arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

University of Southern California(南加州大学)

共收录 1293
2511.07343 2025-11-11 cs.LG cs.AI

TNT: Improving Chunkwise Training for Test-Time Memorization

Zeman Li, Ali Behrouz, Yuan Deng, Peilin Zhong, Praneeth Kacham, Mahdi Karami, Meisam Razaviyayn, Vahab Mirrokni

机构 * University of Southern California(南加州大学) Google Research(谷歌研究)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.06913 2025-11-11 cs.LG cs.AI

Sampling and Loss Weights in Multi-Domain Training

Mahdi Salmani, Pratik Worah, Meisam Razaviyayn, Vahab Mirrokni

机构 * University of Southern California(南加州大学) Google Research(谷歌研究)

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.11002 2025-11-11 cs.LG cs.DC

pMixFed: Efficient Personalized Federated Learning through Adaptive Layer-Wise Mixup

Yasaman Saadati, Mohammad Rostami, M. Hadi Amini

机构 * Florida International University(佛罗里达国际大学) USC Information Sciences Institute(南加州大学信息科学研究所)

Comments 45 pages, 10 Images

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.06134 2025-11-11 cs.AI cs.MA

Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMs

Wei Yang, Jiacheng Pang, Shixuan Li, Paul Bogdan, Stephen Tu, Jesse Thomason

机构 * University of Southern California(南加州大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.05684 2025-11-11 cs.IR cs.CL

A Representation Sharpening Framework for Zero Shot Dense Retrieval

Dhananjay Ashok, Suraj Nair, Mutasem Al-Darabsah, Choon Hui Teo, Tarun Agarwal, Jonathan May

机构 * Information Sciences Institute, University of Southern California(信息科学研究所,南加州大学) Amazon(亚马逊)

Comments 15 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.03464 2025-11-11 cs.GT cs.LG math.OC

From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications

Yang Cai, Haipeng Luo, Chen-Yu Wei, Weiqiang Zheng

机构 * Yale University(耶鲁大学) University of Southern California(南加州大学) University of Virginia(弗吉尼亚大学)

Comments NeurIPS 2025. 24 pages. Updated version with more discussions and robustness in the bandit feedback setting

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.04907 2025-11-10 cs.LG stat.ML

Efficient Swap Multicalibration of Elicitable Properties

Lunjia Hu, Haipeng Luo, Spandan Senapati, Vatsal Sharan

机构 * Northeastern University(东北大学) University of Southern California(南加州大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.05583 2025-11-10 cs.LG cs.AI stat.ML

Conformal Prediction Adaptive to Unknown Subpopulation Shifts

Nien-Shao Wang, Duygu Nur Yaldiz, Yavuz Faruk Bakman, Sai Praneeth Karimireddy

机构 * University of Southern California(南加州大学)

Comments 21 pages, 7 figures, 5 tables, submitted to ICLR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.04646 2025-11-07 cs.AI cs.CL cs.LG cs.MA

DR. WELL: Dynamic Reasoning and Learning with Symbolic World Model for Embodied LLM-Based Multi-Agent Collaboration

Narjes Nourzad, Hanqing Yang, Shiyu Chen, Carlee Joe-Wong

机构 * University of Southern California(南加州大学) Carnegie Mellon University(卡内基梅隆大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.03939 2025-11-07 cs.LG cs.AI cs.CL

RLHF: A comprehensive Survey for Cultural, Multimodal and Low Latency Alignment Methods

Raghav Sharma, Manan Mehta, Sai Tiger Raina

机构 * Northeastern University(东北大学) University of Southern California(南加州大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.03831 2025-11-07 cs.LG math.ST stat.ML stat.TH

Higher-Order Causal Structure Learning with Additive Models

James Enouen, Yujia Zheng, Ignavier Ng, Yan Liu, Kun Zhang

机构 * University of Southern California(南加州大学) Carnegie Mellon University(卡内基梅隆大学) Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.03757 2025-11-07 cs.LG cs.AI

Laugh, Relate, Engage: Stylized Comment Generation for Short Videos

Xuan Ouyang, Senan Wang, Bouzhou Wang, Siyuan Xiahou, Jinrong Zhou, Yuekang Li

机构 * University of New South Wales(新南威尔士大学) University of Sydney(悉尼大学) The University of Hong Kong(香港大学) University of Southern California(南加州大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.01833 2025-11-07 cs.CV

TIR-Bench: A Comprehensive Benchmark for Agentic Thinking-with-Images Reasoning

Ming Li, Jike Zhong, Shitian Zhao, Haoquan Zhang, Shaoheng Lin, Yuxiang Lai, Chen Wei, Konstantinos Psounis, Kaipeng Zhang

