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 1294
2510.19150 2025-10-23 cs.CV cs.AI cs.LG

X-Ego: Acquiring Team-Level Tactical Situational Awareness via Cross-Egocentric Contrastive Video Representation Learning

Yunzhe Wang, Soham Hans, Volkan Ustun

机构 * University of Southern California(南加州大学) USC Institute for Creative Technologies(USC创意技术研究所)

Comments 8 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.18828 2025-10-23 cs.LG cs.AI cs.RO stat.ML

Actor-Free Continuous Control via Structurally Maximizable Q-Functions

Yigit Korkmaz, Urvi Bhuwania, Ayush Jain, Erdem Bıyık

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

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.18370 2025-10-22 cs.LG

Training Diverse Graph Experts for Ensembles: A Systematic Empirical Study

Gangda Deng, Yuxin Yang, Ömer Faruk Akgül, Hanqing Zeng, Yinglong Xia, Rajgopal Kannan, Viktor Prasanna

机构 * University of Southern California(美国南加州大学) Meta AI DEVCOM ARL Army Research Office(DEVCOM ARL陆军研究办公室)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.18238 2025-10-22 cs.LG cs.CY

Fostering the Ecosystem of AI for Social Impact Requires Expanding and Strengthening Evaluation Standards

Bryan Wilder, Angela Zhou

机构 * Bryan Wilder Machine Learning Department(比尔·韦尔德机器学习部门) Carnegie Mellon University(卡内基梅隆大学) Angela Zhou Department of Data Sciences and Operations(安杰莉娅·周数据科学与运营部门) Department of Computer Science University of Southern California(计算机科学系美国南加州大学)

Comments Accepted at NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.15700 2025-10-22 cs.AI cs.CL

InternLM2.5-StepProver: Advancing Automated Theorem Proving via Critic-Guided Search

Zijian Wu, Suozhi Huang, Zhejian Zhou, Huaiyuan Ying, Zheng Yuan, Wenwei Zhang, Dahua Lin, Kai Chen

机构 * Shanghai AI Laboratory(上海人工智能实验室) The Chinese University of Hong Kong(香港中文大学) Tsinghua University(清华大学) University of Southern California(美国南加州大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.17072 2025-10-21 stat.ML cs.LG stat.ME

DFNN: A Deep Fréchet Neural Network Framework for Learning Metric-Space-Valued Responses

Kyum Kim, Yaqing Chen, Paromita Dubey

机构 * Rutgers University–New Brunswick(新布伦斯维克罗切斯特大学) University of Southern California(南加州大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.17058 2025-10-21 cs.LG cs.AI

Bitwidth-Specific Logarithmic Arithmetic for Future Hardware-Accelerated Training

Hassan Hamad, Yuou Qiu, Peter A. Beerel, Keith M. Chugg

机构 * Ming Hsieh Department of Electrical and Computer Engineering University of Southern California(明世赫电气与计算机工程系美国南加州大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.16819 2025-10-21 cs.CL

Cross-Genre Authorship Attribution via LLM-Based Retrieve-and-Rerank

Shantanu Agarwal, Joel Barry, Steven Fincke, Scott Miller

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.16716 2025-10-21 cs.CR cs.LG

DistilLock: Safeguarding LLMs from Unauthorized Knowledge Distillation on the Edge

Asmita Mohanty, Gezheng Kang, Lei Gao, Murali Annavaram

机构 * University of Southern California(南加州大学) University of California, Davis(加州大学戴维斯分校)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.10343 2025-10-21 cs.CL cs.AI

Code Execution as Grounded Supervision for LLM Reasoning

Dongwon Jung, Wenxuan Zhou, Muhao Chen

机构 * University of California, Davis(加州大学戴维斯分校) University of Southern California(南加州大学)

Comments EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.16034 2025-10-21 cs.CV

VisualLens: Personalization through Task-Agnostic Visual History

Wang Bill Zhu, Deqing Fu, Kai Sun, Yi Lu, Zhaojiang Lin, Seungwhan Moon, Kanika Narang, Mustafa Canim, Yue Liu, Anuj Kumar, Xin Luna Dong

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

Comments Accepted by NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.12468 2025-10-21 cs.CL cs.AI cs.IR cs.LG

Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation

Dongwon Jung, Qin Liu, Tenghao Huang, Ben Zhou, Muhao Chen

机构 * University of California, Davis(加州大学戴维斯分校) University of Southern California(南加州大学) Arizona State University(亚利桑那州立大学)

