Qing Qu

papers

796

total citations

papers (22)

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

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

Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation

ICML 2024arXiv

citations

SITCOM: Step-wise Triple-Consistent Diffusion Sampling For Inverse Problems

ICML 2025arXiv

citations

Neural Collapse in Multi-label Learning with Pick-all-label Loss

ICML 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

Optimal Eye Surgeon: Finding image priors through sparse generators at initialization

ICML 2024arXiv

citations

FlowDAS: A Stochastic Interpolant-based Framework for Data Assimilation

NEURIPS 2025arXiv

citations

Symmetric Matrix Completion with ReLU Sampling

ICML 2024arXiv

citations

Attention-Only Transformers via Unrolled Subspace Denoising

ICML 2025arXiv

citations

A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective

NEURIPS 2025arXiv

citations

Shallow Diffuse: Robust and Invisible Watermarking through Low-Dim Subspaces in Diffusion Models

NEURIPS 2025

citations

UGoDIT: Unsupervised Group Deep Image Prior Via Transferable Weights

NEURIPS 2025arXiv

citations

Improving Training Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architecture

CVPR 2024

citations

The Emergence of Reproducibility and Consistency in Diffusion Models

ICML 2024

citations

Qing Qu

papers (22)

A Geometric Analysis of Neural Collapse with Unconstrained Features

Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency

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

Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery

Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training

Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation

SITCOM: Step-wise Triple-Consistent Diffusion Sampling For Inverse Problems

Neural Collapse in Multi-label Learning with Pick-all-label Loss

A Global Geometric Analysis of Maximal Coding Rate Reduction

Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling

Optimal Eye Surgeon: Finding image priors through sparse generators at initialization

FlowDAS: A Stochastic Interpolant-based Framework for Data Assimilation

Symmetric Matrix Completion with ReLU Sampling

Attention-Only Transformers via Unrolled Subspace Denoising

A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective

Shallow Diffuse: Robust and Invisible Watermarking through Low-Dim Subspaces in Diffusion Models

UGoDIT: Unsupervised Group Deep Image Prior Via Transferable Weights

Improving Training Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architecture

The Emergence of Reproducibility and Consistency in Diffusion Models

papers (22)

A Geometric Analysis of Neural Collapse with Unconstrained Features

Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency

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

Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery

Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training

Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation

SITCOM: Step-wise Triple-Consistent Diffusion Sampling For Inverse Problems

Neural Collapse in Multi-label Learning with Pick-all-label Loss

A Global Geometric Analysis of Maximal Coding Rate Reduction

Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling

Optimal Eye Surgeon: Finding image priors through sparse generators at initialization

FlowDAS: A Stochastic Interpolant-based Framework for Data Assimilation

Symmetric Matrix Completion with ReLU Sampling

Attention-Only Transformers via Unrolled Subspace Denoising

A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective

Shallow Diffuse: Robust and Invisible Watermarking through Low-Dim Subspaces in Diffusion Models

UGoDIT: Unsupervised Group Deep Image Prior Via Transferable Weights

Improving Training Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architecture

The Emergence of Reproducibility and Consistency in Diffusion Models