NeurIPS

Stable Cinemetrics : Structured Taxonomy and Evaluation for Professional Video Generation

Agneet Chatterjee, Rahim Entezari, Maksym Zhuravinskyi, Maksim Lapin, Reshinth Adithyan, Amit Raj, Chitta Baral, Yezhou Yang, Varun Jampani

机构 * Stability AI ； Arizona State University（亚利桑那州立大学） ； Google DeepMind（谷歌DeepMind） 纠错

Comments NeurIPS 2025. Project Page : https://stable-cinemetrics.github.io/

Deep Taxonomic Networks for Unsupervised Hierarchical Prototype Discovery

Zekun Wang, Ethan Haarer, Tianyi Zhu, Zhiyi Dai, Christopher J. MacLellan

机构 * Georgia Institute of Technology（佐治亚理工学院） ； University of Virginia（弗吉尼亚大学） 纠错

Comments NeurIPS 2025

Journal ref NeurIPS 2025

MaskSQL: Safeguarding Privacy for LLM-Based Text-to-SQL via Abstraction

Sepideh Abedini, Shubhankar Mohapatra, D. B. Emerson, Masoumeh Shafieinejad, Jesse C. Cresswell, Xi He

机构 * University of Waterloo（多伦多大学） ； Vector Institute（向量研究所） ； Layer 6 AI 纠错

Comments Accepted to the 3rd Workshop on Regulatable ML at NeurIPS 2025

Scalable Fingerprinting of Large Language Models

Anshul Nasery, Jonathan Hayase, Creston Brooks, Peiyao Sheng, Himanshu Tyagi, Pramod Viswanath, Sewoong Oh

机构 * University of Washington（华盛顿大学） ； Sentient 纠错

Comments Spotlight at NeurIPS 2025

Unlocking Transfer Learning for Open-World Few-Shot Recognition

Byeonggeun Kim, Juntae Lee, Kyuhong Shim, Simyung Chang

Comments Accepted at NeurIPS 2025 workshop

Sandbagging in a Simple Survival Bandit Problem

Joel Dyer, Daniel Jarne Ornia, Nicholas Bishop, Anisoara Calinescu, Michael Wooldridge

机构 * University of Oxford（牛津大学） 纠错

Comments Forthcoming in the "Reliable ML from Unreliable Data Workshop" at NeurIPS 2025

Ordinal Label-Distribution Learning with Constrained Asymmetric Priors for Imbalanced Retinal Grading

Nagur Shareef Shaik, Teja Krishna Cherukuri, Adnan Masood, Ehsan Adeli, Dong Hye Ye

Comments Accepted at 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: The Second Workshop on GenAI for Health: Potential, Trust, and Policy Compliance

Vocabulary Customization for Efficient Domain-Specific LLM Deployment

Christian Herold, Michael Kozielski, Nicholas Santavas, Yannick Versley, Shahram Khadivi

机构 * eBay Inc（eBay公司） 纠错

Comments Accepted at NEURIPS 2025 CCFM Workshop

Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation

Guoqing Hu, An Zhang. Shuchang Liu, Wenyu Mao, Jiancan Wu, Xun Yang, Xiang Li, Lantao Hu, Han Li, Kun Gai, Xiang Wang

Journal ref NeurIPS 2025

GeoLink: Empowering Remote Sensing Foundation Model with OpenStreetMap Data

Lubian Bai, Xiuyuan Zhang, Siqi Zhang, Zepeng Zhang, Haoyu Wang, Wei Qin, Shihong Du

机构 * School of Earth and Space Sciences, Peking University（地球与空间科学学院，北京大学） ； College of Urban and Environmental Sciences, Peking University（城市与环境科学学院，北京大学） ； State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation, CAS（多模态人工智能系统国家重点实验室，中国科学院自动化研究所） ； Intelligent Maintenance and Operations Systems Lab（智能维护与运营系统实验室） 纠错

Comments NeurIPS 2025

The Impact of Scaling Training Data on Adversarial Robustness

Marco Zimmerli, Andreas Plesner, Till Aczel, Roger Wattenhofer

机构 * ETH-Zurich（苏黎世联邦理工学院） 纠错

Comments Accepted at the workshop Reliable ML from Unreliable Data at NeurIPS 2025

RL-Guided Data Selection for Language Model Finetuning

Animesh Jha, Harshit Gupta, Ananjan Nandi

机构 * Stanford University（斯坦福大学） 纠错

Comments To appear in NeurIPS 2025 Constrained Optimization for ML Workshop

MIDAS: Misalignment-based Data Augmentation Strategy for Imbalanced Multimodal Learning

Seong-Hyeon Hwang, Soyoung Choi, Steven Euijong Whang

机构 * KAIST（韩国科学技术院） 纠错

Comments Accepted to NeurIPS 2025

Boundary-to-Region Supervision for Offline Safe Reinforcement Learning

Huikang Su, Dengyun Peng, Zifeng Zhuang, YuHan Liu, Qiguang Chen, Donglin Wang, Qinghe Liu

机构 * Harbin Institute of Technology, Weihai（哈尔滨工业大学（威海）） ； Harbin Institute of Technology, Harbin（哈尔滨工业大学） ； Westlake University, Hangzhou（西湖大学） 纠错

Comments NeurIPS 2025

Generalized Contrastive Learning for Universal Multimodal Retrieval

Jungsoo Lee, Janghoon Cho, Hyojin Park, Munawar Hayat, Kyuwoong Hwang, Fatih Porikli, Sungha Choi