Comments EMNLP 2025 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.04649 2025-10-20 eess.SY cs.LG cs.SY math.OC

End-to-End Learning Framework for Solving Non-Markovian Optimal Control

Xiaole Zhang, Peiyu Zhang, Xiongye Xiao, Shixuan Li, Vasileios Tzoumas, Vijay Gupta, Paul Bogdan

机构 * Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA 90089, USA(美国南加州大学明希斯电气与计算机工程系) Department of Aerospace Engineering, University of Michigan, Ann Arbor, MI 48109, USA(美国密歇根大学航空航天工程系) Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47907, USA(美国普渡大学埃尔莫家庭电气与计算机工程学院)

Journal ref International Conference on Machine Learning (ICML) 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.14242 2025-10-17 cs.CL cs.LG

Flip-Flop Consistency: Unsupervised Training for Robustness to Prompt Perturbations in LLMs

Parsa Hejabi, Elnaz Rahmati, Alireza S. Ziabari, Morteza Dehghani

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

Comments 14 pages, 6 figures, 3 tables, and 1 algorithm

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.16411 2025-10-17 cs.CV cs.LG

Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression

Sreetama Sarkar, Yue Che, Alex Gavin, Peter A. Beerel, Souvik Kundu

机构 * University of Southern California(美国南加州大学) Intel Labs(英特尔实验室) Harvard-Westlake School(哈佛-韦斯利学校)

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.06658 2025-10-17 cs.AI

TriQXNet: Forecasting Dst Index from Solar Wind Data Using an Interpretable Parallel Classical-Quantum Framework with Uncertainty Quantification

Md Abrar Jahin, M. F. Mridha, Zeyar Aung, Nilanjan Dey, R. Simon Sherratt

机构 * Department of Computer Science, Viterbi School of Engineering, University of Southern California(计算机科学系,维特比工程学院,南加州大学) Department of Computer Science, American International University-Bangladesh(计算机科学系,美国国际大学-孟加拉国) Department of Computer Science & Engineering, Techno International New Town(计算机科学与工程系,Techno International New Town) Department of Biomedical Engineering, University of Reading(生物医学工程系,阅读大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.03052 2025-10-16 cs.CL cs.LG

Teaching Models to Understand (but not Generate) High-risk Data

Ryan Wang, Matthew Finlayson, Luca Soldaini, Swabha Swayamdipta, Robin Jia

机构 * Department of Computer Science, University of Southern California(计算机科学系,南加州大学) Allen Institute for AI(人工智能研究所)

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.12470 2025-10-16 cs.CL

Reasoning on a Spectrum: Aligning LLMs to System 1 and System 2 Thinking

Alireza S. Ziabari, Nona Ghazizadeh, Zhivar Sourati, Farzan Karimi-Malekabadi, Payam Piray, Morteza Dehghani

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
2510.13621 2025-10-16 cs.CY cs.AI

The Role of Computing Resources in Publishing Foundation Model Research

Yuexing Hao, Yue Huang, Haoran Zhang, Chenyang Zhao, Zhenwen Liang, Paul Pu Liang, Yue Zhao, Lichao Sun, Saleh Kalantari, Xiangliang Zhang, Marzyeh Ghassemi

机构 * EECS, MIT(MIT电子工程与计算机科学系) Cornell University(康奈尔大学) CSE, University of Notre Dame(诺丁汉大学计算机科学工程系) Computer Science Department, University of California, Los Angeles(加州大学洛杉矶分校计算机科学系) Computer Science Department, Lehigh University(莱斯大学计算机科学系) School of Advanced Computing, University of Southern California(南加州大学高级计算学院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.13037 2025-10-16 stat.ML cs.LG

Conformal Inference for Open-Set and Imbalanced Classification

Tianmin Xie, Yanfei Zhou, Ziyi Liang, Stefano Favaro, Matteo Sesia

机构 * Department of Data Sciences and Operations, University of Southern California, USA(美国南加州大学数据科学与运营系) Department of Statistics, University of California, Irvine, USA(美国加州大学伊尔弗斯分校统计系) Dipartimento di Scienze Economico-Sociali e Matematico-Statistiche, Università di Torino and Collegio Carlo Alberto, Italy(意大利都灵大学经济与社会科学系和卡尔罗·阿尔贝托学院) Department of Computer Science, University of Southern California, USA(美国南加州大学计算机科学系)

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.00874 2025-10-16 cs.DL cs.AI cs.CV cs.CY

