asha

wl1982's activity

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

New activity in TIGER-Lab/MMEB-Leaderboard 3 days ago

Upload Ovis-Omni-Embedding-v0.1-3B.json

#155 opened 3 days ago by

wl1982

upvoted a paper 21 days ago

OvisOCR2 Technical Report

Paper • 2607.13639 • Published 22 days ago • 55

liked a Space 22 days ago

Running on Zero

Agents

Featured

99

OvisOCR2

🔎

99

Stream structured Markdown from document images and PDFs.

liked a model 24 days ago

ATH-MaaS/OvisOCR2

Image-Text-to-Text • 0.9B • Updated 21 days ago • 90.1k • 369

liked a model 3 months ago

ATH-MaaS/Ovis2.6-80B-A3B

Image-Text-to-Text • 81B • Updated May 14 • 64 • 67

liked a model 5 months ago

ATH-MaaS/Ovis2.6-30B-A3B

Image-Text-to-Text • 31B • Updated Feb 24 • 4.59k • 163

liked a Space 8 months ago

Sleeping

Agents

Featured

83

Ovis Image 7B

🖼

83

Official demo for Ovis-Image

liked a model 8 months ago

ATH-MaaS/Ovis-Image-7B

Text-to-Image • 7B • Updated May 15 • 305 • • 208

upvoted a paper 12 months ago

Ovis2.5 Technical Report

Paper • 2508.11737 • Published Aug 15, 2025 • 116

liked 2 Spaces 12 months ago

Build error

Agents

110

Ovis2.5 2B

📚

110

Lightweight vision for efficient deployment

Running on Zero

Agents

Featured

177

Ovis2.5 9B

📊

177

High-accuracy vision & reasoning for complex tasks

upvoted a collection 12 months ago

Ovis2.5

Collection

Our next-generation MLLMs for native-resolution vision and advanced reasoning • 5 items • Updated Aug 19, 2025 • 58

liked 2 models 12 months ago

ATH-MaaS/Ovis2.5-9B

Image-Text-to-Text • 9B • Updated Feb 13 • 228k • 308

ATH-MaaS/Ovis2.5-2B

Image-Text-to-Text • 3B • Updated Feb 13 • 7.54k • 201

upvoted a paper about 1 year ago

Ovis-U1 Technical Report

Paper • 2506.23044 • Published Jun 29, 2025 • 63

liked a model about 1 year ago

ATH-MaaS/Ovis-U1-3B

Any-to-Any • 4B • Updated Jul 3, 2025 • 2k • 214

liked a Space about 1 year ago

Sleeping

Agents

Featured

174

Ovis U1 3B

🎨

174

Demo for multimodal understanding and generation