Picture for Huan-ang Gao

Huan-ang Gao

FB-4D: Spatial-Temporal Coherent Dynamic 3D Content Generation with Feature Banks

Add code
Mar 26, 2025
Viaarxiv icon

PartRM: Modeling Part-Level Dynamics with Large Cross-State Reconstruction Model

Add code
Mar 25, 2025
Viaarxiv icon

MOAT: Evaluating LMMs for Capability Integration and Instruction Grounding

Add code
Mar 12, 2025
Viaarxiv icon

Afford-X: Generalizable and Slim Affordance Reasoning for Task-oriented Manipulation

Add code
Mar 05, 2025
Viaarxiv icon

Straight-Line Diffusion Model for Efficient 3D Molecular Generation

Add code
Mar 04, 2025
Viaarxiv icon

AVD2: Accident Video Diffusion for Accident Video Description

Add code
Feb 21, 2025
Viaarxiv icon

Diffusion-based Visual Anagram as Multi-task Learning

Add code
Dec 03, 2024
Figure 1 for Diffusion-based Visual Anagram as Multi-task Learning
Figure 2 for Diffusion-based Visual Anagram as Multi-task Learning
Figure 3 for Diffusion-based Visual Anagram as Multi-task Learning
Figure 4 for Diffusion-based Visual Anagram as Multi-task Learning
Viaarxiv icon

Dual-frame Fluid Motion Estimation with Test-time Optimization and Zero-divergence Loss

Add code
Oct 15, 2024
Viaarxiv icon

Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling

Add code
Oct 15, 2024
Figure 1 for Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling
Figure 2 for Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling
Figure 3 for Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling
Figure 4 for Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling
Viaarxiv icon

RGM: Reconstructing High-fidelity 3D Car Assets with Relightable 3D-GS Generative Model from a Single Image

Add code
Oct 10, 2024
Figure 1 for RGM: Reconstructing High-fidelity 3D Car Assets with Relightable 3D-GS Generative Model from a Single Image
Figure 2 for RGM: Reconstructing High-fidelity 3D Car Assets with Relightable 3D-GS Generative Model from a Single Image
Figure 3 for RGM: Reconstructing High-fidelity 3D Car Assets with Relightable 3D-GS Generative Model from a Single Image
Figure 4 for RGM: Reconstructing High-fidelity 3D Car Assets with Relightable 3D-GS Generative Model from a Single Image
Viaarxiv icon