RynnEC: Bringing MLLMs into Embodied World
• 9
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model
WorldOlympiad: Can Your World Model Survive a Triathlon?
Articles
-
Alibaba-DAMO-Academy/RynnBrain1.1-2B
Image-Text-to-Text • 2B • Updated • 562 • 7 -
Alibaba-DAMO-Academy/RynnBrain1.1-9B
Image-Text-to-Text • 9B • Updated • 271 • 3 -
Alibaba-DAMO-Academy/RynnBrain1.1-122B-A10B
Image-Text-to-Text • 123B • Updated • 231 • 8 -
RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model
Paper • 2607.17977 • Published • 196
ClinFusion series of work.
Lingshu-Cell is a cellular world model that learns transcriptomic state distributions and enables conditional simulation of cellular perturbation.
Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning
-
lingshu-medical-mllm/Lingshu-7B
Image-Text-to-Text • 8B • Updated • 145k • 78 -
lingshu-medical-mllm/Lingshu-I-8B
Image-Text-to-Text • 8B • Updated • 2.15k • 7 -
lingshu-medical-mllm/Lingshu-32B
Image-Text-to-Text • 33B • Updated • 1.66k • • 80 -
Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning
Paper • 2506.07044 • Published • 114
-
PixelRefer
🚀2Referring Any Pixel from Image and Video
-
PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary Granularity
Paper • 2510.23603 • Published • 26 -
Alibaba-DAMO-Academy/PixelRefer-2B
Video-Text-to-Text • Updated • 104 • 4 -
Alibaba-DAMO-Academy/PixelRefer-7B
Video-Text-to-Text • Updated • 26 • 4
Using Human Demonstrations to Improve Robot Manipulation
RynnWorld
-
Alibaba-DAMO-Academy/RynnWorld-4D
Image-to-Video • Updated • 9 -
Alibaba-DAMO-Academy/RynnWorld-Teleop-Causal
Image-to-Video • Updated • 93 • 1 -
Alibaba-DAMO-Academy/RynnWorld-Teleop
Image-to-Video • Updated • 71 • 7 -
RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation
Paper • 2607.06559 • Published • 95
Speedup Volume Understanding with Efficient Multimodal Large Language Models
OmniCT: Towards a Unified Slice-Volume LVLM for Comprehensive CT Analysis
-
Alibaba-DAMO-Academy/OmniCT-3B
Image-Text-to-Text • 3B • Updated • 18 • 2 -
Alibaba-DAMO-Academy/OmniCT-7B
Image-Text-to-Text • 8B • Updated • 23 • 4 -
lintw/MedEval-CT
Preview • Updated • 27 • 4 -
OmniCT: Towards a Unified Slice-Volume LVLM for Comprehensive CT Analysis
Paper • 2602.16110 • Published • 4
-
RynnBrain
📉10Query images or videos with visual and text prompts
-
Alibaba-DAMO-Academy/RynnBrain-2B
Image-Text-to-Text • 2B • Updated • 4.72k • 26 -
Alibaba-DAMO-Academy/RynnBrain-8B
Image-Text-to-Text • 9B • Updated • 409 • 12 -
Alibaba-DAMO-Academy/RynnBrain-30B-A3B
Image-Text-to-Text • 17B • Updated • 126 • 19
Lumos Project: Frontier video generation research.
-
Alibaba-DAMO-Academy/RynnBrain1.1-2B
Image-Text-to-Text • 2B • Updated • 562 • 7 -
Alibaba-DAMO-Academy/RynnBrain1.1-9B
Image-Text-to-Text • 9B • Updated • 271 • 3 -
Alibaba-DAMO-Academy/RynnBrain1.1-122B-A10B
Image-Text-to-Text • 123B • Updated • 231 • 8 -
RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model
Paper • 2607.17977 • Published • 196
RynnWorld
-
Alibaba-DAMO-Academy/RynnWorld-4D
Image-to-Video • Updated • 9 -
Alibaba-DAMO-Academy/RynnWorld-Teleop-Causal
Image-to-Video • Updated • 93 • 1 -
Alibaba-DAMO-Academy/RynnWorld-Teleop
Image-to-Video • Updated • 71 • 7 -
RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation
Paper • 2607.06559 • Published • 95
ClinFusion series of work.
Speedup Volume Understanding with Efficient Multimodal Large Language Models
Lingshu-Cell is a cellular world model that learns transcriptomic state distributions and enables conditional simulation of cellular perturbation.
OmniCT: Towards a Unified Slice-Volume LVLM for Comprehensive CT Analysis
-
Alibaba-DAMO-Academy/OmniCT-3B
Image-Text-to-Text • 3B • Updated • 18 • 2 -
Alibaba-DAMO-Academy/OmniCT-7B
Image-Text-to-Text • 8B • Updated • 23 • 4 -
lintw/MedEval-CT
Preview • Updated • 27 • 4 -
OmniCT: Towards a Unified Slice-Volume LVLM for Comprehensive CT Analysis
Paper • 2602.16110 • Published • 4
Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning
-
lingshu-medical-mllm/Lingshu-7B
Image-Text-to-Text • 8B • Updated • 145k • 78 -
lingshu-medical-mllm/Lingshu-I-8B
Image-Text-to-Text • 8B • Updated • 2.15k • 7 -
lingshu-medical-mllm/Lingshu-32B
Image-Text-to-Text • 33B • Updated • 1.66k • • 80 -
Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning
Paper • 2506.07044 • Published • 114
-
RynnBrain
📉10Query images or videos with visual and text prompts
-
Alibaba-DAMO-Academy/RynnBrain-2B
Image-Text-to-Text • 2B • Updated • 4.72k • 26 -
Alibaba-DAMO-Academy/RynnBrain-8B
Image-Text-to-Text • 9B • Updated • 409 • 12 -
Alibaba-DAMO-Academy/RynnBrain-30B-A3B
Image-Text-to-Text • 17B • Updated • 126 • 19
-
PixelRefer
🚀2Referring Any Pixel from Image and Video
-
PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary Granularity
Paper • 2510.23603 • Published • 26 -
Alibaba-DAMO-Academy/PixelRefer-2B
Video-Text-to-Text • Updated • 104 • 4 -
Alibaba-DAMO-Academy/PixelRefer-7B
Video-Text-to-Text • Updated • 26 • 4
Lumos Project: Frontier video generation research.
Using Human Demonstrations to Improve Robot Manipulation