4 papers
MV-STRIDE: Enabling MLLMs to Master Multi-View Spatial Reasoning via Hierarchical Capability Modeling
Jin Xu, Xiaojian Huang, Zhuodong Luo +6
Despite the rapid progress of Multimodal Large Language Models (MLLMs) in 2D vision-language tasks, robust multi-view spatial reasoning remains a fundamental bottleneck due to the…
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…
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…
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…