4 papers
Learn Before You Judge: Progressive Knowledge-to-Decision Alignment for Explainable Hateful Meme Detection
Bo Xu, Chenyuan Wang, Xinyu Chen +5
Hateful memes spread abusive content through implicit interactions between images and text, posing serious threats to the safety of online communities. In recent years, multimodal…
Can We Trust Video Hallucination Detectors? VidHalLoc for Evaluating the Evaluators
Xinyu Chen, Adnan Mahmood, Mark Dras
Video-language models and video agents can produce hallucinations that conflict with spatiotemporal evidence. Existing benchmarks mainly evaluate model hallucinations, and heteroge…
Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models
Xinyu Chen, Haotian Zhai, Can Zhang +2
In zero-shot setting, test-time adaptation adjusts pre-trained models using unlabeled data from the test phase to enhance performance on unknown test distributions. Existing cache-…
Mitigating Cache Noise in Test-Time Adaptation for Large Vision-Language Models
Haotian Zhai, Xinyu Chen, Can Zhang +2
Test-time adaptation (TTA) of visual language models has recently attracted significant attention as a solution to the performance degradation caused by distribution shifts in down…