Kewei Zhang

xiwenyoumu's activity

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

upvoted a paper 12 days ago

PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation

Paper • 2606.28128 • Published 15 days ago • 51

upvoted a paper 15 days ago

HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining

Paper • 2606.20521 • Published 23 days ago • 14

upvoted a paper about 1 month ago

Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Driving

Paper • 2605.23163 • Published May 25 • 17

upvoted 2 papers 2 months ago

HumanNet: Scaling Human-centric Video Learning to One Million Hours

Paper • 2605.06747 • Published May 7 • 55

Efficient Training on Multiple Consumer GPUs with RoundPipe

Paper • 2604.27085 • Published Apr 29 • 47

upvoted a paper 3 months ago

Generative World Renderer

Paper • 2604.02329 • Published Apr 2 • 103

upvoted a paper 4 months ago

Enhancing Spatial Understanding in Image Generation via Reward Modeling

Paper • 2602.24233 • Published Feb 27 • 60

upvoted 4 papers 6 months ago

Rethinking Video Generation Model for the Embodied World

Paper • 2601.15282 • Published Jan 21 • 46

Focal Guidance: Unlocking Controllability from Semantic-Weak Layers in Video Diffusion Models

Paper • 2601.07287 • Published Jan 12 • 6

MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head

Paper • 2601.07832 • Published Jan 12 • 53

MAGREF: Masked Guidance for Any-Reference Video Generation

Paper • 2505.23742 • Published May 29, 2025 • 11