arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Columbia University(哥伦比亚大学)

共收录 1073
2511.21758 2025-12-01 cs.CR cs.AI cs.CY

A Longitudinal Measurement of Privacy Policy Evolution for Large Language Models

大型语言模型隐私政策演变的纵向测量

Zhen Tao, Shidong Pan, Zhenchang Xing, Emily Black, Talia Gillis, Chunyang Chen

机构 * Technical University of Munich(慕尼黑技术大学) Columbia University(哥伦比亚大学) New York University(纽约大学) CSIRO’s Data61(CSIRO的数据61)

AI总结 本文首次对全球主流LLM提供者的隐私政策进行了纵向研究,揭示了隐私政策的演变趋势、内容特征及地区差异。

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.19657 2025-12-01 cs.LG

LLMEasyQuant: Scalable Quantization for Parallel and Distributed LLM Inference

LLMEasyQuant: 用于并行和分布式LLM推理的可扩展量化

Dong Liu, Yanxuan Yu

机构 * Yale University(耶鲁大学) Columbia University(哥伦比亚大学)

AI总结 LLMEasyQuant通过模块化和系统感知的量化框架,实现高效低比特LLM推理,支持多种量化方法并优化多GPU和分布式环境下的性能。

Comments Accepted as International Conference of Computational Optimization 2025 Oral

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.21008 2025-11-27 cs.LG stat.ML

Estimating Ising Models in Total Variation Distance

在总变分距离下估计Ising模型

Constantinos Daskalakis, Vardis Kandiros, Rui Yao

机构 * EECS Department MIT(MIT电子工程与计算机科学系) Data Science Institute Columbia University(哥伦比亚大学数据科学研究所)

AI总结 本文提出了一种统一分析框架,针对两种通用的Ising模型类,展示了最大伪似然估计量在总变分距离下的多项式时间算法及最优样本复杂性保证。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.18583 2025-11-26 stat.ML cs.LG math.ST stat.TH

Differential privacy with dependent data

具有依赖数据的差分隐私

Valentin Roth, Marco Avella-Medina

机构 * Institute of Science and Technology Austria(奥地利科学与技术研究院) Department of Statistics, Columbia University(哥伦比亚大学统计系)

AI总结 本文研究了依赖数据下的差分隐私,提出在弱依赖性条件下使用winsorized均值估计器,并扩展到随机效应模型等场景。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.23738 2025-11-26 cs.CV cs.GR

How Animals Dance (When You're Not Looking)

动物跳舞(当你不在看的时候)

Xiaojuan Wang, Aleksander Holynski, Brian Curless, Ira Kemelmacher, Steve Seitz

机构 * University of Washington(华盛顿大学) Columbia University(哥伦比亚大学)

AI总结 该研究提出了一种生成音乐同步且具有舞蹈意识的动物跳舞视频的框架,通过引入舞蹈模式和图优化问题实现高效舞蹈合成。

Comments Project page: https://how-animals-dance.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.21740 2025-11-26 cs.CL cs.AI

Counterfactual Simulatability of LLM Explanations for Generation Tasks

大语言模型生成任务中解释的反事实可模拟性

Marvin Limpijankit, Yanda Chen, Melanie Subbiah, Nicholas Deas, Kathleen McKeown

机构 * Department of Computer Science, Columbia University(计算机科学系,哥伦比亚大学)

AI总结 本文提出了一种评估大语言模型生成任务中解释反事实可模拟性的通用框架,发现其在新闻摘要任务中表现良好,但在医疗建议任务中仍有改进空间。

Comments INLG25

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.19815 2025-11-25 cs.RO

ReactEMG: Stable, Low-Latency Intent Detection from sEMG via Masked Modeling

ReactEMG: 通过掩码建模实现从sEMG信号稳定、低延迟的意图检测

Runsheng Wang, Xinyue Zhu, Ava Chen, Jingxi Xu, Lauren Winterbottom, Dawn M. Nilsen, Joel Stein, Matei Ciocarlie

机构 * Department of Mechanical Engineering, Columbia University in the City of New York(机械工程系,哥伦比亚大学纽约市分校) Department of Computer Science, Columbia University in the City of New York(计算机科学系,哥伦比亚大学纽约市分校) Department of Rehabilitation and Regenerative Medicine, Columbia University Irving Medical Center(康复与再生医学系,哥伦比亚大学伊万杰琳医学中心)

