Picture for Yihua Shao

Yihua Shao

MambaIC: State Space Models for High-Performance Learned Image Compression

Add code
Mar 16, 2025
Viaarxiv icon

WonderVerse: Extendable 3D Scene Generation with Video Generative Models

Add code
Mar 13, 2025
Viaarxiv icon

GM-MoE: Low-Light Enhancement with Gated-Mechanism Mixture-of-Experts

Add code
Mar 10, 2025
Viaarxiv icon

TR-DQ: Time-Rotation Diffusion Quantization

Add code
Mar 09, 2025
Viaarxiv icon

In-Context Meta LoRA Generation

Add code
Jan 30, 2025
Figure 1 for In-Context Meta LoRA Generation
Figure 2 for In-Context Meta LoRA Generation
Figure 3 for In-Context Meta LoRA Generation
Figure 4 for In-Context Meta LoRA Generation
Viaarxiv icon

3DSceneEditor: Controllable 3D Scene Editing with Gaussian Splatting

Add code
Dec 02, 2024
Figure 1 for 3DSceneEditor: Controllable 3D Scene Editing with Gaussian Splatting
Figure 2 for 3DSceneEditor: Controllable 3D Scene Editing with Gaussian Splatting
Figure 3 for 3DSceneEditor: Controllable 3D Scene Editing with Gaussian Splatting
Figure 4 for 3DSceneEditor: Controllable 3D Scene Editing with Gaussian Splatting
Viaarxiv icon

GWQ: Gradient-Aware Weight Quantization for Large Language Models

Add code
Oct 30, 2024
Figure 1 for GWQ: Gradient-Aware Weight Quantization for Large Language Models
Figure 2 for GWQ: Gradient-Aware Weight Quantization for Large Language Models
Figure 3 for GWQ: Gradient-Aware Weight Quantization for Large Language Models
Figure 4 for GWQ: Gradient-Aware Weight Quantization for Large Language Models
Viaarxiv icon

RenderWorld: World Model with Self-Supervised 3D Label

Add code
Sep 17, 2024
Figure 1 for RenderWorld: World Model with Self-Supervised 3D Label
Figure 2 for RenderWorld: World Model with Self-Supervised 3D Label
Figure 3 for RenderWorld: World Model with Self-Supervised 3D Label
Figure 4 for RenderWorld: World Model with Self-Supervised 3D Label
Viaarxiv icon

AccidentBlip2: Accident Detection With Multi-View MotionBlip2

Add code
Apr 19, 2024
Viaarxiv icon