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

Comments Accepted to NeurIPS 2025

Echoes of Humanity: Exploring the Perceived Humanness of AI Music

Flavio Figueiredo, Giovanni Martinelli, Henrique Sousa, Pedro Rodrigues, Frederico Pedrosa, Lucas N. Ferreira

机构 * Universidade Federal de Minas Gerais (UFMG)（巴西联邦大学矿务格里斯大学） 纠错

Comments Accepted at NeuRIPs 2025 Creative AI Track

Ethics Statements in AI Music Papers: The Effective and the Ineffective

Julia Barnett, Patrick O'Reilly, Jason Brent Smith, Annie Chu, Bryan Pardo

机构 * Northwestern University（西北大学） 纠错

Comments Accepted to the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: AI for Music

Joint Embeddings Go Temporal

Sofiane Ennadir, Siavash Golkar, Leopoldo Sarra

机构 * KTH Stockholm（瑞典斯德哥尔摩皇家理工学院） ； New York University（纽约大学） ； Flatiron Institute（Flatiron研究所） 纠错

Comments Accepted at the Workshop on Time Series in the Age of Large Models - NeurIPS 2024

Safe and Stable Control via Lyapunov-Guided Diffusion Models

Xiaoyuan Cheng, Xiaohang Tang, Yiming Yang

Comments Accepted by NeurIPS 2025

MAESTRO : Adaptive Sparse Attention and Robust Learning for Multimodal Dynamic Time Series

Payal Mohapatra, Yueyuan Sui, Akash Pandey, Stephen Xia, Qi Zhu

机构 * Northwestern University（西北大学） 纠错

Comments Accepted to Neurips 2025 (Spotlight)

MMPB: It's Time for Multi-Modal Personalization

Jaeik Kim, Woojin Kim, Woohyeon Park, Jaeyoung Do

机构 * AIDAS Laboratory（AIDAS实验室） ； IPAI ； ECE（电子工程系） ； Seoul National University（首尔国立大学） 纠错

Comments Accepted in NeurIPS 2025

OrthoLoC: UAV 6-DoF Localization and Calibration Using Orthographic Geodata

Oussema Dhaouadi, Riccardo Marin, Johannes Meier, Jacques Kaiser, Daniel Cremers

机构 * DeepScenario ； TU Munich（慕尼黑工业大学） ； Munich Center of Machine Learning（慕尼黑机器学习中心） 纠错

Comments Accepted at NeurIPS 2025

Scaling RL to Long Videos

Yukang Chen, Wei Huang, Baifeng Shi, Qinghao Hu, Hanrong Ye, Ligeng Zhu, Zhijian Liu, Pavlo Molchanov, Jan Kautz, Xiaojuan Qi, Sifei Liu, Hongxu Yin, Yao Lu, Song Han

机构 * NVIDIA ； MIT（麻省理工学院） ； HKU（香港大学） ； UC Berkeley（加州大学伯克利分校） 纠错

Comments Accepted by NeurIPS 2025. Code at https://github.com/NVlabs/Long-RL and model at https://huggingface.co/Efficient-Large-Model/LongVILA-R1-7B

Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models

Yulei Qin, Gang Li, Zongyi Li, Zihan Xu, Yuchen Shi, Zhekai Lin, Xiao Cui, Ke Li, Xing Sun

机构 * Youtu-Agent Team（YouTu-Agent团队） 纠错

Comments Accepted to NeurIPS 2025; 15 pages of main body, 5 tables, 5 figures, 42 pages of appendix

Personalized Subgraph Federated Learning with Differentiable Auxiliary Projections

Wei Zhuo, Zhaohuan Zhan, Han Yu

机构 * Nanyang Technological University（南洋理工大学） ； Shenzhen MSU-BIT University（深圳MSU-BIT大学） 纠错

Comments Accepted by NeurIPS 2025

KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction

Jang-Hyun Kim, Jinuk Kim, Sangwoo Kwon, Jae W. Lee, Sangdoo Yun, Hyun Oh Song

Comments NeurIPS 2025 Oral. Code: https://github.com/snu-mllab/KVzip

Value-Guided Search for Efficient Chain-of-Thought Reasoning

Kaiwen Wang, Jin Peng Zhou, Jonathan Chang, Zhaolin Gao, Nathan Kallus, Kianté Brantley, Wen Sun

Comments NeurIPS 2025

AudSemThinker: Enhancing Audio-Language Models through Reasoning over Semantics of Sound

Gijs Wijngaard, Elia Formisano, Michele Esposito, Michel Dumontier

机构 * Maastricht University（马斯特里赫特大学） 纠错

Comments Accepted at NeurIPS 2025

TensorRL-QAS: Reinforcement learning with tensor networks for improved quantum architecture search

Akash Kundu, Stefano Mangini

机构 * QTF Centre of Excellence（量子技术前沿卓越中心） ； Department of Physics（物理系） ； University of Helsinki（赫尔辛基大学） 纠错

Comments Accepted at NeurIPS 2025. Code is at: https://github.com/Aqasch/TensorRL-QAS

Linear Attention for Efficient Bidirectional Sequence Modeling

Arshia Afzal, Elias Abad Rocamora, Leyla Naz Candogan, Pol Puigdemont, Francesco Tonin, Yongtao Wu, Mahsa Shoaran, Volkan Cevher

Comments Accepted in NeurIPS 2025