Shi, Zhenmei

40 publications

ICLR 2025 Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix Yingyu Liang, Jiangxuan Long, Zhenmei Shi, Zhao Song, Yufa Zhou

AISTATS 2025 Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-Context by Multi-Step Gradient Descent Bo Chen, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song

CPAL 2025 Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Yekun Ke, Yingyu Liang, Zhenmei Shi, Zhao Song, Chiwun Yang

WACV 2025 Differential Privacy Mechanisms in Neural Tangent Kernel Regression Jiuxiang Gu, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song

ICML 2025 Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference Policies Yuefan Cao, Xiaoyu Li, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Jiahao Zhang

ICLRW 2025 Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference Policies Yuefan Cao, Xiaoyu Li, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Jiahao Zhang

ICLRW 2025 Fast Gradient Computation for RoPE Attention in Almost Linear Time Yifang Chen, Jiayan Huo, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song

CPAL 2025 Fast John Ellipsoid Computation with Differential Privacy Optimization Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song, Junwei Yu

AISTATS 2025 Fourier Circuits in Neural Networks and Transformers: A Case Study of Modular Arithmetic with Multiple Inputs Chenyang Li, Yingyu Liang, Zhenmei Shi, Zhao Song, Tianyi Zhou

ICML 2025 Fundamental Limits of Visual Autoregressive Transformers: Universal Approximation Abilities Yifang Chen, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song

CPAL 2025 HSR-Enhanced Sparse Attention Acceleration Bo Chen, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song

ICLRW 2025 High-Order Matching for One-Step Shortcut Diffusion Models Bo Chen, Chengyue Gong, Xiaoyu Li, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Mingda Wan

NeurIPS 2025 Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score Learning Dechen Zhang, Zhenmei Shi, Yi Zhang, Yingyu Liang, Difan Zou

AISTATS 2025 Looped ReLU MLPs May Be All You Need as Practical Programmable Computers Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Yufa Zhou

UAI 2025 NRFlow: Towards Noise-Robust Generative Modeling via High-Order Mechanism Bo Chen, Chengyue Gong, Xiaoyu Li, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Mingda Wan, Xugang Ye

ICLRW 2025 RichSpace: Enriching Text-to-Video Prompt Space via Text Embedding Interpolation Yuefan Cao, Chengyue Gong, Xiaoyu Li, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song

CPAL 2025 The Computational Limits of State-Space Models and Mamba via the Lens of Circuit Complexity Yifang Chen, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song

ICLRW 2025 Towards Infinite-Long Prefix in Transformers Yingyu Liang, Zhenmei Shi, Zhao Song, Chiwun Yang

ICCV 2025 Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Mingda Wan, Yufa Zhou

AISTATS 2025 When Can We Solve the Weighted Low Rank Approximation Problem in Truly Subquadratic Time? Chenyang Li, Yingyu Liang, Zhenmei Shi, Zhao Song

NeurIPSW 2024 A Tighter Complexity Analysis of SparseGPT Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song

NeurIPSW 2024 Differential Privacy of Cross-Attention with Provable Guarantee Yingyu Liang, Zhenmei Shi, Zhao Song, Yufa Zhou

ICLRW 2024 Do Large Language Models Have Compositional Ability? an Investigation into Limitations and Scalability Zhuoyan Xu, Zhenmei Shi, Yingyu Liang

CPAL 2024 Domain Generalization via Nuclear Norm Regularization Zhenmei Shi, Yifei Ming, Ying Fan, Frederic Sala, Yingyu Liang

NeurIPS 2024 Is a Picture Worth a Thousand Words? Delving into Spatial Reasoning for Vision Language Models Jiayu Wang, Yifei Ming, Zhenmei Shi, Vibhav Vineet, Xin Wang, Yixuan Li, Neel Joshi

NeurIPSW 2024 Multi-Layer Transformers Gradient Can Be Approximated in Almost Linear Time Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Yufa Zhou

NeurIPSW 2024 Tensor Attention Training: Provably Efficient Learning of Higher-Order Transformers Yingyu Liang, Zhenmei Shi, Zhao Song, Yufa Zhou

ICLR 2024 Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning Zhuoyan Xu, Zhenmei Shi, Junyi Wei, Fangzhou Mu, Yin Li, Yingyu Liang

ICML 2024 Why Larger Language Models Do In-Context Learning Differently? Zhenmei Shi, Junyi Wei, Zhuoyan Xu, Yingyu Liang

NeurIPS 2023 A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning Yiyou Sun, Zhenmei Shi, Yixuan Li

ICLRW 2023 Improving Foundation Models for Few-Shot Learning via Multitask Finetuning Zhuoyan Xu, Zhenmei Shi, Junyi Wei, Yin Li, Yingyu Liang

NeurIPS 2023 Provable Guarantees for Neural Networks via Gradient Feature Learning Zhenmei Shi, Junyi Wei, Yingyu Liang

ICLR 2023 The Trade-Off Between Universality and Label Efficiency of Representations from Contrastive Learning Zhenmei Shi, Jiefeng Chen, Kunyang Li, Jayaram Raghuram, Xi Wu, Yingyu Liang, Somesh Jha

ICML 2023 When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis Yiyou Sun, Zhenmei Shi, Yingyu Liang, Yixuan Li

NeurIPSW 2023 Why Larger Language Models Do In-Context Learning Differently? Zhenmei Shi, Junyi Wei, Zhuoyan Xu, Yingyu Liang

ICLR 2022 A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features Zhenmei Shi, Junyi Wei, Yingyu Liang

TMLR 2022 Attentive Walk-Aggregating Graph Neural Networks Mehmet F Demirel, Shengchao Liu, Siddhant Garg, Zhenmei Shi, Yingyu Liang

WACV 2022 Deep Online Fused Video Stabilization Zhenmei Shi, Fuhao Shi, Wei-Sheng Lai, Chia-Kai Liang, Yingyu Liang

NeurIPSW 2022 Domain Generalization with Nuclear Norm Regularization Zhenmei Shi, Yifei Ming, Ying Fan, Frederic Sala, Yingyu Liang

ICMLW 2022 The Trade-Off Between Label Efficiency and Universality of Representations from Contrastive Learning Zhenmei Shi, Jiefeng Chen, Kunyang Li, Jayaram Raghuram, Xi Wu, Yingyu Liang, Somesh Jha