AI总结 ReactEMG通过掩码建模实现从sEMG信号稳定、低延迟的意图检测,适用于可穿戴机器人和假肢系统。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.17883 2025-11-25 cs.CV cs.RO

ArticFlow: Generative Simulation of Articulated Mechanisms

ArticFlow: 关节机构生成性模拟

Jiong Lin, Jinchen Ruan, Hod Lipson

机构 * Creative Machines Lab, Columbia University(创意机器实验室,哥伦比亚大学)

AI总结 ArticFlow通过两阶段流匹配框架实现关节机构的生成与模拟,以高精度运动学和形状质量生成多样化关节结构。

Comments 8 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.09567 2025-11-25 cs.LG

Let the Experts Speak: Improving Survival Prediction & Calibration via Mixture-of-Experts Heads

让专家发言:通过专家混合头改进生存预测与校准

Todd Morrill, Aahlad Puli, Murad Megjhani, Soojin Park, Richard Zemel

机构 * Department of Computer Science Columbia University USA(哥伦比亚大学计算机科学系) Department of Computer Science New York University USA(纽约大学计算机科学系) Department of Neurology Columbia University Medical Center USA(哥伦比亚大学医学中心神经病学系) Department of Computer Science Barnard College USA(巴纳德学院计算机科学系) Department of Biomedical Informatics Columbia University Medical Center USA(哥伦比亚大学医学中心生物医学信息学系) NewYork-Presbyterian Hospital at Columbia University Medical Center USA(哥伦比亚大学医学中心新英格兰-纽约 Presbyterian 医院)

AI总结 本文提出了一种改进生存预测和校准的混合专家架构,通过更具表现力的专家实现更准确的患者分组和预测。

Comments Accepted as a proceedings paper at the 2025 Machine Learning for Health Symposium and as a workshop paper at the Learning from Time Series for Health workshop at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.16933 2025-11-24 cs.LG q-bio.QM

A novel approach to classification of ECG arrhythmia types with latent ODEs

一种利用隐式微分方程进行心电图心律失常分类的新方法

Angelina Yan, Matt L. Sampson, Peter Melchior

机构 * Columbia University(哥伦比亚大学) Princeton University(普林斯顿大学)

AI总结 本文提出利用隐式微分方程和梯度提升树对心电图进行心律失常分类,实现不同采样频率下的鲁棒性,推动小型可穿戴设备的长期心脏健康监测。

Comments Accepted into NeurIPS 2025 Learning from Time Series for Health workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.11289 2025-11-24 cs.AI cs.LG

Meta-World+: An Improved, Standardized, RL Benchmark

Meta-World+: 一种改进、标准化的强化学习基准

Reginald McLean, Evangelos Chatzaroulas, Luc McCutcheon, Frank Röder, Tianhe Yu, Zhanpeng He, K. R. Zentner, Ryan Julian, J K Terry, Isaac Woungang, Nariman Farsad, Pablo Samuel Castro

机构 * Toronto Metropolitan University(多伦多 Metropolitan 大学) Farama Foundation(Farama 基金会) University of Surrey(塞维耶大学) Hamburg University of Technology(汉堡技术大学) Columbia University(哥伦比亚大学) Google DeepMind(谷歌DeepMind) University of Southern California(南加州大学) Universite de Montreal(蒙特利尔大学) Mila

AI总结 Meta-World+通过改进和标准化,提供一个更可复现、技术更高效的强化学习基准,以促进多任务和元强化学习的研究与比较。

Comments Accepted at NeurIPs 2025, Datasets and Benchmarks

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.16072 2025-11-21 cs.CL cs.AI

Early science acceleration experiments with GPT-5

使用GPT-5进行早期科学加速实验

Sébastien Bubeck, Christian Coester, Ronen Eldan, Timothy Gowers, Yin Tat Lee, Alexandru Lupsasca, Mehtaab Sawhney, Robert Scherrer, Mark Sellke, Brian K. Spears, Derya Unutmaz, Kevin Weil, Steven Yin, Nikita Zhivotovskiy

