WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories
Paper
• 2603.02049 • Published
• 17
Honglei Xu
SuperPsyduck
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
Mode Seeking meets Mean Seeking for Fast Long Video Generation upvoted a paper 1 day ago
Enhancing Spatial Understanding in Image Generation via Reward Modeling Organizations
None yet
upvoted 3 papers 1 day ago
upvoted 4 papers 12 days ago
GeoWorld: Geometric World Models
Paper
• 2602.23058 • Published
• 7
Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance Scheduling
Paper
• 2602.21760 • Published
• 13
The Trinity of Consistency as a Defining Principle for General World Models
Paper
• 2602.23152 • Published
• 196
tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction
Paper
• 2602.20160 • Published
• 10