Yuan Zhang

A Memory Efficient Randomized Subspace Optimization Method for Training Large Language Models

Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures

Generative Pre-trained Autoregressive Diffusion Transformer

Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads

Retraction-free optimization over the Stiefel manifold with application to the LoRA fine-tuning

Retraction-free optimization over the Stiefel manifold with application to the LoRA fine-tuning