Yunheng Li

lyhisme's activity

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

upvoted a paper 3 days ago

Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought

Paper • 2603.22847 • Published 4 days ago • 21

submitted a paper to Daily Papers 3 days ago

Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought

Paper • 2603.22847 • Published 4 days ago • 21

updated 2 models 16 days ago

AudioVisual-Caption/ASID-Captioner-7B

Image-Text-to-Text • 9B • Updated 16 days ago • 188 • 5

AudioVisual-Caption/ASID-Captioner-3B

Image-Text-to-Text • 5B • Updated 16 days ago • 2.64k • 37

updated a dataset 16 days ago

AudioVisual-Caption/ASID-1M

Viewer • Updated 16 days ago • 241k • 6.23k • 82

updated a Space 16 days ago

Running

ASID-Caption

🦉

liked a dataset 25 days ago

AudioVisual-Caption/ASID-1M

Viewer • Updated 16 days ago • 241k • 6.23k • 82

liked 4 models 26 days ago

mradermacher/ASID-Captioner-7B-GGUF

8B • Updated 28 days ago • 270 • 1

mradermacher/ASID-Captioner-3B-GGUF

3B • Updated 28 days ago • 318 • 1

mradermacher/ASID-Captioner-3B-i1-GGUF

3B • Updated 27 days ago • 2.42k • 1

mradermacher/ASID-Captioner-7B-i1-GGUF

8B • Updated 27 days ago • 2.32k • 1

liked 2 models 30 days ago

AudioVisual-Caption/ASID-Captioner-7B

Image-Text-to-Text • 9B • Updated 16 days ago • 188 • 5

AudioVisual-Caption/ASID-Captioner-3B

Image-Text-to-Text • 5B • Updated 16 days ago • 2.64k • 37

upvoted a paper about 1 month ago

Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions

Paper • 2602.13013 • Published Feb 13 • 54

submitted a paper to Daily Papers about 1 month ago

Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions

Paper • 2602.13013 • Published Feb 13 • 54

published 2 models about 1 month ago

AudioVisual-Caption/ASID-Captioner-3B

Image-Text-to-Text • 5B • Updated 16 days ago • 2.64k • 37

AudioVisual-Caption/ASID-Captioner-7B

Image-Text-to-Text • 9B • Updated 16 days ago • 188 • 5

published a Space about 1 month ago

Running

ASID-Caption

🦉

published a dataset about 2 months ago

AudioVisual-Caption/ASID-1M

Viewer • Updated 16 days ago • 241k • 6.23k • 82

upvoted a paper 6 months ago

MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization

Paper • 2510.08540 • Published Oct 9, 2025 • 110