mjorah7

mjorah7's activity

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

upvoted 3 papers about 6 hours ago

How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks

Paper • 2608.14905 • Published 6 days ago • 26

An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models

Paper • 2608.16887 • Published 3 days ago • 29

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

Paper • 2608.16072 • Published 3 days ago • 125

upvoted 2 papers 1 day ago

Latent On-Policy Self-Distillation

Paper • 2608.13040 • Published 7 days ago • 21

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published 6 days ago • 161

upvoted a paper 2 days ago

Alaya-EVOKE: From Linear-Scaling Supervision to Endless World

Paper • 2608.13546 • Published 7 days ago • 129

upvoted a paper 5 days ago

Learning How the World Evolves: Extrapolative Video World Models via Latent Dynamics Reasoning

Paper • 2608.09926 • Published 10 days ago • 11

upvoted 4 papers 6 days ago

Addressable Memory for Video World Models

Paper • 2608.07408 • Published 13 days ago • 14

MirrorWorld: Taming Video Diffusion Models for Mirror Reflection Generation

Paper • 2608.07463 • Published 13 days ago • 6

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published 11 days ago • 212

Beyond Pixels: From Video Priors to 4D Worlds

Paper • 2608.10744 • Published 9 days ago • 179

upvoted 4 papers 12 days ago

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

Paper • 2608.04349 • Published 15 days ago • 12

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

Paper • 2608.04964 • Published 15 days ago • 13

HelloWorld: Enabling Socially Interactive Characters in Video World Models

Paper • 2608.05070 • Published 15 days ago • 40

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

Paper • 2608.03632 • Published 16 days ago • 23

upvoted 5 papers 13 days ago

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

Paper • 2607.29122 • Published 20 days ago • 5

DAPD: Dual-Anchored Policy Distillation

Paper • 2608.01735 • Published 17 days ago • 149

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

Paper • 2608.03316 • Published 16 days ago • 26

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

Paper • 2608.03457 • Published 16 days ago • 32

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

Paper • 2608.03974 • Published 16 days ago • 97