3 papers
cs.AI2026
DT2IT-MRM: Debiased Preference Construction and Iterative Training for Multimodal Reward Modeling
Zhihong Zhang, Jie Zhao, Xiaojian Huang +5
Multimodal reward models (MRMs) play a crucial role in aligning Multimodal Large Language Models (MLLMs) with human preferences. Training a good MRM requires high-quality multimoda…
cs.CY2025
Evolutionary Reinforcement Learning based AI tutor for Socratic Interdisciplinary Instruction
Mei Jiang, Haihai Shen, Zhuo Luo +4
Cultivating higher-order cognitive abilities -- such as knowledge integration, critical thinking, and creativity -- in modern STEM education necessitates a pedagogical shift from p…
cs.CV2025
VideoRewardBench: Comprehensive Evaluation of Multimodal Reward Models for Video Understanding
Zhihong Zhang, Xiaojian Huang, Jin Xu +4
Multimodal reward models (MRMs) play a crucial role in the training, inference, and evaluation of Large Vision Language Models (LVLMs) by assessing response quality. However, exist…