mjorah7

mjorah7's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 4 papers 1 day ago

Poly-OPD: Heterogeneous Multi-Teacher On-Policy Distillation for Capability-Selectable Flow Models

Paper • 2608.04349 • Published 3 days ago • 10

WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models

Paper • 2608.04964 • Published 3 days ago • 11

HelloWorld: Enabling Socially Interactive Characters in Video World Models

Paper • 2608.05070 • Published 3 days ago • 18

When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation

Paper • 2608.03632 • Published 4 days ago • 21

upvoted 5 papers 2 days ago

A Frozen Pixel-Space Diffusion Model Can Guide Itself with Its Own Samples

Paper • 2607.29122 • Published 8 days ago • 4

DAPD: Dual-Anchored Policy Distillation

Paper • 2608.01735 • Published 5 days ago • 105

Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging

Paper • 2608.03316 • Published 4 days ago • 26

LLaDA MoE v2: Scaling Mixture-of-Experts Diffusion Language Models

Paper • 2608.03457 • Published 4 days ago • 30

JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion

Paper • 2608.03974 • Published 4 days ago • 87

upvoted 3 papers 4 days ago

SAF-OPD: Stable Advantage Fusion for On-Policy Distillation

Paper • 2607.29209 • Published 8 days ago • 34

Weak-to-Strong On-Policy Distillation

Paper • 2607.26246 • Published 11 days ago • 55

Mental World Modeling

Paper • 2607.27201 • Published 10 days ago • 103

upvoted 5 papers 5 days ago

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow

Paper • 2607.28362 • Published 9 days ago • 21

β-OPSD: Deriving with Policy Optimization, Training with Self-Distillation

Paper • 2607.28582 • Published 9 days ago • 23

Flux-OPD: On-Policy Distillation with Evolving Contexts

Paper • 2607.28022 • Published 9 days ago • 44

VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System

Paper • 2607.27380 • Published 10 days ago • 70

PhiZero: A World Model Built Around Physical Language

Paper • 2607.28624 • Published 9 days ago • 167

upvoted 3 papers 9 days ago

Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control

Paper • 2607.25337 • Published 11 days ago • 6

Parallel Decoding Distillation for Fast Image and Video Generation

Paper • 2607.26004 • Published 11 days ago • 16

Visual prompt engineering for video models

Paper • 2607.25537 • Published 11 days ago • 22