Ke Yan

ToVE: Efficient Vision-Language Learning via Knowledge Transfer from Vision Experts

Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration

Hallucination in LVLMs: Fictitious Presupposition Questions, Benchmark, and Solution

Exploring the Collaborative Advantage of Low-level Information on Generalizable AI-generateted Image Detection

YouCLIP: Advancing Multilingual Cross-Modal Learning with Efficient Training.

TAS: Distilling Arbitrary Teacher and Student via a Hybrid Assistant

SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models