arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

NeurIPS

Conference on Neural Information Processing Systems · 会议 · Machine Learning

2026-01-26 至 2026-01-26 共收录 8
2601.16447 2026-01-26 cs.CL

Mixing Expert Knowledge: Bring Human Thoughts Back To the Game of Go

融合专家知识:将人类思维带回围棋游戏

Yichuan Ma, Linyang Li, Yongkang Chen, Peiji Li, Jiasheng Ye, Qipeng Guo, Dahua Lin, Kai Chen

机构 * Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) Fudan University(复旦大学) The Chinese University of Hong Kong(香港中文大学)

AI总结 LoGos通过融合围棋专家知识与通用推理能力,实现了在围棋领域的专业水平表现,展示了自然语言推理和战略决策能力。

Comments Accepted to NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.02979 2026-01-26 cs.HC cs.AI

Systematizing LLM Persona Design: A Four-Quadrant Technical Taxonomy for AI Companion Applications

对LLM人设设计的系统化:面向AI陪伴应用的四象限技术分类

Esther Sun, Zichu Wu

机构 * Carnegie Mellon University(卡内基梅隆大学)

AI总结 本文提出四象限技术分类系统,系统化LLM人设设计,涵盖虚拟与具身、情感与功能增强,分析不同应用场景的技术挑战与核心问题。

Comments Accepted to Neurips 2025 workshop: LLM Persona Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.21935 2026-01-26 cs.LG cs.AI stat.ML

AutoSciDACT: Automated Scientific Discovery through Contrastive Embedding and Hypothesis Testing

AutoSciDACT:通过对比嵌入和假设检验实现自动化科学发现

Samuel Bright-Thonney, Christina Reissel, Gaia Grosso, Nathaniel Woodward, Katya Govorkova, Andrzej Novak, Sang Eon Park, Eric Moreno, Philip Harris

机构 * Department of Physics, Massachusetts Institute of Technology(麻省理工学院物理系) The NSF AI Institute for Artificial Intelligence and Fundamental Interactions(国家科学基金会人工智能与基本相互作用研究所) Department of Physics, University of Wisconsin, Madison(威斯康星大学麦迪逊分校物理系)

AI总结 AutoSciDACT通过对比嵌入和假设检验,实现科学数据中新颖性的自动化检测与统计量化。

Comments Accepted at NeurIPS 2025; 33 pages, 16 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.21310 2026-01-26 cs.CL cs.AI cs.LG

Efficient semantic uncertainty quantification in language models via diversity-steered sampling

通过多样性引导采样实现语言模型中的高效语义不确定性量化

Ji Won Park, Kyunghyun Cho

机构 * Prescient Design, Genentech(普森设计,基因泰克) Center for Data Science, New York University(数据科学中心,纽约大学)

AI总结 本文提出一种多样性引导采样方法,通过注入语义相似性惩罚提升语言模型在问答任务中的不确定性估计效率,实现样本效率提升并覆盖更多语义簇。

Comments 10 pages (+7 appendix), 7 figures. Accepted at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.13911 2026-01-26 cs.LG cs.AI cs.LO

Logical Expressiveness of Graph Neural Networks with Hierarchical Node Individualization

具有层次节点个体化的图神经网络的逻辑表达性

Arie Soeteman, Balder ten Cate

AI总结 本文提出了一种具有层次节点个体化的图神经网络,通过理论分析和实验验证,展示了其在区分同构图方面的表达能力及实用性。

Comments Submitted to NeurIPS 2025, 28 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.11777 2026-01-26 cs.CV cs.AI cs.CY cs.LG

Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation

通过在线聚类蒸馏实现心电图视频的自监督学习

Divyanshu Mishra, Mohammadreza Salehi, Pramit Saha, Olga Patey, Aris T. Papageorghiou, Yuki M. Asano, J. Alison Noble

机构 * Department of Engineering Science, University of Oxford(工程科学系,牛津大学) Nuffield Department of Women’s and Reproductive Health, University of Oxford(妇女与生殖健康系,牛津大学) Fundamental AI Lab, University of Technology Nuremberg(基础人工智能实验室,纽伦堡技术大学) University of Amsterdam(阿姆斯特丹大学)

AI总结 DISCOVR通过在线聚类蒸馏实现心脏超声视频的自监督学习,结合时序动态和细粒度空间语义,提升临床任务性能。

Comments Accepted in NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.10805 2026-01-26 cs.LG

Detecting High-Stakes Interactions with Activation Probes

通过激活探针检测高风险交互

Alex McKenzie, Urja Pawar, Phil Blandfort, William Bankes, David Krueger, Ekdeep Singh Lubana, Dmitrii Krasheninnikov

机构 * LASR Labs(LASR实验室) University College London(伦敦大学学院) MILA Harvard University(哈佛大学) NTT Research(NTT研究所) Goodfire University of Cambridge(剑桥大学)

AI总结 通过激活探针检测高风险交互,实现高效且资源敏感的监控系统

Comments Accepted at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.19350 2026-01-26 physics.chem-ph cs.LG

FlashMD: long-stride, universal prediction of molecular dynamics

FlashMD: 长步长、通用的分子动力学预测

Filippo Bigi, Sanggyu Chong, Agustinus Kristiadi, Michele Ceriotti

机构 * Institute of Materials(材料研究所) Ecole Polytechnique Fédérale de Lausanne(洛桑联邦理工学院) Department of Computer Science(计算机科学系) Vector Institute(向量研究所)

AI总结 FlashMD通过长步长预测分子动力学,实现高效模拟长时尺度的微观过程。

Comments NeurIPS 2025 (Spotlight)

详情

展开后加载摘要…

URL PDF HTML 收藏