ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Fanghui Liu

Fanghui Liu

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 14, 2026, 7:08 PM AMS

13

papers

132

total citations

papers (13)

Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)

NEURIPS 2022arXiv

Generalization Properties of NAS under Activation and Skip Connection Search

NEURIPS 2022arXiv

Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks

NEURIPS 2023arXiv

Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study

NEURIPS 2022arXiv

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently

On the Convergence of Encoder-only Shallow Transformers

NEURIPS 2023arXiv

On the Double Descent of Random Features Models Trained with SGD

NEURIPS 2022arXiv

Sound and Complete Verification of Polynomial Networks

NEURIPS 2022arXiv

Revisiting Character-level Adversarial Attacks for Language Models

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Understanding Deep Neural Function Approximation in Reinforcement Learning via $\epsilon$-Greedy Exploration

The $\varphi$ Curve: The Shape of Generalization through the Lens of Norm-based Capacity Control

NEURIPS 2025arXiv