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~~

高校专区

Georgia Institute of Technology(佐治亚理工学院)

2025-10-20 至 2025-10-20 共收录 5
2510.15081 2025-10-20 cs.CL cs.SI

A Generalizable Rhetorical Strategy Annotation Model Using LLM-based Debate Simulation and Labelling

Shiyu Ji, Farnoosh Hashemi, Joice Chen, Juanwen Pan, Weicheng Ma, Hefan Zhang, Sophia Pan, Ming Cheng, Shubham Mohole, Saeed Hassanpour, Soroush Vosoughi, Michael Macy

机构 * Cornell University(康奈尔大学) Georgia Institute of Technology(佐治亚理工学院) Dartmouth College(达特茅斯学院)

Comments The first two authors contributed equally

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.11620 2025-10-20 cs.CL

Enhancing Long Chain-of-Thought Reasoning through Multi-Path Plan Aggregation

Siheng Xiong, Ali Payani, Faramarz Fekri

机构 * Georgia Institute of Technology(佐治亚理工学院) Cisco Research(思科研究)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.22467 2025-10-20 cs.MA cs.AI cs.LG

Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent Systems

Jiaxi Yang, Mengqi Zhang, Yiqiao Jin, Hao Chen, Qingsong Wen, Lu Lin, Yi He, Srijan Kumar, Weijie Xu, James Evans, Jindong Wang

机构 * The Pennsylvania State University(宾夕法尼亚州立大学) William & Mary(威廉与玛丽学院) Georgia Institute of Technology(佐治亚理工学院) AMD(AMD公司) Squirrel AI Amazon(亚马逊公司) University of Chicago(芝加哥大学)

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.08216 2025-10-20 stat.ML cs.LG

Landmark-Based Node Representations for Shortest Path Distance Approximations in Random Graphs

My Le, Luana Ruiz, Souvik Dhara

机构 * Dept. of Applied Mathematics & Statistics(应用数学与统计学系) Johns Hopkins University(约翰霍普金斯大学) School of Industrial and Systems Engineering(工业与系统工程学院) Georgia Institute of Technology(佐治亚理工学院)

Comments Landmark-based embeddings preserve global distances in graphs more efficiently; on Erdos-Renyi random graphs they need lower dimensions, and GNNs generalize these embeddings to large real-world networks

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.13342 2025-10-20 stat.ML cs.LG

Validity of Feature Importance in Low-Performing Machine Learning for Tabular Biomedical Data

Youngro Lee, Giacomo Baruzzo, Jeonghwan Kim, Jongmo Seo, Barbara Di Camillo

机构 * Seoul National University(首尔国立大学) University of Padova(帕多瓦大学) Georgia Institute of Technology(佐治亚理工学院)

Journal ref IEEE Access (Early Access), 2025

详情

展开后加载摘要…

URL PDF HTML 收藏