tsunghanwu/visual_haystacks
Viewer
•
Updated
•
20.1k
•
75
•
8
Patrick (Tsung-Han) Wu
tsunghanwu
·
AI & ML interests
Vision and Language
Recent Activity
authored
a paper
4 days ago
Self-correcting LLM-controlled Diffusion Models
authored
a paper
4 days ago
See, Say, and Segment: Teaching LMMs to Overcome False Premises
authored
a paper
4 days ago
Visual Haystacks: Answering Harder Questions About Sets of Images
Organizations
tsunghanwu's activity
liked
a
dataset
9 months ago