arxiv:2510.07318
Weihao Yu
whyu
AI & ML interests
Computer Vision, NLP and AI
Recent Activity
upvoted a paper 1 day ago
ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer submitted a paper 21 days ago
NoLan: Mitigating Object Hallucinations in Large Vision-Language Models via Dynamic Suppression of Language Priors