Haiyang Guo

One Patch Doesn’t Fit All: Adaptive Patching for Native-Resolution Multimodal Large Language Models

MLLM-CL: Continual Learning for Multimodal Large Language Models

MIGA: Make Train-Free Infinite Frame Generation Great Again for Consistent Long Videos

RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness

DESIRE: Dynamic Knowledge Consolidation for Rehearsal-Free Continual Learning

Dual-Modality Guided Prompt for Continual Learning of Large Multimodal Models