机构 * OpenAI University of Oxford(牛津大学) Collège de France and University of Cambridge(法兰西学院和剑桥大学) Vanderbilt University(范德比大学) Columbia University(哥伦比亚大学) Harvard University(哈佛大学) Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室) The Jackson Laboratory(杰克逊实验室) University of California, Berkeley(加州大学伯克利分校)

AI总结 本文通过GPT-5在多个学科中的应用案例,展示了AI如何加速科学研究,并验证了其在解决数学难题中的潜力。

Comments 89 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.14969 2025-11-20 eess.AS cs.AI cs.LG eess.IV eess.SP

Quality-Controlled Multimodal Emotion Recognition in Conversations with Identity-Based Transfer Learning and MAMBA Fusion

Zanxu Wang, Homayoon Beigi

机构 * Columbia University, New York, USA(哥伦比亚大学) Recognition Technologies, Inc., New York, USA(识别技术公司)

Comments 8 pages, 14 images, 3 tables, Recognition Technologies, Inc. Technical Report RTI-20251118-01

Journal ref Recognition Technologies, Inc. Technical Reports, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.03858 2025-11-19 cs.AI cs.ET cs.MA

MI9: An Integrated Runtime Governance Framework for Agentic AI

Charles L. Wang, Trisha Singhal, Ameya Kelkar, Jason Tuo

机构 * Barclays, Model Risk Management(巴克莱银行,模型风险管理部门) Columbia University(哥伦比亚大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.16194 2025-11-19 cs.AI

Towards Automatic Evaluation and Selection of PHI De-identification Models via Multi-Agent Collaboration

Guanchen Wu, Zuhui Chen, Yuzhang Xie, Carl Yang

机构 * Department of Computer Science, Emory University(埃默里大学计算机科学系) Department of Statistics, Columbia University(哥伦比亚大学统计系)

Comments Agents4Science 2025 (Spotlight)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.12236 2025-11-18 cs.CL cs.AI cs.LG

Consistency Is the Key: Detecting Hallucinations in LLM Generated Text By Checking Inconsistencies About Key Facts

Raavi Gupta, Pranav Hari Panicker, Sumit Bhatia, Ganesh Ramakrishnan

机构 * Columbia University(哥伦比亚大学) IIT Bombay(印度理工学院Bombay) Media and Data Science Research (MDSR) Lab, Adobe(Adobe媒体与数据科学研究实验室)

Comments To appear at International Joint Conference on Natural Language Processing & Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL), 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.06067 2025-11-18 cs.CV cs.AI

Reasoning under Vision: Understanding Visual-Spatial Cognition in Vision-Language Models for CAPTCHA

Python Song, Luke Tenyi Chang, Yun-Yun Tsai, Penghui Li, Junfeng Yang

机构 * Columbia University Department of Computer Science(哥伦比亚大学计算机科学系)

Comments 14pages, 11figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.25230 2025-11-18 cs.LG cs.AI

Energy Guided Geometric Flow Matching

Aaron Zweig, Mingxuan Zhang, Elham Azizi, David Knowles

机构 * Columbia University(哥伦比亚大学) New York Genome Center(纽约基因组中心)

详情

展开后加载摘要…

URL PDF HTML 收藏
2306.06031 2025-11-18 q-fin.ST cs.CL cs.LG q-fin.TR

FinGPT: Open-Source Financial Large Language Models

Hongyang Yang, Xiao-Yang Liu, Christina Dan Wang

机构 * AI4Finance Foundation(AI4Finance基金会) Columbia University(哥伦比亚大学) New York University Shanghai(纽约大学上海)

Comments Accepted by the FinLLM Symposium at IJCAI 2023. Recipient of the Best Presentation Award (Hongyang Yang). Workshop link: https://finllm.github.io/workshop. This is the first official FinGPT paper; please cite this work when referencing FinGPT

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.11170 2025-11-17 cs.LG physics.ao-ph

Power Ensemble Aggregation for Improved Extreme Event AI Prediction

Julien Collard, Pierre Gentine, Tian Zheng

机构 * Ecole Polytechnique(巴黎政治学院) LEAP, Columbia University(哥伦比亚大学LEAP) Department of Statistics, Columbia University(哥伦比亚大学统计系)

