RynnEC: Bringing MLLMs into Embodied World
•
7
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
BlockVid: Block Diffusion for High-Quality and Consistent Minute-Long Video Generation
Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation
Articles
-
PixelRefer
🚀2Referring Any Pixel from Image and Video
-
PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary Granularity
Paper • 2510.23603 • Published • 22 -
Alibaba-DAMO-Academy/PixelRefer-2B
Video-Text-to-Text • Updated • 41 • 3 -
Alibaba-DAMO-Academy/PixelRefer-7B
Video-Text-to-Text • Updated • 94 • 3
-
PixelRefer
🚀2Referring Any Pixel from Image and Video
-
PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary Granularity
Paper • 2510.23603 • Published • 22 -
Alibaba-DAMO-Academy/PixelRefer-2B
Video-Text-to-Text • Updated • 41 • 3 -
Alibaba-DAMO-Academy/PixelRefer-7B
Video-Text-to-Text • Updated • 94 • 3
Lumos Project: Frontier video generation research.
models
15
Alibaba-DAMO-Academy/RynnVLA-002
Updated
•
10
Alibaba-DAMO-Academy/UniLumos
Updated
•
7
Alibaba-DAMO-Academy/PixelRefer-Lite-7B
Video-Text-to-Text
•
Updated
•
15
•
2
Alibaba-DAMO-Academy/PixelRefer-Lite-2B
Video-Text-to-Text
•
Updated
•
32
•
2
Alibaba-DAMO-Academy/PixelRefer-7B
Video-Text-to-Text
•
Updated
•
94
•
3
Alibaba-DAMO-Academy/PixelRefer-2B
Video-Text-to-Text
•
Updated
•
41
•
3
Alibaba-DAMO-Academy/Lumos-1
Updated
•
8
Alibaba-DAMO-Academy/WorldVLA
Updated
•
12
Alibaba-DAMO-Academy/RynnVLA-001-7B-Trajectory
7B
•
Updated
•
16
•
4
Alibaba-DAMO-Academy/RynnVLA-001-7B-Base
7B
•
Updated
•
11
•
8