Picture for Zhiling Ye

Zhiling Ye

EDiT: A Local-SGD-Based Efficient Distributed Training Method for Large Language Models

Add code
Dec 10, 2024
Viaarxiv icon

R2-Talker: Realistic Real-Time Talking Head Synthesis with Hash Grid Landmarks Encoding and Progressive Multilayer Conditioning

Add code
Dec 09, 2023
Figure 1 for R2-Talker: Realistic Real-Time Talking Head Synthesis with Hash Grid Landmarks Encoding and Progressive Multilayer Conditioning
Figure 2 for R2-Talker: Realistic Real-Time Talking Head Synthesis with Hash Grid Landmarks Encoding and Progressive Multilayer Conditioning
Figure 3 for R2-Talker: Realistic Real-Time Talking Head Synthesis with Hash Grid Landmarks Encoding and Progressive Multilayer Conditioning
Figure 4 for R2-Talker: Realistic Real-Time Talking Head Synthesis with Hash Grid Landmarks Encoding and Progressive Multilayer Conditioning
Viaarxiv icon

AGD: an Auto-switchable Optimizer using Stepwise Gradient Difference for Preconditioning Matrix

Add code
Dec 04, 2023
Viaarxiv icon

Sharpness-Aware Minimization Revisited: Weighted Sharpness as a Regularization Term

Add code
May 25, 2023
Viaarxiv icon

MFAGAN: A Compression Framework for Memory-Efficient On-Device Super-Resolution GAN

Add code
Jul 27, 2021
Figure 1 for MFAGAN: A Compression Framework for Memory-Efficient On-Device Super-Resolution GAN
Figure 2 for MFAGAN: A Compression Framework for Memory-Efficient On-Device Super-Resolution GAN
Figure 3 for MFAGAN: A Compression Framework for Memory-Efficient On-Device Super-Resolution GAN
Figure 4 for MFAGAN: A Compression Framework for Memory-Efficient On-Device Super-Resolution GAN
Viaarxiv icon