← Authors

Zhihui Zhu

37 papers · 2018–2025 · 9 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (7) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (67) πŸƒ Academic Marathon (7) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (11) 🌍 Conference Polyglot (9) πŸ† Keyword Champion (4) 🀝 Dynamic Duo (13) πŸ† Grand Slam πŸ”¬ Deep Specialist (10) πŸ—ƒοΈ Keyword Collector (177) ⚑ Prolific Year (7) πŸ’Ž Century Club (37) πŸ”₯ Unstoppable (8) πŸ“ˆ Trend Setter

Conferences

NIPS (14) ICML (7) CVPR (3) ICLR (3) JMLR (3) AAAI (2) AACL (2) IJCNLP (2) AISTATS (1)

Top co-authors

Qing Qu (13) Tianyu Ding (10) Chong You (9) Xiao Li (8) Jinxin Zhou (6) RenΓ© Vidal (6) Hanwen Du (4) Luming Liang (4) Xinyi Ling (4) Xia Ning (4)

Keywords

non-convex optimization (4) dual principal component pursuit (4) riemannian optimization (4) gradient descent (4) neural collapse (4) feature learning (3) matrix factorization (3) outlier detection (3) multimodal learning (3) subspace learning (3) nonconvex optimization (3) dictionary learning (3) low-rank matrix recovery (2) model pruning (2) deep neural network (2) model compression (2) sparse recovery (2) label smoothing (2) representation learning (2) domain generalization (2)

Papers

Captions Speak Louder than Images: Generalizing Foundation Models for E-commerce from High-quality Multimodal Instruction Data IJCNLP 2025
The Distributional Reward Critic Framework for Reinforcement Learning Under Perturbed Rewards AAAI 2025
EcomMMMU: Strategic Utilization of Visuals for Robust Multimodal E-commerce Models IJCNLP 2025
EcomMMMU: Strategic Utilization of Visuals for Robust Multimodal E-commerce Models AACL 2025
Captions Speak Louder than Images: Generalizing Foundation Models for E-commerce from High-quality Multimodal Instruction Data AACL 2025
Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity ICLR 2025
Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination JMLR 2025
Generalized Neural Collapse for a Large Number of Classes ICML 2024
DREAM: Diffusion Rectification and Estimation-Adaptive Models CVPR 2024
Guaranteed Nonconvex Factorization Approach for Tensor Train Recovery JMLR 2024
A Global Geometric Analysis of Maximal Coding Rate Reduction ICML 2024
OTOv2: Automatic, Generic, User-Friendly ICLR 2023
Error Analysis of Tensor-Train Cross Approximation NIPS 2022
Are All Losses Created Equal: A Neural Collapse Perspective NIPS 2022
On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features ICML 2022
Recovery and Generalization in Over-Realized Dictionary Learning JMLR 2022
Robust Training under Label Noise by Over-parameterization ICML 2022
Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold NIPS 2022
Revisiting Sparse Convolutional Model for Visual Recognition NIPS 2022
Dual Principal Component Pursuit for Learning a Union of Hyperplanes: Theory and Algorithms AISTATS 2021
Only Train Once: A One-Shot Neural Network Training And Pruning Framework NIPS 2021
Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery NIPS 2021
Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training NIPS 2021
A Geometric Analysis of Neural Collapse with Unconstrained Features NIPS 2021
CDFI: Compression-Driven Network Design for Frame Interpolation CVPR 2021
Dual Principal Component Pursuit for Robust Subspace Learning: Theory and Algorithms for a Holistic Approach ICML 2021
Viewpoint-Aware Loss with Angular Regularization for Person Re-Identification AAAI 2020
Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization NIPS 2020
Geometric Analysis of Nonconvex Optimization Landscapes for Overcomplete Learning ICLR 2020
Robust Homography Estimation via Dual Principal Component Pursuit CVPR 2020
Noisy Dual Principal Component Pursuit ICML 2019
A Nonconvex Approach for Exact and Efficient Multichannel Sparse Blind Deconvolution NIPS 2019
Alternating Minimizations Converge to Second-Order Optimal Solutions ICML 2019
A Linearly Convergent Method for Non-Smooth Non-Convex Optimization on the Grassmannian with Applications to Robust Subspace and Dictionary Learning NIPS 2019
Distributed Low-rank Matrix Factorization With Exact Consensus NIPS 2019
Dual Principal Component Pursuit: Improved Analysis and Efficient Algorithms NIPS 2018
Dropping Symmetry for Fast Symmetric Nonnegative Matrix Factorization NIPS 2018