Picture for Siyu Zhu

Siyu Zhu

Efficient AI in Practice: Training and Deployment of Efficient LLMs for Industry Applications

Add code
Feb 20, 2025
Viaarxiv icon

Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors

Add code
Feb 11, 2025
Viaarxiv icon

MCMat: Multiview-Consistent and Physically Accurate PBR Material Generation

Add code
Dec 18, 2024
Figure 1 for MCMat: Multiview-Consistent and Physically Accurate PBR Material Generation
Figure 2 for MCMat: Multiview-Consistent and Physically Accurate PBR Material Generation
Figure 3 for MCMat: Multiview-Consistent and Physically Accurate PBR Material Generation
Figure 4 for MCMat: Multiview-Consistent and Physically Accurate PBR Material Generation
Viaarxiv icon

OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation

Add code
Dec 03, 2024
Figure 1 for OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation
Figure 2 for OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation
Figure 3 for OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation
Figure 4 for OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation
Viaarxiv icon

Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Diffusion Transformer Networks

Add code
Dec 01, 2024
Viaarxiv icon

Liger Kernel: Efficient Triton Kernels for LLM Training

Add code
Oct 14, 2024
Figure 1 for Liger Kernel: Efficient Triton Kernels for LLM Training
Figure 2 for Liger Kernel: Efficient Triton Kernels for LLM Training
Figure 3 for Liger Kernel: Efficient Triton Kernels for LLM Training
Figure 4 for Liger Kernel: Efficient Triton Kernels for LLM Training
Viaarxiv icon

Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation

Add code
Oct 10, 2024
Figure 1 for Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation
Figure 2 for Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation
Figure 3 for Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation
Figure 4 for Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation
Viaarxiv icon

Towards Native Generative Model for 3D Head Avatar

Add code
Oct 02, 2024
Figure 1 for Towards Native Generative Model for 3D Head Avatar
Figure 2 for Towards Native Generative Model for 3D Head Avatar
Figure 3 for Towards Native Generative Model for 3D Head Avatar
Figure 4 for Towards Native Generative Model for 3D Head Avatar
Viaarxiv icon

Dynamic PDB: A New Dataset and a SE(3) Model Extension by Integrating Dynamic Behaviors and Physical Properties in Protein Structures

Add code
Aug 22, 2024
Figure 1 for Dynamic PDB: A New Dataset and a SE(3) Model Extension by Integrating Dynamic Behaviors and Physical Properties in Protein Structures
Figure 2 for Dynamic PDB: A New Dataset and a SE(3) Model Extension by Integrating Dynamic Behaviors and Physical Properties in Protein Structures
Figure 3 for Dynamic PDB: A New Dataset and a SE(3) Model Extension by Integrating Dynamic Behaviors and Physical Properties in Protein Structures
Figure 4 for Dynamic PDB: A New Dataset and a SE(3) Model Extension by Integrating Dynamic Behaviors and Physical Properties in Protein Structures
Viaarxiv icon

4D Diffusion for Dynamic Protein Structure Prediction with Reference Guided Motion Alignment

Add code
Aug 22, 2024
Figure 1 for 4D Diffusion for Dynamic Protein Structure Prediction with Reference Guided Motion Alignment
Figure 2 for 4D Diffusion for Dynamic Protein Structure Prediction with Reference Guided Motion Alignment
Figure 3 for 4D Diffusion for Dynamic Protein Structure Prediction with Reference Guided Motion Alignment
Figure 4 for 4D Diffusion for Dynamic Protein Structure Prediction with Reference Guided Motion Alignment
Viaarxiv icon