Comments Accepted for the NeurIPS 2025 ML4PS workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.03902 2025-11-17 cs.LG stat.ML

Stochastic Variational Inference with Tuneable Stochastic Annealing

John Paisley, Ghazal Fazelnia, Brian Barr

机构 * Columbia University(哥伦比亚大学) Spotify Research(Spotify研究) Capital One Labs(Capital One实验室)

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.03485 2025-11-17 cs.LG

Gaussian Process Tilted Nonparametric Density Estimation using Fisher Divergence Score Matching

John Paisley, Wei Zhang, Brian Barr

机构 * Columbia University(哥伦比亚大学) Capital One Labs(Capital One 实验室)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.10974 2025-11-17 cs.CV

Preserving Cross-Modal Consistency for CLIP-based Class-Incremental Learning

Haoran Chen, Houze Xu, Micah Goldblum, Daoguo Dong, Zuxuan Wu

机构 * Institute of Trustworthy Embodied AI(可信具身人工智能研究院) Fudan University(复旦大学) Shanghai Collaborative Innovation Center of Intelligent Visual Computing(上海智能视觉计算协同创新中心) Columbia University(哥伦比亚大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.02385 2025-11-14 cs.LG quant-ph stat.ML

Multi-agent Markov Entanglement

Shuze Chen, Tianyi Peng

机构 * Graduate School of Business, Columbia University(哥伦比亚大学商学院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.09897 2025-11-14 stat.ML cs.LG

Theory and computation for structured variational inference

Shunan Sheng, Bohan Wu, Bennett Zhu, Sinho Chewi, Aram-Alexandre Pooladian

机构 * Department of Statistics, Columbia University(哥伦比亚大学统计系) Department of Statistics and Data Science, Yale University(耶鲁大学统计与数据科学系) Foundations of Data Science, Yale University(耶鲁大学数据科学基础)

Comments 78 pages, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.15062 2025-11-13 cs.RO cs.AI cs.LG

Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper

Xinyue Zhu, Binghao Huang, Yunzhu Li

机构 * Columbia University(哥伦比亚大学)

Comments More videos can be found on our website:https://binghao-huang.github.io/touch_in_the_wild/

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.08791 2025-11-13 stat.ML cs.LG

The Probably Approximately Correct Learning Model in Computational Learning Theory

Rocco A. Servedio

机构 * Columbia University(哥伦比亚大学)

Comments 45 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.08620 2025-11-13 cs.CL cs.AI cs.LG

Learn More, Forget Less: A Gradient-Aware Data Selection Approach for LLM

Yibai Liu, Shihang Wang, Zeming Liu, Zheming Song, Junzhe Wang, Jingjing Liu, Qingjie Liu, Yunhong Wang

机构 * Fu Foundation School of Engineering and Applied Science, Columbia University(哥伦比亚大学工程与应用科学学院) School of Computer Science and Engineering, Beihang University(北航计算机科学与工程学院)

Comments Under review

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.07677 2025-11-12 cs.SD cs.AI

Speech Separation for Hearing-Impaired Children in the Classroom

Feyisayo Olalere, Kiki van der Heijden, H. Christiaan Stronks, Jeroen Briaire, Johan H. M. Frijns, Yagmur Güçlütürk

机构 * Radboud University(拉德堡德大学) Donders Institute for Brain, Cognition, and Behaviour(大脑、认知与行为研究所) Leiden University Medical Centre(莱顿大学医学中心) Mortimer B. Zuckerman Mind, Brain, Behavior Institute(莫蒂默·B·祖克erman心智、大脑与行为研究所) Columbia University(哥伦比亚大学) Department of Otorhinolaryngology(耳鼻喉科部门) Leiden Institute for Brain and Cognition(莱顿大脑与认知研究所) Delft University of Technology(代尔夫特理工大学)

Comments 13 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.13979 2025-11-12 cs.CL

Mixed Signals: Understanding Model Disagreement in Multimodal Empathy Detection

Maya Srikanth, Run Chen, Julia Hirschberg

机构 * Columbia University(哥伦比亚大学)

Comments To appear in Findings of IJCNLP-AACL 2025

详情

展开后加载摘要…

URL PDF HTML 收藏