Junchao Yi

Junc1i's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 3 papers about 15 hours ago

Glance: Accelerating Diffusion Models with 1 Sample

Paper • 2512.02899 • Published Dec 2, 2025 • 30

Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT

Paper • 2505.24182 • Published May 30, 2025

FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching

Paper • 2604.06757 • Published 2 days ago • 5

commented a paper about 21 hours ago

FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching

Paper • 2604.06757 • Published 2 days ago • 5 •

2

upvoted a paper about 21 hours ago

FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching

Paper • 2604.06757 • Published 2 days ago • 5

updated a model about 21 hours ago

CSU-JPG/FlowInOne

Image-to-Image • Updated about 21 hours ago • 2

updated 2 datasets about 21 hours ago

CSU-JPG/VPBench

Viewer • Updated about 21 hours ago • 1.06k • 45

CSU-JPG/VisPrompt5M

Viewer • Updated about 21 hours ago • 5.36M • 192 • 1

published 2 datasets 3 days ago

CSU-JPG/VPBench

Viewer • Updated about 21 hours ago • 1.06k • 45

CSU-JPG/VisPrompt5M

Viewer • Updated about 21 hours ago • 5.36M • 192 • 1

published a model 12 days ago

CSU-JPG/FlowInOne

Image-to-Image • Updated about 21 hours ago • 2

updated a model about 1 month ago

Junc1i/FlowInOne

Updated Feb 28

updated a dataset about 2 months ago

Junc1i/VisPrompt

Updated Feb 10 • 219

published a model 2 months ago

Junc1i/FlowInOne

Updated Feb 28

published a dataset 3 months ago

Junc1i/VisPrompt

Updated Feb 10 • 219

upvoted a paper 4 months ago

EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models

Paper • 2512.14666 • Published Dec 16, 2025 • 10

liked a model 4 months ago

CSU-JPG/Glance

Text-to-Image • Updated Dec 15, 2025 • 39 • • 14

upvoted a paper 5 months ago

UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback

Paper • 2511.01678 • Published Nov 3, 2025 • 38

upvoted a paper 7 months ago

Video models are zero-shot learners and reasoners

Paper • 2509.20328 • Published Sep 24, 2025 • 100

updated a dataset 11 months ago

CSU-JPG/MVPBench

Viewer • Updated May 15, 2025 • 4.7k • 25 • 1