Qing Qu

22

Papers

59

Total Citations

Papers (22)

Convolutional Phase Retrieval

NeurIPS 2017arXiv

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

Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling

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

The Emergence of Reproducibility and Consistency in Diffusion Models

A Global Geometric Analysis of Maximal Coding Rate Reduction

Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation

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

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

Generalized Neural Collapse for a Large Number of Classes

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

Symmetric Matrix Completion with ReLU Sampling

A Nonconvex Approach for Exact and Efficient Multichannel Sparse Blind Deconvolution

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

Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery

Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training

A Geometric Analysis of Neural Collapse with Unconstrained Features

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

Are All Losses Created Equal: A Neural Collapse Perspective

Complete Dictionary Recovery Using Nonconvex Optimization