Qing Qu

SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL CVPR 2026 Attention-Only Transformers via Unrolled Subspace Denoising ICML 2025 Learning Dynamics of Deep Matrix Factorization Beyond the Edge of Stability ICLR 2025 SITCOM: Step-wise Triple-Consistent Diffusion Sampling For Inverse Problems ICML 2025 Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination JMLR 2025 A Global Geometric Analysis of Maximal Coding Rate Reduction ICML 2024 BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference NeurIPS 2024 Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation ICML 2024 Efficient Low-Dimensional Compression of Overparameterized Models AISTATS 2024 Exploring Low-Dimensional Subspace in Diffusion Models for Controllable Image Editing NeurIPS 2024 Generalized Neural Collapse for a Large Number of Classes ICML 2024 Image Reconstruction Via Autoencoding Sequential Deep Image Prior NeurIPS 2024 Improving Training Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architecture CVPR 2024 Neural Collapse in Multi-label Learning with Pick-all-label Loss ICML 2024 Optimal Eye Surgeon: Finding image priors through sparse generators at initialization ICML 2024 Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency ICLR 2024 Symmetric Matrix Completion with ReLU Sampling ICML 2024 The Emergence of Reproducibility and Consistency in Diffusion Models ICML 2024 Understanding Generalizability of Diffusion Models Requires Rethinking the Hidden Gaussian Structure NeurIPS 2024 Are All Losses Created Equal: A Neural Collapse Perspective NeurIPS 2022 Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning EMNLP 2022 Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold NeurIPS 2022 On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features ICML 2022 Robust Training under Label Noise by Over-parameterization ICML 2022 A Geometric Analysis of Neural Collapse with Unconstrained Features NeurIPS 2021 Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training NeurIPS 2021 Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery NeurIPS 2021 Geometric Analysis of Nonconvex Optimization Landscapes for Overcomplete Learning ICLR 2020 Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization NeurIPS 2020 Short and Sparse Deconvolution --- A Geometric Approach ICLR 2020 A Nonconvex Approach for Exact and Efficient Multichannel Sparse Blind Deconvolution NeurIPS 2019 Convolutional Phase Retrieval NeurIPS 2017 Complete Dictionary Recovery Using Nonconvex Optimization ICML 2015 Finding a sparse vector in a subspace: Linear sparsity using alternating directions NeurIPS 2014