ICML

Uncertainty Quantification for Multimodal Large Language Models with Incoherence-adjusted Semantic Volume

多模态大语言模型的不确定性量化：基于不一致性调整的语义体积

Gregory Kang Ruey Lau, Hieu Dao, Nicole Kan Hui Lin, Bryan Kian Hsiang Low

机构 * Department of Computer Science, National University of Singapore（新加坡国立大学计算机科学系） 纠错

AI总结 UMPIRE是一种无需训练的多模态大语言模型不确定性量化框架，通过内部特征有效捕捉语义多样性和响应不一致性，提升错误检测和不确定性校准性能。

Comments Earlier versions presented at ICLR 2025 QUESTION workshop and ICML 2025 R2-FM workshop

Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases

对抗扩散模型中的奖励过度优化：从归纳偏置和优先偏置的角度出发

Ziyi Zhang, Sen Zhang, Yibing Zhan, Yong Luo, Yonggang Wen, Dacheng Tao

机构 * Institute of Artificial Intelligence, School of Computer Science, Wuhan University, China ； Hubei Luojia Laboratory, Wuhan, China ； The University of Sydney, Australia ； JD Explore Academy, Beijing, China ； Nanyang Technological University, Singapore 纠错

AI总结 本文提出TDPO-R算法，通过利用扩散模型的时间归纳偏置和抑制活跃神经元的优先偏置，有效缓解奖励过度优化问题。

Comments Accepted to ICML 2024

Journal ref International Conference on Machine Learning, pp. 60396-60413, 2024