PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning
PDCR:感知分解置信度奖励用于视觉-语言推理
Hee Suk Yoon, Eunseop Yoon, Ji Woo Hong, SooHwan Eom, Gwanhyeong Koo, Mark Hasegawa-Johnson, Qi Dai, Chong Luo, Chang D. Yoo
机构
*
Korea Advanced Institute of Science and Technology (KAIST)(韩国高级科学技术研究院)
;
University of Illinois at Urbana-Champaign (UIUC)(伊利诺伊大学厄巴纳-香槟分校)
;
Microsoft Research Asia (MSRA)(微软亚洲研究院)
Are Compact Rationales Free? Measuring Tile Selection Headroom in Frozen WSI-MIL
紧凑的理性是否免费?测量冻结WSI-MIL中的瓷砖选择余地
Hyun Do Jung, Jungwon Choi, Soojung Choi, Yujin Oh, Hwiyoung Kim
机构
*
Department of Artificial Intelligence, Yonsei University(延世大学人工智能系)
;
Kim Jaechul Graduate School of AI, KAIST(金 Jaechul人工智能研究生院,韩国科学技术院)
;
Department of Integrative Medicine, College of Medicine, Yonsei University(延世大学医学院整合医学系)
;
Department of Biomedical Systems Informatics, College of Medicine, Yonsei University(延世大学医学院生物医学系统信息学系)
;
H-Data Strategy Center, Hallym University Chuncheon Sacred Heart Hospital(翰林大学春川圣心医院H-Data战略中心)
Comments9 pages, 16 figures. Accepted at the ICLR 2026 Workshop on Principled Design for Trustworthy AI: Interpretability, Robustness, and Safety across Modalities