Yuanze/Olympus
Image-Text-to-Text
•
Updated
•
48
•
3
yz
Yuanze
AI & ML interests
Multimodal large language models, diffusion models
Recent Activity
commented on
a paper
20 days ago
IllumiCraft: Unified Geometry and Illumination Diffusion for
Controllable Video Generation
commented on
a paper
20 days ago
IllumiCraft: Unified Geometry and Illumination Diffusion for
Controllable Video Generation
Organizations
None yet