Zhihui Zhu

papers

839

total citations

papers (17)

Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold

NEURIPS 2022arXiv

citations

Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization

NEURIPS 2020arXiv

citations

Generalized Neural Collapse for a Large Number of Classes

ICML 2024arXiv

citations

Revisiting Sparse Convolutional Model for Visual Recognition

NEURIPS 2022arXiv

citations

Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery

NEURIPS 2021arXiv

citations

Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training

NEURIPS 2021arXiv

citations

Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity

ICLR 2025arXiv

citations

Error Analysis of Tensor-Train Cross Approximation

NEURIPS 2022arXiv

citations

DREAM: Diffusion Rectification and Estimation-Adaptive Models

CVPR 2024arXiv

citations

A Global Geometric Analysis of Maximal Coding Rate Reduction

ICML 2024arXiv

citations

Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling

NEURIPS 2025arXiv

citations

Robust Homography Estimation via Dual Principal Component Pursuit

CVPR 2020

citations

The Distributional Reward Critic Framework for Reinforcement Learning Under Perturbed Rewards

AAAI 2025arXiv

citations

Zhihui Zhu

papers (17)

A Geometric Analysis of Neural Collapse with Unconstrained Features

Only Train Once: A One-Shot Neural Network Training And Pruning Framework

CDFI: Compression-Driven Network Design for Frame Interpolation

Are All Losses Created Equal: A Neural Collapse Perspective

Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold

Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization

Generalized Neural Collapse for a Large Number of Classes

Revisiting Sparse Convolutional Model for Visual Recognition

Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery

Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training

Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity

Error Analysis of Tensor-Train Cross Approximation

DREAM: Diffusion Rectification and Estimation-Adaptive Models

A Global Geometric Analysis of Maximal Coding Rate Reduction

Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling

Robust Homography Estimation via Dual Principal Component Pursuit

The Distributional Reward Critic Framework for Reinforcement Learning Under Perturbed Rewards

papers (17)

A Geometric Analysis of Neural Collapse with Unconstrained Features

Only Train Once: A One-Shot Neural Network Training And Pruning Framework

CDFI: Compression-Driven Network Design for Frame Interpolation

Are All Losses Created Equal: A Neural Collapse Perspective

Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold

Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization

Generalized Neural Collapse for a Large Number of Classes

Revisiting Sparse Convolutional Model for Visual Recognition

Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery

Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training

Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity

Error Analysis of Tensor-Train Cross Approximation

DREAM: Diffusion Rectification and Estimation-Adaptive Models

A Global Geometric Analysis of Maximal Coding Rate Reduction

Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling

Robust Homography Estimation via Dual Principal Component Pursuit

The Distributional Reward Critic Framework for Reinforcement Learning Under Perturbed Rewards