AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Paper • 2503.23733 • Published 7 days ago • 11 • 3
DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding Paper • 2503.12797 • Published 21 days ago • 29 • 2
Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models Paper • 2501.05767 • Published Jan 10 • 30 • 2