ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow
Paper • 2607.28362 • Published • 17
mjorah7
mjorah7
AI & ML interests
None yet
Recent Activity
upvoted a paper about 21 hours ago
β-OPSD: Deriving with Policy Optimization, Training with Self-Distillation upvoted a paper about 21 hours ago
Flux-OPD: On-Policy Distillation with Evolving ContextsOrganizations
None yet
upvoted 5
papers about 21 hours ago
β-OPSD: Deriving with Policy Optimization, Training with Self-Distillation
Paper • 2607.28582 • Published • 21
Flux-OPD: On-Policy Distillation with Evolving Contexts
Paper • 2607.28022 • Published • 41
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System
Paper • 2607.27380 • Published • 65
PhiZero: A World Model Built Around Physical Language
Paper • 2607.28624 • Published • 161
upvoted 5
papers 5 days ago
Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control
Paper • 2607.25337 • Published • 5
Parallel Decoding Distillation for Fast Image and Video Generation
Paper • 2607.26004 • Published • 14
Visual prompt engineering for video models
Paper • 2607.25537 • Published • 19
Wonder: Video World Model Done Better
Paper • 2607.26037 • Published • 19
Pass the Baton: Trajectory-Relayed On-Policy Distillation
Paper • 2607.26057 • Published • 32
upvoted 4
papers 6 days ago
Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling
Paper • 2607.23518 • Published • 8
Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification
Paper • 2607.24027 • Published • 35
Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation
Paper • 2607.24731 • Published • 75
Kimi K3: Open Frontier Intelligence
Paper • 2607.24653 • Published • 446
upvoted 5
papers 7 days ago
GraphVid: Interactive Graph-Controllable Video Generation
Paper • 2607.21580 • Published • 8
Multi-Turn On-Policy Distillation with Prefix Replay
Paper • 2607.04763 • Published • 12
SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation
Paper • 2607.21553 • Published • 39
Visual Contrastive Self-Distillation
Paper • 2607.21556 • Published • 51
Three-Body Scattering for Generative Modeling
Paper • 2607.18198 • Published • 16
upvoted a paper 8 days ago