Logit-Entropy Adaptive Stopping Heuristic for Efficient Chain-of-Thought Reasoning
机构 * Purdue University（普渡大学）
Comments Presented at the 1st Workshop on Efficient Reasoning (NeurIPS 2025)
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
Dynamic causal discovery in Alzheimer's disease through latent pseudotime modelling
机构 * King’s College London（伦敦国王学院）
Comments Accepted to the NeurIPS 2025 Workshop on CauScien: Uncovering Causality in Science
Estimating Hitting Times Locally At Scale
Comments Accepted for presentation at NeurIPS 2025
Differentially Private In-Context Learning with Nearest Neighbor Search
机构 * Nokia Bell Labs（诺基亚贝尔实验室）
Comments NeurIPS Lock-LLM Workshop 2025
Homogeneous Keys, Heterogeneous Values: Exploiting Local KV Cache Asymmetry for Long-Context LLMs
机构 * MoE Key Laboratory of Interdisciplinary Research of Computation and Economics（交叉计算与经济学 interdisciplinary 研究联合实验室） ； Shanghai University of Finance and Economics（上海财经大学）
Comments 14 pages,7 figures;Accepted by NeurIPS 2025
MIND: Material Interface Generation from UDFs for Non-Manifold Surface Reconstruction
机构 * Key Laboratory of System Software and State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所系统软件重点实验室、计算机科学国家重点实验室） ； University of Chinese Academy of Sciences（中国科学院大学） ； Department of Computer Science, Stony Brook University（石溪大学计算机科学系） ； College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）
Comments NIPS 2025
How do Transformers Learn Implicit Reasoning?
机构 * DCST, BNRist（中国清华大学人工智能研究院） ； KIRC, Institute for Artificial Intelligence, Tsinghua University, China
Comments Accepted as Spotlight at NeurIPS 2025
CREA: A Collaborative Multi-Agent Framework for Creative Image Editing and Generation
机构 * Virginia Tech（弗吉尼亚理工学院）
Comments Published at NeurIPS'25 Main Conference
GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs
机构 * Birla Institute of Technology and Science（比拉理工学院） ； CISPA Helmholtz Center for Information Security（信息安全赫尔姆霍茨中心）
Comments Accepted to NeurIPS 2025. Project page and demos: https://air-ml.org/project/gasp/
Understanding Adam Requires Better Rotation Dependent Assumptions
机构 * Mila, Quebec AI Institute（魁北克人工智能研究所） ； Université de Montréal（蒙特利尔大学） ； University of British Columbia（不列颠哥伦比亚大学） ； Samsung SAIL Montreal（三星SAIL蒙特利尔分校） ； Canada CIFAR AI Chair（加拿大CIFAR人工智能主席） ； Archimedes Unit, Athena Research Center（阿提卡研究中心阿基米德单位）
Comments Published at NeurIPS 2025
Text to Sketch Generation with Multi-Styles
机构 * School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院） ； Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东省人工智能与数字经济实验室（深圳））
Comments Accepted by NeurIPS 2025
Tortoise and Hare Guidance: Accelerating Diffusion Model Inference with Multirate Integration
Comments 21 pages, 8 figures. NeurIPS 2025. Project page: https://yhlee-add.github.io/THG
DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization
机构 * Nanjing University of Science and Technology（南京理工大学） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； Huawei Technologies Co., Ltd.（华为技术有限公司）
Comments NeurIPS 2025, 10 pages, 12 figures
Towards Scalable Meta-Learning of near-optimal Interpretable Models via Synthetic Model Generations
机构 * Capital One
Comments 9 pages, 3 figures, Neurips 2025 GenAI in Finance Workshop
Context informs pragmatic interpretation in vision-language models
机构 * Department of Psychology Stanford University（心理学系 斯坦福大学）
Comments Accepted at CogInterp Workshop, NeurIPS 2025
To See or To Read: User Behavior Reasoning in Multimodal LLMs
机构 * Personalization Team, Walmart Global Tech（Walmart全球科技个性化团队）
