-
A Comprehensive Survey of Evaluating Multimodal Foundation Models: Hierarchical Perspective and Extensive Applications
An up-to-date survey on the evaluation of MLLMs in 2025
-
Diversity-based Data Subset Selection with Deep Reinforcement Learning
A novel reinforcement learning based method for efficiently selecting most diverse subsets
-
Instruction-aware Visual Feature Extraction for Multimodal Large Language Mode
A novel efficient multimodal large language model that compress visual prefix based on instructions
