arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

期刊&会议

NeurIPS

Conference on Neural Information Processing Systems · 会议 · Machine Learning

2026-02-12 至 2026-02-12 共收录 7
2505.16415 2026-02-12 cs.CL cs.AI cs.LG

Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation

基于Jensen-Shannon散度的响应归因研究:一种驱动上下文归因的机理研究

Ruizhe Li, Chen Chen, Yuchen Hu, Yanjun Gao, Xi Wang, Emine Yilmaz

机构 * University of Aberdeen(阿伯丁大学) Nanyang Technological University(南洋理工大学) University College London(伦敦大学学院) University of Colorado Anschutz Medical Campus(科罗拉多大学安舒兹医学校区) University of Sheffield(谢菲尔德大学)

AI总结 本文提出基于Jensen-Shannon散度的ARC-JSD方法,实现高效准确的上下文归因,提升RAG模型的性能和效率。

Comments Accepted at ICLR 2026; Best Paper Award at COLM 2025 XLLM-Reason-Plan Workshop; Accepted at NeurIPS 2025 Mechanistic Interpretability Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.10253 2026-02-12 cs.DS cs.AI

The Complexity of Bayesian Network Learning: Revisiting the Superstructure

贝叶斯网络学习的复杂性:重新审视超结构

Robert Ganian, Viktoriia Korchemna

机构 * Algorithms and Complexity Group, TU Wien(算法与复杂性组,维也纳技术大学)

AI总结 本文研究了贝叶斯网络学习的复杂性,证明通过反馈边集大小参数化可实现固定参数可处理性,并展示了其在不同输入表示下的应用及扩展至聚树学习的可能。

Comments A preliminary version of this article appeared in the proceedings of NeurIPS 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.10129 2026-02-12 cs.SI math.OC

Causal-Informed Hybrid Online Adaptive Optimization for Ad Load Personalization in Large-Scale Social Networks

因果信息引导的混合在线自适应优化用于大规模社交网络广告负载个性化

Aakash Mishra, Qi Xu, Zhigang Hua, Keyu Nie, Vishwanath Sangale, Vishal Vaingankar, Jizhe Zhang, Ren Mao

AI总结 本文提出CTR CBO框架,结合对偶方法与贝叶斯优化,利用因果机器学习模型提升广告负载个性化效果。

Comments 5 pages, 3 figures, NeurIPS COML Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.23599 2026-02-12 cs.LG math.RT math.ST stat.ML stat.TH

On Transferring Transferability: Towards a Theory for Size Generalization

关于转移的转移:迈向大小泛化理论

Eitan Levin, Yuxin Ma, Mateo Díaz, Soledad Villar

机构 * Department of Computing and Mathematical Sciences, Caltech(加州理工学院计算与数学科学系) Department of Applied Mathematics and Statistics and the Mathematical Institute for Data Science, Johns Hopkins University(约翰霍普金斯大学应用数学与统计学系及数据科学数学研究所)

AI总结 本文提出了一种通用框架,用于研究不同维度间的转移性,并通过理论分析和实验验证了大小泛化的能力。

Comments 75 pages, 10 figures, closest to version to be published in NeurIPS

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.13804 2026-02-12 cs.CR cs.SE

QUT-DV25: A Dataset for Dynamic Analysis of Next-Gen Software Supply Chain Attacks

QUT-DV25:一个用于下一代软件供应链攻击动态分析的数据集

Sk Tanzir Mehedi, Raja Jurdak, Chadni Islam, Gowri Ramachandran

AI总结 QUT-DV25数据集通过动态分析方法,识别出此前被标记为无害的恶意PyPI包,为下一代软件供应链攻击检测提供了新的研究基础。

Comments 9 pages, 2 figures, 6 tables. https://neurips.cc/virtual/2025/loc/san-diego/poster/121753

Journal ref Advances in Neural Information Processing Systems 39 (NeurIPS 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.13444 2026-02-12 cs.CL cs.CV

ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models

ChartMuseum: 测试大型视觉-语言模型的视觉推理能力

Liyan Tang, Grace Kim, Xinyu Zhao, Thom Lake, Wenxuan Ding, Fangcong Yin, Prasann Singhal, Manya Wadhwa, Zeyu Leo Liu, Zayne Sprague, Ramya Namuduri, Bodun Hu, Juan Diego Rodriguez, Puyuan Peng, Greg Durrett

机构 * The University of Texas at Austin(德克萨斯大学奥斯汀分校)

AI总结 ChartMuseum通过评估复杂视觉和文本推理能力,揭示了大型视觉-语言模型在视觉推理上的不足。

Comments NeurIPS 2025 Datasets & Benchmarks

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.05082 2026-02-12 cs.LG cs.IT math.IT math.PR

ItDPDM: Information-Theoretic Discrete Poisson Diffusion Model

ItDPDM:信息论视角下的离散泊松扩散模型

Sagnik Bhattacharya, Abhiram Gorle, Ahsan Bilal, Connor Ding, Amit Kumar Singh Yadav, Tsachy Weissman

机构 * Department of Electrical Engineering, Stanford University(斯坦福大学电气工程系) Department of Computer Science, Oklahoma University(俄克拉荷马大学计算机科学系) School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA(普渡大学电气与计算机工程学院)

AI总结 本文提出ItDPDM模型,结合信息论视角和离散泊松重建损失,实现对离散数据的精确似然估计与生成建模。

Comments Published in NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