Picture for Tianke Zhang

Tianke Zhang

EVLM: An Efficient Vision-Language Model for Visual Understanding

Add code
Jul 19, 2024
Figure 1 for EVLM: An Efficient Vision-Language Model for Visual Understanding
Figure 2 for EVLM: An Efficient Vision-Language Model for Visual Understanding
Figure 3 for EVLM: An Efficient Vision-Language Model for Visual Understanding
Figure 4 for EVLM: An Efficient Vision-Language Model for Visual Understanding
Viaarxiv icon

TrainerAgent: Customizable and Efficient Model Training through LLM-Powered Multi-Agent System

Add code
Nov 23, 2023
Viaarxiv icon

Audio-Driven 3D Facial Animation from In-the-Wild Videos

Add code
Jun 20, 2023
Viaarxiv icon

From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels

Add code
Mar 23, 2023
Viaarxiv icon

HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Details

Add code
Mar 20, 2023
Viaarxiv icon

Rethinking Knowledge Distillation via Cross-Entropy

Add code
Aug 22, 2022
Figure 1 for Rethinking Knowledge Distillation via Cross-Entropy
Figure 2 for Rethinking Knowledge Distillation via Cross-Entropy
Figure 3 for Rethinking Knowledge Distillation via Cross-Entropy
Figure 4 for Rethinking Knowledge Distillation via Cross-Entropy
Viaarxiv icon