Video Generation Models are General-Purpose Vision Learners
Paper • 2607.09024 • Published • 85
RF Liang
nexuslrf
AI & ML interests
None yet
Recent Activity
upvoted a paper 17 days ago
Video Generation Models are General-Purpose Vision Learners upvoted a paper about 1 month ago
FlowBender: Feedback-Aware Training for Self-Correcting Conditional Flows updated a model 4 months ago
nexuslrf/LuxDiTOrganizations
None yet