机构 * Shanghai AI Laboratory(上海人工智能实验室) University of Southern California(南加州大学) Emory University(埃默里大学) Chinese University of Hong Kong(香港中文大学) Rice University(德克萨斯大学奥斯汀分校)

Comments Preprint

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.03228 2025-11-06 cs.CL cs.IR

Beyond Ranked Lists: The SARAL Framework for Cross-Lingual Document Set Retrieval

Shantanu Agarwal, Joel Barry, Elizabeth Boschee, Scott Miller

机构 * Information Sciences Institute University of Southern California(信息科学研究所 美国南加州大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.01852 2025-11-06 cs.GT cs.LG

Proximal Regret and Proximal Correlated Equilibria: A New Tractable Solution Concept for Online Learning and Games

Yang Cai, Constantinos Daskalakis, Haipeng Luo, Chen-Yu Wei, Weiqiang Zheng

机构 * Yale University(耶鲁大学) MIT CSAIL(麻省理工学院CSAIL) University of Southern California(南加州大学) University of Virginia(弗吉尼亚大学)

Comments This paper presents proximal regret and proximal correlated equilibria results that do not appear in the NeurIPS version of arXiv:2403.08171

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.04220 2025-11-06 cs.CV

Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMs

Fangrui Zhu, Hanhui Wang, Yiming Xie, Jing Gu, Tianye Ding, Jianwei Yang, Huaizu Jiang

机构 * Northeastern University(东北大学) Microsoft Research(微软研究院) University of Southern California(南加州大学) University of California, Santa Cruz(加州大学圣克鲁兹分校)

Comments NeurIPS 2025, code link: https://github.com/neu-vi/struct2d

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.02832 2025-11-05 cs.RO cs.CV cs.LG

TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System

Yanjie Ze, Siheng Zhao, Weizhuo Wang, Angjoo Kanazawa, Rocky Duan, Pieter Abbeel, Guanya Shi, Jiajun Wu, C. Karen Liu

机构 * Amazon FAR(亚马逊 FAR) Stanford University(斯坦福大学) USC(美国大学) UC Berkeley(伯克利大学) CMU(卡内基梅隆大学)

Comments Website: https://yanjieze.com/TWIST2

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.02504 2025-11-05 cs.RO

Dexterous Robotic Piano Playing at Scale

Le Chen, Yi Zhao, Jan Schneider, Quankai Gao, Simon Guist, Cheng Qian, Juho Kannala, Bernhard Schölkopf, Joni Pajarinen, Dieter Büchler

机构 * Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所) Aalto University(阿alto大学) University of Southern California(南加州大学) Imperial College London(伦敦帝国理工学院) University of Oulu(奥卢大学) University of Alberta(阿尔伯塔大学) Alberta Machine Intelligence Institute(阿尔伯塔人工智能研究所)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.00689 2025-11-05 cs.CL

Do Methods to Jailbreak and Defend LLMs Generalize Across Languages?

Berk Atil, Rebecca J. Passonneau, Fred Morstatter

机构 * Penn State University(宾夕法尼亚州立大学) Information Sciences Institute, USC(信息科学研究所)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.18467 2025-11-05 cs.CL cs.AI

LAWCAT: Efficient Distillation from Quadratic to Linear Attention with Convolution across Tokens for Long Context Modeling

Zeyu Liu, Souvik Kundu, Lianghao Jiang, Anni Li, Srikanth Ronanki, Sravan Bodapati, Gourav Datta, Peter A. Beerel

机构 * University of Southern California(南加州大学) Intel Labs(英特尔实验室) Amazon AGI(亚马逊人工智能实验室) Case Western Reserve University(凯斯西储大学)

Comments 17 pages, 8 figures. EMNLP2025 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.01163 2025-11-04 cs.CV

ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation

Yongyuan Liang, Wei Chow, Feng Li, Ziqiao Ma, Xiyao Wang, Jiageng Mao, Jiuhai Chen, Jiatao Gu, Yue Wang, Furong Huang

机构 * University of Maryland, College Park(马里兰大学学院公园分校) University of Pennsylvania(宾夕法尼亚大学) The Hong Kong University of Science and Technology(香港科学与技术大学) University of Michigan(密歇根大学) University of Southern California(南加州大学)

Comments Project Page: https://roverbench.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.01082 2025-11-04 cs.CV cs.AI cs.LG

