Yongyi Su

Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs

Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model

On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning

Test-Time Training for Out-of-Distribution Industrial Anomaly Detection via Robust Distribution Alignment