Comments Accepted by the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Workshop: Efficient Reasoning
ASAP: an Agentic Solution to Auto-optimize Performance of Large-Scale LLM Training
Comments This work has been accepted to Workshop on ML for Systems at NeurIPS 2025
Sketch-Augmented Features Improve Learning Long-Range Dependencies in Graph Neural Networks
机构 * Department of Computer Science, University of Chicago（芝加哥大学计算机科学系） ； Leadership Computing Facility, Argonne National Laboratory（阿贡国家实验室领导计算设施） ； Department of Statistics, University of Chicago（芝加哥大学统计系） ； NSF-Simons National Institute for Theory and Mathematics in Biology（国家理论与生物数学研究所）
Comments To appear at NeurIPS 2025
Optimizing Reasoning Efficiency through Prompt Difficulty Prediction
机构 * UC San Diego（加州大学圣地亚哥分校） ； Capital One（Capital One公司）
Comments NeurIPS 2025 Workshop on Efficient Reasoning
Learning Paths for Dynamic Measure Transport: A Control Perspective
机构 * Massachusetts Institute of Technology（麻省理工学院） ； University of Washington（华盛顿大学）
Comments To appear at NeurIPS 2025 Workshop on Frontiers of Probabilistic Inference: Sampling Meets Learning
What's in Common? Multimodal Models Hallucinate When Reasoning Across Scenes
机构 * FAIR at Meta（Meta 的 FAIR）
Comments 10 pages, 6 figures. Accepted to NeurIPS Datasets & Benchmarks 2025
Node-Based Editing for Multimodal Generation of Text, Audio, Image, and Video
机构 * Massachusetts Institute of Technology（麻省理工学院） ； Microsoft Research（微软研究院）
Comments Accepted to NeurIPS 2025, Conference on Neural Information Processing Systems, Workshop on Generative and Protective AI for Content Creation
A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning
机构 * HKUST (GZ)（香港科技大学（广州）） ； INFORMED-AI Hub（INFORMED-AI中心） ； University of Bristol（布里斯托大学） ； ELLIS Institute Finland（芬兰ELLIS研究所） ； Centre for Artificial Intelligence（人工智能中心） ； University College London（伦敦大学学院） ； School of Engineering Mathematics and Technology（工程数学与技术学院）
Comments Published in NeurIPS 2025
HiMaCon: Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data
机构 * HKU Musketeers Foundation Institute of Data Science（香港大学数据科学学院） ； The University of Hong Kong（香港大学） ； DAMO Academy（达摩院） ； Alibaba Group（阿里巴巴集团）
Comments Accepted at 39th Conference on Neural Information Processing Systems (NeurIPS 2025)
FlexAC: Towards Flexible Control of Associative Reasoning in Multimodal Large Language Models
机构 * University of Electronic Science and Technology of China（电子科学与技术大学） ； Southwestern University of Finance and Economics（西南财经大学） ； Tongji University（同济大学）
Comments 19 pages, 11 figures. Accepted by the 39th Conference on Neural Information Processing Systems (NeurIPS 2025)
Deep Graph Learning for Industrial Carbon Emission Analysis and Policy Impact
机构 * Stanford University（斯坦福大学）
Comments NeurIPS 2025 AI for Science Workshop
AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning
机构 * University of California, Los Angeles（加州大学洛杉矶分校）
Comments NeurIPS 2025; Website link:https://autovla.github.io/
Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models
机构 * Department of Computer Science, National University of Singapore（计算机科学系，新加坡国立大学）
Comments accepted by NeurIPS 2025
Critical Batch Size Revisited: A Simple Empirical Approach to Large-Batch Language Model Training
机构 * Allen Institute for AI（人工智能研究所）
Comments Neurips 2025
Mustafar: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference
机构 * Department of Computer Science, University of Maryland（计算机科学系，马里兰大学） ； d-Matrix
Comments 20 pages, 9 figures, NeurIPS 2025
