li haodong

mickyhimself's activity

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

authored a paper 2 days ago

Proact-VL: A Proactive VideoLLM for Real-Time AI Companions

Paper • 2603.03447 • Published 4 days ago • 24

upvoted 2 papers 2 days ago

OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens

Paper • 2603.02138 • Published 5 days ago • 134

Proact-VL: A Proactive VideoLLM for Real-Time AI Companions

Paper • 2603.03447 • Published 4 days ago • 24

updated a dataset 6 days ago

mickyhimself/coco666

Viewer • Updated 6 days ago • 3.6k • 76

published a dataset 6 days ago

mickyhimself/coco666

Viewer • Updated 6 days ago • 3.6k • 76

authored a paper 17 days ago

GENIUS: Generative Fluid Intelligence Evaluation Suite

Paper • 2602.11144 • Published 24 days ago • 53

upvoted a paper 23 days ago

GENIUS: Generative Fluid Intelligence Evaluation Suite

Paper • 2602.11144 • Published 24 days ago • 53

submitted a paper to Daily Papers 23 days ago

GENIUS: Generative Fluid Intelligence Evaluation Suite

Paper • 2602.11144 • Published 24 days ago • 53

upvoted a paper 23 days ago

Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

Paper • 2602.10604 • Published 24 days ago • 187

authored a paper 25 days ago

GEBench: Benchmarking Image Generation Models as GUI Environments

Paper • 2602.09007 • Published 26 days ago • 39

liked a dataset 25 days ago

stepfun-ai/GEBench

Updated 10 days ago • 533 • 9

New activity in stepfun-ai/GEBench 25 days ago

Update README.md

#1 opened 25 days ago by

mickyhimself

upvoted a paper 25 days ago

GEBench: Benchmarking Image Generation Models as GUI Environments

Paper • 2602.09007 • Published 26 days ago • 39

submitted a paper to Daily Papers 25 days ago

GEBench: Benchmarking Image Generation Models as GUI Environments

Paper • 2602.09007 • Published 26 days ago • 39

authored a paper 26 days ago

How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing

Paper • 2602.01851 • Published Feb 2 • 16

updated a dataset 26 days ago

mickyhimself/GEBench_test

Updated 26 days ago • 89

published a dataset 27 days ago

mickyhimself/GEBench_test

Updated 26 days ago • 89

upvoted a collection about 1 month ago

VIBE Model Results

Collection

This collection archives the raw output generations from various models evaluated on the VIBE benchmark. • 16 items • Updated Feb 1 • 3

upvoted a paper about 1 month ago

How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing

Paper • 2602.01851 • Published Feb 2 • 16

upvoted a paper about 2 months ago

STEP3-VL-10B Technical Report

Paper • 2601.09668 • Published Jan 14 • 194