Picture for Zixuan Huang

Zixuan Huang

PointInfinity: Resolution-Invariant Point Diffusion Models

Apr 04, 2024
Figure 1 for PointInfinity: Resolution-Invariant Point Diffusion Models
Figure 2 for PointInfinity: Resolution-Invariant Point Diffusion Models
Figure 3 for PointInfinity: Resolution-Invariant Point Diffusion Models
Figure 4 for PointInfinity: Resolution-Invariant Point Diffusion Models
Viaarxiv icon

Subgoal Diffuser: Coarse-to-fine Subgoal Generation to Guide Model Predictive Control for Robot Manipulation

Mar 19, 2024
Figure 1 for Subgoal Diffuser: Coarse-to-fine Subgoal Generation to Guide Model Predictive Control for Robot Manipulation
Figure 2 for Subgoal Diffuser: Coarse-to-fine Subgoal Generation to Guide Model Predictive Control for Robot Manipulation
Figure 3 for Subgoal Diffuser: Coarse-to-fine Subgoal Generation to Guide Model Predictive Control for Robot Manipulation
Figure 4 for Subgoal Diffuser: Coarse-to-fine Subgoal Generation to Guide Model Predictive Control for Robot Manipulation
Viaarxiv icon

TripoSR: Fast 3D Object Reconstruction from a Single Image

Add code
Mar 04, 2024
Figure 1 for TripoSR: Fast 3D Object Reconstruction from a Single Image
Figure 2 for TripoSR: Fast 3D Object Reconstruction from a Single Image
Figure 3 for TripoSR: Fast 3D Object Reconstruction from a Single Image
Figure 4 for TripoSR: Fast 3D Object Reconstruction from a Single Image
Viaarxiv icon

ZeroShape: Regression-based Zero-shot Shape Reconstruction

Add code
Jan 16, 2024
Figure 1 for ZeroShape: Regression-based Zero-shot Shape Reconstruction
Figure 2 for ZeroShape: Regression-based Zero-shot Shape Reconstruction
Figure 3 for ZeroShape: Regression-based Zero-shot Shape Reconstruction
Figure 4 for ZeroShape: Regression-based Zero-shot Shape Reconstruction
Viaarxiv icon

If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents

Add code
Jan 08, 2024
Viaarxiv icon

Low-shot Object Learning with Mutual Exclusivity Bias

Add code
Dec 06, 2023
Viaarxiv icon

FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback

Add code
Jul 20, 2023
Figure 1 for FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback
Figure 2 for FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback
Figure 3 for FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback
Figure 4 for FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback
Viaarxiv icon

ShapeClipper: Scalable 3D Shape Learning from Single-View Images via Geometric and CLIP-based Consistency

Apr 13, 2023
Figure 1 for ShapeClipper: Scalable 3D Shape Learning from Single-View Images via Geometric and CLIP-based Consistency
Figure 2 for ShapeClipper: Scalable 3D Shape Learning from Single-View Images via Geometric and CLIP-based Consistency
Figure 3 for ShapeClipper: Scalable 3D Shape Learning from Single-View Images via Geometric and CLIP-based Consistency
Figure 4 for ShapeClipper: Scalable 3D Shape Learning from Single-View Images via Geometric and CLIP-based Consistency
Viaarxiv icon

Self-supervised Cloth Reconstruction via Action-conditioned Cloth Tracking

Feb 19, 2023
Figure 1 for Self-supervised Cloth Reconstruction via Action-conditioned Cloth Tracking
Figure 2 for Self-supervised Cloth Reconstruction via Action-conditioned Cloth Tracking
Figure 3 for Self-supervised Cloth Reconstruction via Action-conditioned Cloth Tracking
Figure 4 for Self-supervised Cloth Reconstruction via Action-conditioned Cloth Tracking
Viaarxiv icon

Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization

Add code
Nov 28, 2022
Figure 1 for Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization
Figure 2 for Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization
Figure 3 for Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization
Figure 4 for Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization
Viaarxiv icon