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 2 days ago
Flow-OPD: On-Policy Distillation for Flow Matching Models upvoted a paper 2 days ago
Geometric Context Transformer for Streaming 3D ReconstructionOrganizations
authored a
paper about 2 months ago
submitted a
paper to Daily Papers about 2 months ago