Similar Items: Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models
- Driver-WM: A Driver-Centric Traffic-Conditioned Latent World Model for In-Cabin Dynamics Rollout
- EmambaIR: Efficient Visual State Space Model for Event-guided Image Reconstruction
- Continuous Latent Diffusion Language Model
- InpaintSLat: Inpainting Structured 3D Latents via Initial Noise Optimization
- LaST-R1: Reinforcing Action via Adaptive Physical Latent Reasoning for VLA Models
- OmniRobotHome: A Multi-Camera Platform for Real-Time Multiadic Human-Robot Interaction