default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDZhenmei Shi
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2025
[i39]Yekun Ke, Xiaoyu Li, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song:
On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis. CoRR abs/2501.04377 (2025)- [i38]Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song, Wei Wang, Jiahao Zhang:
On the Computational Capability of Graph Neural Networks: A Circuit Complexity Bound Perspective. CoRR abs/2501.06444 (2025) - 2024
- [c9]Zhuoyan Xu, Zhenmei Shi, Junyi Wei, Fangzhou Mu, Yin Li, Yingyu Liang:
Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning. ICLR 2024 - [c8]Zhenmei Shi, Junyi Wei, Zhuoyan Xu, Yingyu Liang:
Why Larger Language Models Do In-context Learning Differently? ICML 2024 - [c7]Jiayu Wang, Yifei Ming, Zhenmei Shi, Vibhav Vineet, Xin Wang, Sharon Li, Neel Joshi:
Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models. NeurIPS 2024 - [i37]Jiuxiang Gu, Chenyang Li, Yingyu Liang, Zhenmei Shi, Zhao Song, Tianyi Zhou:
Fourier Circuits in Neural Networks: Unlocking the Potential of Large Language Models in Mathematical Reasoning and Modular Arithmetic. CoRR abs/2402.09469 (2024) - [i36]Zhuoyan Xu, Zhenmei Shi, Junyi Wei, Fangzhou Mu, Yin Li, Yingyu Liang:
Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning. CoRR abs/2402.15017 (2024) - [i35]Jiuxiang Gu, Chenyang Li, Yingyu Liang, Zhenmei Shi, Zhao Song:
Exploring the Frontiers of Softmax: Provable Optimization, Applications in Diffusion Model, and Beyond. CoRR abs/2405.03251 (2024) - [i34]Jiuxiang Gu, Yingyu Liang, Heshan Liu, Zhenmei Shi, Zhao Song, Junze Yin:
Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers. CoRR abs/2405.05219 (2024) - [i33]Jiuxiang Gu, Yingyu Liang, Zhenmei Shi, Zhao Song, Yufa Zhou:
Tensor Attention Training: Provably Efficient Learning of Higher-order Transformers. CoRR abs/2405.16411 (2024) - [i32]Jiuxiang Gu, Yingyu Liang, Zhenmei Shi, Zhao Song, Yufa Zhou:
Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective. CoRR abs/2405.16418 (2024) - [i31]Zhenmei Shi, Junyi Wei, Zhuoyan Xu, Yingyu Liang:
Why Larger Language Models Do In-context Learning Differently? CoRR abs/2405.19592 (2024) - [i30]Jiuxiang Gu, Yingyu Liang, Zhenmei Shi, Zhao Song, Chiwun Yang:
Toward Infinite-Long Prefix in Transformer. CoRR abs/2406.14036 (2024) - [i29]Jiayu Wang, Yifei Ming, Zhenmei Shi, Vibhav Vineet, Xin Wang, Neel Joshi:
Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models. CoRR abs/2406.14852 (2024) - [i28]Jiuxiang Gu, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song:
Differential Privacy Mechanisms in Neural Tangent Kernel Regression. CoRR abs/2407.13621 (2024) - [i27]Jiuxiang Gu, Yingyu Liang, Zhenmei Shi, Zhao Song, Yufa Zhou:
Differential Privacy of Cross-Attention with Provable Guarantee. CoRR abs/2407.14717 (2024) - [i26]Zhuoyan Xu, Zhenmei Shi, Yingyu Liang:
Do Large Language Models Have Compositional Ability? An Investigation into Limitations and Scalability. CoRR abs/2407.15720 (2024) - [i25]Jiuxiang Gu, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song, Junwei Yu:
Fast John Ellipsoid Computation with Differential Privacy Optimization. CoRR abs/2408.06395 (2024) - [i24]Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song:
A Tighter Complexity Analysis of SparseGPT. CoRR abs/2408.12151 (2024) - [i23]Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Yufa Zhou:
Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time. CoRR abs/2408.13233 (2024) - [i22]Zhenmei Shi, Yifei Ming, Xuan-Phi Nguyen, Yingyu Liang, Shafiq Joty:
Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction. CoRR abs/2409.17422 (2024) - [i21]Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Yufa Zhou:
