Yiming Dong

4 papers Peking University

• AdaMSS: Adaptive Multi-Subspace Approach for Parameter-Efficient Fine-Tuning
• Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads
• On the $O(\frac{\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\ell_1$ Norm
• Stepsize anything: A unified learning rate schedule for budgeted-iteration training