Picture for Xiaoshui Huang

Xiaoshui Huang

Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B

Jun 11, 2024
Viaarxiv icon

Diverse Teacher-Students for Deep Safe Semi-Supervised Learning under Class Mismatch

Add code
May 25, 2024
Viaarxiv icon

3DBench: A Scalable 3D Benchmark and Instruction-Tuning Dataset

Apr 23, 2024
Viaarxiv icon

Taming Stable Diffusion for Text to 360° Panorama Image Generation

Add code
Apr 11, 2024
Viaarxiv icon

GVGEN: Text-to-3D Generation with Volumetric Representation

Add code
Mar 19, 2024
Figure 1 for GVGEN: Text-to-3D Generation with Volumetric Representation
Figure 2 for GVGEN: Text-to-3D Generation with Volumetric Representation
Figure 3 for GVGEN: Text-to-3D Generation with Volumetric Representation
Figure 4 for GVGEN: Text-to-3D Generation with Volumetric Representation
Viaarxiv icon

THOR: Text to Human-Object Interaction Diffusion via Relation Intervention

Mar 17, 2024
Figure 1 for THOR: Text to Human-Object Interaction Diffusion via Relation Intervention
Figure 2 for THOR: Text to Human-Object Interaction Diffusion via Relation Intervention
Figure 3 for THOR: Text to Human-Object Interaction Diffusion via Relation Intervention
Figure 4 for THOR: Text to Human-Object Interaction Diffusion via Relation Intervention
Viaarxiv icon

NeRF-Det++: Incorporating Semantic Cues and Perspective-aware Depth Supervision for Indoor Multi-View 3D Detection

Add code
Feb 22, 2024
Viaarxiv icon

A Comprehensive Survey on 3D Content Generation

Add code
Feb 02, 2024
Viaarxiv icon

3DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4V

Dec 15, 2023
Figure 1 for 3DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4V
Figure 2 for 3DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4V
Figure 3 for 3DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4V
Figure 4 for 3DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4V
Viaarxiv icon

UniDream: Unifying Diffusion Priors for Relightable Text-to-3D Generation

Add code
Dec 14, 2023
Viaarxiv icon