WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories Paper • 2603.02049 • Published 25 days ago • 17
Mode Seeking meets Mean Seeking for Fast Long Video Generation Paper • 2602.24289 • Published 28 days ago • 41
Enhancing Spatial Understanding in Image Generation via Reward Modeling Paper • 2602.24233 • Published 28 days ago • 58
Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance Scheduling Paper • 2602.21760 • Published about 1 month ago • 13
The Trinity of Consistency as a Defining Principle for General World Models Paper • 2602.23152 • Published 29 days ago • 200
tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction Paper • 2602.20160 • Published Feb 23 • 10
The Design Space of Tri-Modal Masked Diffusion Models Paper • 2602.21472 • Published about 1 month ago • 3
World Guidance: World Modeling in Condition Space for Action Generation Paper • 2602.22010 • Published 30 days ago • 14