ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding
Paper
•
2501.05452
•
Published
•
15
Xingyu Fu
Fiaa
AI & ML interests
NLP, multimodal
Recent Activity
liked
a model
4 days ago
meta-llama/Llama-3.1-8B
liked
a dataset
17 days ago
mvp-lab/LLaVA-OneVision-1.5-Mid-Training-85M
liked
a dataset
17 days ago
HuggingFaceM4/FineVision
Organizations
authored
a
paper
10 months ago
authored
5
papers
over 1 year ago
Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?
Paper
•
2406.07546
•
Published
•
9
MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
Paper
•
2406.09411
•
Published
•
19
Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models
Paper
•
2406.09403
•
Published
•
23
ImagenHub: Standardizing the evaluation of conditional image generation models
Paper
•
2310.01596
•
Published
•
19
BLINK: Multimodal Large Language Models Can See but Not Perceive
Paper
•
2404.12390
•
Published
•
26