks

Marcus Lassila, Johan Östman, Khac-Hoang Ngo, Alexandre Graell i Amat

Comments In NeurIPS 2025, 10 pages plus 15 pages of appendices

Preference Learning with Response Time: Robust Losses and Guarantees

Ayush Sawarni, Sahasrajit Sarmasarkar, Vasilis Syrgkanis

Comments Accepted at NeurIPS 2025

FALCON: An ML Framework for Fully Automated Layout-Constrained Analog Circuit Design

Asal Mehradfar, Xuzhe Zhao, Yilun Huang, Emir Ceyani, Yankai Yang, Shihao Han, Hamidreza Aghasi, Salman Avestimehr

机构 * University of Southern California（南加州大学） ； University of California, Irvine（加州大学伊藤分校） 纠错

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

MoPFormer: Motion-Primitive Transformer for Wearable-Sensor Activity Recognition

Hao Zhang, Zhan Zhuang, Xuehao Wang, Xiaodong Yang, Yu Zhang

机构 * Southern University of Science and Technology（南方科技大学） ； City University of Hong Kong（香港城市大学） ； Zhejiang University（浙江大学） ； Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所） 纠错

Comments Accepted by NeurIPS 2025

Structured Reinforcement Learning for Combinatorial Decision-Making

Heiko Hoppe, Léo Baty, Louis Bouvier, Axel Parmentier, Maximilian Schiffer

机构 * Technical University of Munich（慕尼黑技术大学） ； École des Ponts（巴黎理工大学） 纠错

Comments 29 pages, 8 figures, accepted at the 39th Annual Conference on Neural Information Processing Systems (NeurIPS 2025)