Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation
Paper
•
2504.02542
•
Published
•
51
•
9
Dan Xu
danxuhk
AI & ML interests
Computer Vision, Deep Learning, Multimedia
Recent Activity
upvoted
a
paper
15 days ago
Controllable Video Generation: A Survey
authored
a paper
about 2 months ago
N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models
upvoted
a
paper
about 2 months ago
N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models
Organizations
None yet
commented
a
paper
10 months ago