Mask$^2$DiT: Dual Mask-based Diffusion Transformer for Multi-Scene Long Video Generation
Paper • 2503.19881 • Published • 6 •
2
Tianhao Qi
qth
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild upvoted a paper 3 days ago
LibraGen: Playing a Balance Game in Subject-Driven Video Generation upvoted a paper 3 months ago
DreaMontage: Arbitrary Frame-Guided One-Shot Video GenerationOrganizations
None yet
commented a
paper 12 months ago