Generative
- Artemis: Geometry-Grounded Multi-Agent Driving World Models with Shared 3D State and Progressive Memory Update
- LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference
- Neural-MMGS: Multi-modal Neural Gaussian Splats for Large-Scale Scene Reconstruction
- NeuralFloors++: Consistent Street-Level Scene Generation From BEV Semantic Maps
- NeRFoot: Robot-Footprint Estimation for Image-Based Visual Servoing
- NeuralFloors: Conditional Street-Level Scene Generation From BEV Semantic Maps via Neural Fields
- Depth-SIMS: Semi-Parametric Image and Depth Synthesis