Official datasets and checkpoints of the paper -- Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling
Patrick (Tsung-Han) Wu
tsunghanwu
·
AI & ML interests
Vision and Language
Recent Activity
authored
a paper
1 day ago
Self-correcting LLM-controlled Diffusion Models
authored
a paper
1 day ago
See, Say, and Segment: Teaching LMMs to Overcome False Premises
authored
a paper
1 day ago
Visual Haystacks: Answering Harder Questions About Sets of Images
Organizations
