Han-Jia Ye

han-jia's activity

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

authored a paper 4 days ago

Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning

Paper • 2503.13360 • Published 7 days ago • 6

liked 6 models about 1 month ago

AIDC-AI/Ovis2-34B

Image-Text-to-Text • Updated 25 days ago • 3.43k • 145

AIDC-AI/Ovis2-16B

Image-Text-to-Text • Updated 25 days ago • 4.35k • 86

AIDC-AI/Ovis2-8B

Image-Text-to-Text • Updated 25 days ago • 7.82k • 58

AIDC-AI/Ovis2-4B

Image-Text-to-Text • Updated 25 days ago • 6.53k • 50

AIDC-AI/Ovis2-2B

Image-Text-to-Text • Updated 25 days ago • 6.98k • 52

AIDC-AI/Ovis2-1B

Image-Text-to-Text • Updated 25 days ago • 7.9k • 78