Lei Wu

5

Papers

25

Total Citations

Papers (5)

BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices

SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity

A duality framework for analyzing random feature and two-layer neural networks

Why Do You Grok? A Theoretical Analysis on Grokking Modular Addition

Achieving Margin Maximization Exponentially Fast via Progressive Norm Rescaling