Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models
Paper • 2603.17051 • Published • 95
Hyperflux
HYPRFLX
AI & ML interests
-Research Engineering (Google DeepMind, NVIDIA)
-AI/MLOps Infrastructure Engineering
-Data Solutions Architecture
Recent Activity
updated a collection 3 days ago
Research Papers/Reviews/LiteratureOrganizations
None yet
upvoted a paper 2 days ago
updated a
collection 3 days ago
upvoted 3
papers 4 days ago
Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation
Paper • 2603.19220 • Published • 58
SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing
Paper • 2603.19228 • Published • 64
Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding
Paper • 2603.19235 • Published • 90
upvoted a collection 4 days ago
liked a
model 4 days ago
liked a
dataset 5 days ago
liked a
model 5 days ago
upvoted 11
collections 23 days ago