Cheng-Lin Liu

7

Papers

42

Total Citations

Papers (7)

Active Generalized Category Discovery

RCL: Reliable Continual Learning for Unified Failure Detection

DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning

Unified Entropy Optimization for Open-Set Test-Time Adaptation

Recoverable Compression: A Multimodal Vision Token Recovery Mechanism Guided by Text Information

Federated Continual Instruction Tuning

MV-MATH: Evaluating Multimodal Math Reasoning in Multi-Visual Contexts