GeoToken: Hierarchical Geolocalization of Images via Next Token Prediction

Narges Ghasemi, Amir Ziashahabi, Salman Avestimehr, Cyrus Shahabi

机构 * of Computer Science, University of Southern California, Los Angeles, CA, USA Computer Engineering, University of Southern California, Los Angeles, CA, USA

Comments Accepted to IEEE International Conference on Data Mining (ICDM) 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.00747 2025-11-04 cs.LG

Effective Series Decomposition and Components Learning for Time Series Generation

Zixuan Ma, Chenfeng Huang

机构 * School of Engineering and Applied Science, University of Pennsylvania(工程与应用科学学院,宾夕法尼亚大学) Viterbi School of Engineering, University of Southern California(工程学院,南加州大学)

Comments Accepted at IEEE International Conference on Data Mining (ICDM 2025). Camera-ready version to appear

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.00351 2025-11-04 cs.LG cs.CL

Reject Only Critical Tokens: Pivot-Aware Speculative Decoding

Amir Ziashahabi, Yavuz Faruk Bakman, Duygu Nur Yaldiz, Mostafa El-Khamy, Sai Praneeth Karimireddy, Salman Avestimehr

机构 * University of Southern California(南加州大学) Device Solutions Research America, Samsung Semiconductor, Inc.(三星半导体公司)

Comments Accepted at NeurIPS 2025 Efficient Reasoning Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.00345 2025-11-04 cs.CV cs.LG

OSMGen: Highly Controllable Satellite Image Synthesis using OpenStreetMap Data

Amir Ziashahabi, Narges Ghasemi, Sajjad Shahabi, John Krumm, Salman Avestimehr, Cyrus Shahabi

机构 * University of Southern California(南加州大学)

Comments Accepted at NeurIPS 2025 UrbanAI Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.00202 2025-11-04 cs.SE cs.LG cs.LO

Position: Vibe Coding Needs Vibe Reasoning: Improving Vibe Coding with Formal Verification

Jacqueline Mitchell, Yasser Shaaban

机构 * University of Southern California(南加州大学)

Comments 7 pages, 3 figures, In Proceedings of the 1st ACM SIGPLAN International Workshop on Language Models and Programming Languages (LMPL'25), October 12-18, 2025, Singapore, Singapore. ACM, New York, NY, USA

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.03724 2025-11-04 cs.CV cs.CL

CrowdVLM-R1: Expanding R1 Ability to Vision Language Model for Crowd Counting using Fuzzy Group Relative Policy Reward

Zhiqiang Wang, Pengbin Feng, Yanbin Lin, Shuzhang Cai, Zongao Bian, Jinghua Yan, Xingquan Zhu

机构 * Florida Atlantic University(佛罗里达大学) University of Southern California(南加州大学) University of Texas at Dallas(德克萨斯大学达拉斯分校) Georgia Institute of Technology(佐治亚理工学院) University of Utah(犹他大学)

Comments 10 pages, 6 figures and 4 tables

Journal ref 2025 IEEE International Conference on Big Data (IEEE BigData 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2310.04687 2025-11-04 cs.CV cs.AI

Targeted Attack Improves Protection against Unauthorized Diffusion Customization

Boyang Zheng, Chumeng Liang, Xiaoyu Wu

机构 * Shanghai Jiao Tong University(上海交通大学) University of Southern California(南加州大学)

Comments ICLR 2025 (Spotlight)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.00038 2025-11-04 cs.DC cs.RO

AeroResQ: Edge-Accelerated UAV Framework for Scalable, Resilient and Collaborative Escape Route Planning in Wildfire Scenarios

Suman Raj, Radhika Mittal, Rajiv Mayani, Pawel Zuk, Anirban Mandal, Michael Zink, Yogesh Simmhan, Ewa Deelman

机构 * Indian Institute of Science(印度科学研究院) Information Sciences Institute, University of Southern California(信息科学研究所,南加州大学) Renaissance Computing Institute, University of North Carolina(复兴计算研究所,北卡罗来纳大学) University of Massachusetts(马萨诸塞大学)

Comments 26 pages, 11 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.00024 2025-11-04 cs.CY cs.AI cs.CL cs.LG stat.AP

Chitchat with AI: Understand the supply chain carbon disclosure of companies worldwide through Large Language Model

Haotian Hang, Yueyang Shen, Vicky Zhu, Jose Cruz, Michelle Li

机构 * University of Southern California(南加州大学) University of Michigan(密歇根大学) Babson College(巴布森学院) University of Connecticut(康涅狄格大学)

详情

展开后加载摘要…

URL PDF HTML 收藏