AI & ML interests
None defined yet.
Recent 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 • 700 • 64 -
ATH-MaaS/Ovis-VL-Embedding-2B
Feature Extraction • Updated • 489 • 40 -
ATH-MaaS/Ovis-VL-Embedding-9B
Feature Extraction • Updated • 497 • 48 -
Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings
Paper • 2609.25165 • Published • 78
-
ATH-MaaS/Ovis-Omni-Embedding-3B
Feature Extraction • Updated • 700 • 64 -
ATH-MaaS/Ovis-VL-Embedding-2B
Feature Extraction • Updated • 489 • 40 -
ATH-MaaS/Ovis-VL-Embedding-9B
Feature Extraction • Updated • 497 • 48 -
Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings
Paper • 2609.25165 • Published • 78
spaces 20
Running on Zero
Agents
2
PixText Studio
✍
Refine images to higher quality with AI
Running on Zero
Agents
16
OvisOCR3
⚡
OCR and document understanding with OvisOCR3
Running on Zero
Agents
Featured
117
OvisOCR2
🔎
Stream structured Markdown from document images and PDFs.
Running on Zero
Agents
Featured
82
Ovis Image 7B
🖼
Official demo for Ovis-Image
Runtime error
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 • 2.15k • 93
ATH-MaaS/OvisOCR
Image-Text-to-Text • 1B • Updated • 711 • 17
ATH-MaaS/OvisOCR2
Image-Text-to-Text • 0.9B • Updated • 119k • • 504
ATH-MaaS/PixText
Updated • 16
ATH-MaaS/TextVerifier-CJK-CLIP
Image Classification • Updated • 5
ATH-MaaS/Ovis-Omni-Embedding-3B
Feature Extraction • Updated • 700 • 64
ATH-MaaS/Ovis-VL-Embedding-9B
Feature Extraction • Updated • 497 • 48
ATH-MaaS/Ovis-VL-Embedding-2B
Feature Extraction • Updated • 489 • 40
ATH-MaaS/Qwen-MT-Lumen
Updated • 8
ATH-MaaS/CaptchaMind-7B
8B • Updated • 94 • 5
datasets 10
ATH-MaaS/TextRefinementBench
Viewer • Updated • 3.32k • 49 • 4
ATH-MaaS/TextRenderBench-ZH
Viewer • Updated • 7.43k • 74 • 4
ATH-MaaS/CSEMOTIONS
Viewer • Updated • 4.16k • 1.9k • 38
ATH-MaaS/HSCodeComp
Viewer • Updated • 632 • 744 • 13
ATH-MaaS/Marco_Longspeech
Preview • Updated • 3.73k • 19
ATH-MaaS/Captcha
Viewer • Updated • 82.4k • 19.6k • 1
ATH-MaaS/HalloMTBench
Viewer • Updated • 6.91k • 76 • 7
ATH-MaaS/DeepWideSearch
Preview • Updated • 1.39k • 12
ATH-MaaS/Marco-Bench-MIF
Preview • Updated • 503 • 4
ATH-MaaS/Parrot-dataset
Viewer • Updated • 25.1k • 863 • 8