Lei Wu
11
Papers
25
Total Citations
Papers (11)
BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices
CVPR 2025
20
citations
SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsity
CVPR 2025
3
citations
A duality framework for analyzing random feature and two-layer neural networks
NeurIPS 2025
2
citations
SOM: Semantic Obviousness Metric for Image Quality Assessment
CVPR 2015
0
citations
Why Do You Grok? A Theoretical Analysis on Grokking Modular Addition
ICML 2024
0
citations
Achieving Margin Maximization Exponentially Fast via Progressive Norm Rescaling
ICML 2024
0
citations
How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective
NeurIPS 2018
0
citations
Global Convergence of Gradient Descent for Deep Linear Residual Networks
NeurIPS 2019
0
citations
The alignment property of SGD noise and how it helps select flat minima: A stability analysis
NeurIPS 2022
0
citations
Theoretical Analysis of the Inductive Biases in Deep Convolutional Networks
NeurIPS 2023
0
citations
The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects
ICML 2019
0
citations