-
ATH-MaaS/Ovis-Omni-Embedding-3B
Feature Extraction • Updated • 26 -
ATH-MaaS/Ovis-VL-Embedding-2B
Feature Extraction • Updated • 25 -
ATH-MaaS/Ovis-VL-Embedding-9B
Feature Extraction • Updated • 20 -
Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings
Paper • 2609.25165 • Published • 33
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings
UMEM: Unified Memory Extraction and Management Framework for Generalizable Memory
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 • 26 -
ATH-MaaS/Ovis-VL-Embedding-2B
Feature Extraction • Updated • 25 -
ATH-MaaS/Ovis-VL-Embedding-9B
Feature Extraction • Updated • 20 -
Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings
Paper • 2609.25165 • Published • 33
spaces 18
Running on Zero
Agents
Featured
112
OvisOCR2
🔎
Stream structured Markdown from document images and PDFs.
Running on Zero
Agents
Featured
83
Ovis Image 7B
🖼
Official demo for Ovis-Image
Runtime error
Agents
9
CHATS
🚀
The demo for CHATS-SDXL text-to-image generation model
Running on Zero
Agents
Featured
179
Ovis2.5 9B
📊
High-accuracy vision & reasoning for complex tasks
Running on Zero
Agents
Featured
174
Ovis U1 3B
🎨
Demo for multimodal understanding and generation
models 62
ATH-MaaS/Ovis-VL-Embedding-9B
Feature Extraction • Updated • 20
ATH-MaaS/Ovis-VL-Embedding-2B
Feature Extraction • Updated • 25
ATH-MaaS/Ovis-Omni-Embedding-3B
Feature Extraction • Updated • 26
ATH-MaaS/OvisOCR2
Image-Text-to-Text • 0.9B • Updated • 217k • • 470
ATH-MaaS/Lumen_wmt26
Updated • 3
ATH-MaaS/OvisOCR
Image-Text-to-Text • 1B • Updated • 224 • 16
ATH-MaaS/CaptchaMind-7B
8B • Updated • 93 • 3
ATH-MaaS/Marco-DeepResearch-8B-FP8
Text Generation • 8B • Updated • 12
ATH-MaaS/Marco-DeepResearch-8B-i1-GGUF
Text Generation • 8B • Updated • 788 • 5
ATH-MaaS/Marco-DeepResearch-8B-GGUF
Text Generation • 8B • Updated • 538 • 5
datasets 8
ATH-MaaS/CSEMOTIONS
Viewer • Updated • 4.16k • 1.13k • 34
ATH-MaaS/HSCodeComp
Viewer • Updated • 632 • 743 • 12
ATH-MaaS/Marco_Longspeech
Preview • Updated • 685 • 18
ATH-MaaS/Captcha
Viewer • Updated • 82.4k • 900
ATH-MaaS/HalloMTBench
Viewer • Updated • 6.91k • 82 • 7
ATH-MaaS/DeepWideSearch
Preview • Updated • 956 • 11
ATH-MaaS/Marco-Bench-MIF
Preview • Updated • 389 • 3
ATH-MaaS/Parrot-dataset
Viewer • Updated • 25.1k • 1k • 7