Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion
Paper
• 2603.06577 • Published
• 37
zyzhang
zzygetready
AI & ML interests
None yet
Recent Activity
upvoted a paper about 23 hours ago
Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion upvoted a paper 3 months ago
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length upvoted a paper 4 months ago
VITA-E: Natural Embodied Interaction with Concurrent Seeing, Hearing,
Speaking, and Acting Organizations
None yet