Liu, Cheng-Lin
51 publications
ICLR
2026
One Patch Doesn’t Fit All: Adaptive Patching for Native-Resolution Multimodal Large Language Models
CVPR
2025
DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning
AAAI
2025
Recoverable Compression: A Multimodal Vision Token Recovery Mechanism Guided by Text Information