Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models
Paper • 2603.17051 • Published • 109
Franklin PRO
Franklinzhang
AI & ML interests
None yet
Recent Activity
upvoted a paper about 13 hours ago
DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models upvoted a paper about 16 hours ago
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion TransformerOrganizations
authored a
paper about 2 months ago
submitted a
paper to Daily Papers about 2 months ago