Position: The Artificial Intelligence and Machine Learning Community Should Adopt a More Transparent and Regulated Peer Review Process

Jing Yang

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

Comments ICML 2025; https://papercopilot.com/

详情

展开后加载摘要…

URL PDF HTML 收藏
2206.02346 2025-10-16 math.OC cs.AI cs.LG cs.SY eess.SY

Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPs

Dongsheng Ding, Kaiqing Zhang, Jiali Duan, Tamer Başar, Mihailo R. Jovanović

机构 * University of Tennessee, Knoxville(田纳西大学) University of Maryland, College Park(马里兰大学) Apple Inc.(苹果公司) University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) University of Southern California(南加州大学)

Comments 76 pages, 4 figures, 2 tables; Journal version of the NeurIPS 2020 paper; Accepted to JMLR

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12256 2025-10-15 cs.CV

Vectorized Video Representation with Easy Editing via Hierarchical Spatio-Temporally Consistent Proxy Embedding

Ye Chen, Liming Tan, Yupeng Zhu, Yuanbin Wang, Bingbing Ni

机构 * Shanghai Jiao Tong University(上海交通大学) USC-SJTU Institute of Cultural and Creative Industry(USC-SJTU文化创意产业研究院)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12185 2025-10-15 cs.CL cs.SD

Not in Sync: Unveiling Temporal Bias in Audio Chat Models

Jiayu Yao, Shenghua Liu, Yiwei Wang, Rundong Cheng, Lingrui Mei, Baolong Bi, Zhen Xiong, Xueqi Cheng

机构 * Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所) University of California, Merced(加州大学默塞德分校) Beijing University of Posts and Telecommunications(北京邮电大学) University of Southern California(南加州大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12040 2025-10-15 cs.CL

Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directions

Sungmin Kang, Yavuz Faruk Bakman, Duygu Nur Yaldiz, Baturalp Buyukates, Salman Avestimehr

机构 * University of Southern California(南加州大学) University of Birmingham(伯明翰大学)

Comments 24 pages, 3 figures, magazine

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.05670 2025-10-15 cs.CL

Can LLMs Express Personality Across Cultures? Introducing CulturalPersonas for Evaluating Trait Alignment

Priyanka Dey, Yugal Khanter, Aayush Bothra, Jieyu Zhao, Emilio Ferrara

机构 * Department of Computer Science, University of Southern California(计算机科学系,南加州大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.11566 2025-10-14 cs.RO cs.CV

SCOOP'D: Learning Mixed-Liquid-Solid Scooping via Sim2Real Generative Policy

Kuanning Wang, Yongchong Gu, Yuqian Fu, Zeyu Shangguan, Sicheng He, Xiangyang Xue, Yanwei Fu, Daniel Seita

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

Comments Project page is at https://scoopdiff.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.11535 2025-10-14 cs.NI cs.AI

A Flexible Multi-Agent Deep Reinforcement Learning Framework for Dynamic Routing and Scheduling of Latency-Critical Services

Vincenzo Norman Vitale, Antonia Maria Tulino, Andreas F. Molisch, Jaime Llorca

机构 * University of Naples Federico II(那不勒斯费德里科二世大学) University of Southern California(南加州大学) University of Trento(特伦托大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.10409 2025-10-14 cs.AI

Trace Length is a Simple Uncertainty Signal in Reasoning Models

Siddartha Devic, Charlotte Peale, Arwen Bradley, Sinead Williamson, Preetum Nakkiran, Aravind Gollakota

机构 * University of Southern California(南加州大学) Stanford University(斯坦福大学) Apple(苹果公司)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.19073 2025-10-14 cs.CL

MFTCXplain: A Multilingual Benchmark Dataset for Evaluating the Moral Reasoning of LLMs through Multi-hop Hate Speech Explanation

Jackson Trager, Francielle Vargas, Diego Alves, Matteo Guida, Mikel K. Ngueajio, Ameeta Agrawal, Yalda Daryani, Farzan Karimi-Malekabadi, Flor Miriam Plaza-del-Arco

机构 * University of Southern California(南加州大学) São Paulo State University(圣保罗州立大学) Saarland University(萨尔兰大学) University of Melbourne(墨尔本大学) Howard University(霍华德大学) Portland State University(波特兰州立大学) Leiden University(莱顿大学)

Comments Jackson Trager and Francielle Vargas contributed equally

Journal ref Findings of the Association for Computational Linguistics: EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