5 7 13

Xingyu Fu

Fiaa

AI & ML interests

NLP, multimodal

Recent Activity

new activity about 1 hour ago

Fiaa/ReFocus:Add relevant metadata, link to code and paper

liked a model about 1 hour ago

Fiaa/ReFocus

liked a dataset 20 days ago

deepcs233/Visual-CoT

View all activity

Organizations

Fiaa's activity

New activity in Fiaa/ReFocus about 1 hour ago

Add relevant metadata, link to code and paper

#1 opened 27 days ago by

nielsr

liked a model about 1 hour ago

Fiaa/ReFocus

Image-Text-to-Text • Updated about 1 hour ago • 1

liked a dataset 20 days ago

deepcs233/Visual-CoT

Preview • Updated Dec 20, 2024 • 1.47k • 20

liked a model 26 days ago

stabilityai/stable-video-diffusion-img2vid-xt

Image-to-Video • Updated Jul 10, 2024 • 389k • 2.86k

authored a paper 30 days ago

ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding

Paper • 2501.05452 • Published Jan 9 • 15

upvoted a paper 30 days ago

ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding

Paper • 2501.05452 • Published Jan 9 • 15

commented a paper 30 days ago

ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding

Paper • 2501.05452 • Published Jan 9 • 15 •

updated a model 30 days ago

Fiaa/ReFocus

Image-Text-to-Text • Updated about 1 hour ago • 1

upvoted a paper 3 months ago

Visual CoT: Unleashing Chain-of-Thought Reasoning in Multi-Modal Language Models

Paper • 2403.16999 • Published Mar 25, 2024 • 4

liked a dataset 3 months ago

HuggingFaceM4/the_cauldron

Viewer • Updated May 6, 2024 • 1.88M • 77.5k • 366

updated a dataset 4 months ago

Fiaa/ReFocus

Viewer • Updated Oct 30, 2024 • 813 • 50

liked a Space 4 months ago

169

VBench Leaderboard

📊

Upload and evaluate video models

updated 2 datasets 6 months ago

Fiaa/wildvision-errors

Updated Aug 15, 2024 • 38

BLINK-Benchmark/BLINK

Viewer • Updated Aug 13, 2024 • 3.81k • 2.08k • 23

liked 3 datasets 6 months ago

liked a Space 7 months ago

541

Vision Arena (Testing VLMs side-by-side)

🖼

Analyze images to detect and label objects

updated a dataset 8 months ago

CommonsenseT2I/CommonsensenT2I

Viewer • Updated Jun 14, 2024 • 150 • 60 • 4

authored a paper 8 months ago

Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?

Paper • 2406.07546 • Published Jun 11, 2024 • 8