Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion
Paper
• 2603.06577 • Published
• 37
Qingyuan Cao
Franzzi
AI & ML interests
None yet
Recent Activity
upvoted a paper 4 months ago
VITA-E: Natural Embodied Interaction with Concurrent Seeing, Hearing,
Speaking, and Acting updated
a dataset almost 2 years ago
Franzzi/Guwen_try Organizations
None yet