Yuhua Li

BoRA: Towards More Expressive Low-Rank Adaptation with Block Diversity

SAFD: A Style-Agnostic Framework for Detecting LLM-Generated Text

Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation

ChatbotID: Identifying Chatbots with Granger Causality Test

FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models

Self-Disentanglement and Re-Composition for Cross-Domain Few-Shot Segmentation

Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation

Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics

Random Registers for Cross-Domain Few-Shot Learning

Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning

The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning