AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
View all Papers
Organization Card
Welcome to ATH-MaaS 🌍
ATH-MaaS is the Model-as-a-Service team within Alibaba Token Hub (ATH), Alibaba’s unified AI business group. We build efficient, open platforms and technical infrastructure that bridge frontier AI research and scalable real-world deployment. Our work spans multimodal understanding and generation, large language models, speech, and agentic systems.
-
ATH-MaaS/Ovis-Omni-Embedding-3B
Feature Extraction • Updated • 550 • 64 -
ATH-MaaS/Ovis-VL-Embedding-2B
Feature Extraction • Updated • 402 • 41 -
ATH-MaaS/Ovis-VL-Embedding-9B
Feature Extraction • Updated • 383 • 48 -
Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings
Paper • 2609.25165 • Published • 49
-
ATH-MaaS/Ovis-Omni-Embedding-3B
Feature Extraction • Updated • 550 • 64 -
ATH-MaaS/Ovis-VL-Embedding-2B
Feature Extraction • Updated • 402 • 41 -
ATH-MaaS/Ovis-VL-Embedding-9B
Feature Extraction • Updated • 383 • 48 -
Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings
Paper • 2609.25165 • Published • 49
spaces 20
Paused
Agents
2
PixText Studio
✍
Refine images to higher quality with AI
Paused
Agents
19
OvisOCR3
⚡
OCR and document understanding with OvisOCR3
Paused
Agents
Featured
117
OvisOCR2
🔎
Stream structured Markdown from document images and PDFs.
Paused
Agents
Featured
82
Ovis Image 7B
🖼
Official demo for Ovis-Image
Paused
Agents
9
CHATS
🚀
The demo for CHATS-SDXL text-to-image generation model
models 65
ATH-MaaS/OvisOCR3
Image-Text-to-Text • 0.9B • Updated • 32.1k • 113
ATH-MaaS/OvisOCR
Image-Text-to-Text • 1B • Updated • 938 • 18
ATH-MaaS/OvisOCR2
Image-Text-to-Text • 0.9B • Updated • 80.3k • • 504
ATH-MaaS/PixText
Updated • 16
ATH-MaaS/TextVerifier-CJK-CLIP
Image Classification • Updated • 5
ATH-MaaS/Ovis-Omni-Embedding-3B
Feature Extraction • Updated • 550 • 64
ATH-MaaS/Ovis-VL-Embedding-9B
Feature Extraction • Updated • 383 • 48
ATH-MaaS/Ovis-VL-Embedding-2B
Feature Extraction • Updated • 402 • 41
ATH-MaaS/Qwen-MT-Lumen
Updated • 11
ATH-MaaS/CaptchaMind-7B
8B • Updated • 56 • 5
datasets 10
ATH-MaaS/TextRefinementBench
Viewer • Updated • 3.32k • 83 • 4
ATH-MaaS/TextRenderBench-ZH
Viewer • Updated • 7.43k • 132 • 4
ATH-MaaS/CSEMOTIONS
Viewer • Updated • 4.16k • 2.18k • 38
ATH-MaaS/HSCodeComp
Viewer • Updated • 632 • 732 • 13
ATH-MaaS/Marco_Longspeech
Preview • Updated • 8.34k • 19
ATH-MaaS/Captcha
Viewer • Updated • 82.4k • 36.8k • 1
ATH-MaaS/HalloMTBench
Viewer • Updated • 6.91k • 85 • 7
ATH-MaaS/DeepWideSearch
Preview • Updated • 1.3k • 12
ATH-MaaS/Marco-Bench-MIF
Preview • Updated • 567 • 4
ATH-MaaS/Parrot-dataset
Viewer • Updated • 25.1k • 867 • 8