Yuxing Han

AvatarSync: Rethinking Talking-Head Animation through Phoneme-Guided Autoregressive Perspective

Gradient-Constrained Training for Distributed Large Language Models

ALS-LoRA: Improved Low-Rank Matrix Compesation Method for Low Bit Quantization

BackSlash: Rate Constrained Optimized Training of Large Language Models

Disentangling data distribution for Federated Learning