机构
*
School of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院)
;
ZJU-UIUC Institute, Zhejiang University(浙江大学ZJU-UIUC研究院)
;
Shaoxing K3i Technology Co. Ltd(绍兴K3i科技有限公司)
;
State Key Laboratory of CAD&CG, Zhejiang University(浙江大学CAD&CG国家重点实验室)
专题命中
预训练与数据
:LLM(title,summary_cn);large language model(abstract);language model(abstract);分类 cs.CL
机构
*
Mohamed Bin Zayed University of AI, UAE(穆罕默德·本·扎耶德人工智能大学,阿联酋)
;
Khalifa University, UAE(哈利法大学,阿联酋)
;
Australian National University, Australia(澳大利亚国立大学,澳大利亚)
专题命中
预训练与数据
:large language model(title,abstract);language model(title,abstract);pretraining(abstract)
机构
*
School of Electrical and Computer Engineering, College of Engineering, University of Tehran(德黑兰大学工程学院电气与计算机工程学院)
;
School of Engineering Science, College of Engineering, University of Tehran(德黑兰大学工程学院工程科学学院)
;
Tehran Institute for Advanced Studies, Khatam University(哈塔米大学德黑兰高级研究所)
Can Computational Reducibility Lead to Transferable Models for Graph Combinatorial Optimization?
计算可约性能否导致图组合优化的可迁移模型?
Semih Cantürk, Thomas Sabourin, Frederik Wenkel, Michael Perlmutter, Guy Wolf
机构
*
Operations Research, Université de Montréal(运营研究,蒙特利尔大学)
;
Mila – Quebec AI Institute(魁北克人工智能研究所)
;
Valence Labs(Valence实验室)
;
Dept. of Mathematics, Boise State University(数学系,博伊州立大学)
Data Attribution of Emergent Misalignment with Persona Features
基于角色特征的涌现失配数据归因
Clemens Vetter, David Kaczér, Lucie Flek, Florian Mai
机构
*
Bonn-Aachen International Center for Information Technology, University of Bonn(波恩-亚琛信息技术中心,波恩大学)
;
Lamarr Institute for Machine Learning and Artificial Intelligence(拉马尔机器学习与人工智能研究院)
Ablation-Corrected Evaluation of Attribution Maps in Echocardiographic Ejection-Fraction Models
解剖结构忠实但时间上盲目:超声心动图左心室射血分数估计的归因审核
Hyunkyung Han, Min Jung Kim
机构
*
School of Integrated Medicine, Yonsei University(延世大学统合医学院)
;
Department of Radiology, Research Institute of Radiologic Science, Yonsei University College of Medicine(延世大学医学院放射科学研究所放射科)
Comments12 pages, 4 figures. v2: the chance level is now measured rather than computed, which corrects the ratios reported in v1. Adds a composition-matched ablation with an equal-area control, a reliability estimate for it, an ablation-derived score to report alongside overlap, seed repetition, and pediatric validation