arxiv:2606.30292
๐ In a Training Loop
Daniel
dnlayu
ยท
AI & ML interests
Interactive World Models, Video Diffusion, Inference and Training Optimization
Recent Activity
upvoted a paper about 4 hours ago
Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling upvoted a paper about 4 hours ago
WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory authored a paper 3 days ago
DreamForge-World 0.1 Preview: A Low-Compute Real-Time Controllable World Model