Picture for Danfei Xu

Danfei Xu

What Matters in Learning from Large-Scale Datasets for Robot Manipulation

Add code
Jun 16, 2025
Viaarxiv icon

SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies

Add code
Jun 13, 2025
Viaarxiv icon

Learning Predictive Visuomotor Coordination

Add code
Mar 30, 2025
Viaarxiv icon

Generative Trajectory Stitching through Diffusion Composition

Add code
Mar 07, 2025
Figure 1 for Generative Trajectory Stitching through Diffusion Composition
Figure 2 for Generative Trajectory Stitching through Diffusion Composition
Figure 3 for Generative Trajectory Stitching through Diffusion Composition
Figure 4 for Generative Trajectory Stitching through Diffusion Composition
Viaarxiv icon

DreamDrive: Generative 4D Scene Modeling from Street View Images

Add code
Jan 03, 2025
Figure 1 for DreamDrive: Generative 4D Scene Modeling from Street View Images
Figure 2 for DreamDrive: Generative 4D Scene Modeling from Street View Images
Figure 3 for DreamDrive: Generative 4D Scene Modeling from Street View Images
Figure 4 for DreamDrive: Generative 4D Scene Modeling from Street View Images
Viaarxiv icon

STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes

Add code
Dec 31, 2024
Figure 1 for STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes
Figure 2 for STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes
Figure 3 for STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes
Figure 4 for STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes
Viaarxiv icon

LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models

Add code
Dec 10, 2024
Figure 1 for LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models
Figure 2 for LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models
Figure 3 for LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models
Figure 4 for LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models
Viaarxiv icon

EgoMimic: Scaling Imitation Learning via Egocentric Video

Add code
Oct 31, 2024
Viaarxiv icon

Large Spatial Model: End-to-end Unposed Images to Semantic 3D

Add code
Oct 24, 2024
Figure 1 for Large Spatial Model: End-to-end Unposed Images to Semantic 3D
Figure 2 for Large Spatial Model: End-to-end Unposed Images to Semantic 3D
Figure 3 for Large Spatial Model: End-to-end Unposed Images to Semantic 3D
Figure 4 for Large Spatial Model: End-to-end Unposed Images to Semantic 3D
Viaarxiv icon

Opt2Skill: Imitating Dynamically-feasible Whole-Body Trajectories for Versatile Humanoid Loco-Manipulation

Add code
Sep 30, 2024
Figure 1 for Opt2Skill: Imitating Dynamically-feasible Whole-Body Trajectories for Versatile Humanoid Loco-Manipulation
Figure 2 for Opt2Skill: Imitating Dynamically-feasible Whole-Body Trajectories for Versatile Humanoid Loco-Manipulation
Figure 3 for Opt2Skill: Imitating Dynamically-feasible Whole-Body Trajectories for Versatile Humanoid Loco-Manipulation
Figure 4 for Opt2Skill: Imitating Dynamically-feasible Whole-Body Trajectories for Versatile Humanoid Loco-Manipulation
Viaarxiv icon