Looped ReLU MLPs May Be All You Need as Practical Programmable Computers. CoRR abs/2410.09375 (2024) - [i20]Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song, Yufa Zhou:
Fine-grained Attention I/O Complexity: Comprehensive Analysis for Backward Passes. CoRR abs/2410.09397 (2024) - [i19]Bo Chen, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song:
HSR-Enhanced Sparse Attention Acceleration. CoRR abs/2410.10165 (2024) - [i18]Yingyu Liang, Jiangxuan Long, Zhenmei Shi, Zhao Song, Yufa Zhou:
Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix. CoRR abs/2410.11261 (2024) - [i17]Bo Chen, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song:
Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent. CoRR abs/2410.11268 (2024) - [i16]Yekun Ke, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song:
Advancing the Understanding of Fixed Point Iterations in Deep Neural Networks: A Detailed Analytical Study. CoRR abs/2410.11279 (2024) - [i15]Bo Chen, Xiaoyu Li, Yingyu Liang, Jiangxuan Long, Zhenmei Shi, Zhao Song:
Circuit Complexity Bounds for RoPE-based Transformer Architecture. CoRR abs/2411.07602 (2024) - [i14]Xiaoyu Li, Yuanpeng Li, Yingyu Liang, Zhenmei Shi, Zhao Song:
On the Expressive Power of Modern Hopfield Networks. CoRR abs/2412.05562 (2024) - [i13]Yekun Ke, Yingyu Liang, Zhenmei Shi, Zhao Song, Chiwun Yang:
Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond. CoRR abs/2412.06061 (2024) - [i12]Yifang Chen, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song:
The Computational Limits of State-Space Models and Mamba via the Lens of Circuit Complexity. CoRR abs/2412.06148 (2024) - [i11]Yifang Chen, Jiayan Huo, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song:
Fast Gradient Computation for RoPE Attention in Almost Linear Time. CoRR abs/2412.17316 (2024) - [i10]Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song, Mingda Wan:
Theoretical Constraints on the Expressive Power of RoPE-based Tensor Attention Transformers. CoRR abs/2412.18040 (2024) - 2023
- [c6]Zhenmei Shi, Jiefeng Chen, Kunyang Li, Jayaram Raghuram, Xi Wu, Yingyu Liang, Somesh Jha:
The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning. ICLR 2023 - [c5]Yiyou Sun, Zhenmei Shi, Yingyu Liang, Yixuan Li:
When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis. ICML 2023: 33014-33043 - [c4]Zhenmei Shi, Junyi Wei, Yingyu Liang:
Provable Guarantees for Neural Networks via Gradient Feature Learning. NeurIPS 2023 - [c3]Yiyou Sun, Zhenmei Shi, Yixuan Li:
A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning. NeurIPS 2023 - [i9]Zhenmei Shi, Jiefeng Chen, Kunyang Li, Jayaram Raghuram, Xi Wu, Yingyu Liang, Somesh Jha:
The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning. CoRR abs/2303.00106 (2023) - [i8]Zhenmei Shi, Yifei Ming, Ying Fan, Frederic Sala, Yingyu Liang:
Domain Generalization via Nuclear Norm Regularization. CoRR abs/2303.07527 (2023) - [i7]Yiyou Sun, Zhenmei Shi, Yingyu Liang, Yixuan Li:
When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis. CoRR abs/2308.05017 (2023) - [i6]Zhenmei Shi, Junyi Wei, Yingyu Liang:
Provable Guarantees for Neural Networks via Gradient Feature Learning. CoRR abs/2310.12408 (2023) - [i5]Yiyou Sun, Zhenmei Shi, Yixuan Li:
A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning. CoRR abs/2311.03524 (2023) - 2022
- [j1]Mehmet Furkan Demirel, Shengchao Liu, Siddhant Garg, Zhenmei Shi, Yingyu Liang:
Attentive Walk-Aggregating Graph Neural Networks. Trans. Mach. Learn. Res. 2022 (2022) - [c2]Zhenmei Shi, Junyi Wei, Yingyu Liang:
A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features. ICLR 2022 - [c1]Zhenmei Shi
, Fuhao Shi, Wei-Sheng Lai, Chia-Kai Liang, Yingyu Liang:
Deep Online Fused Video Stabilization. WACV 2022: 865-873 - [i4]Zhenmei Shi, Junyi Wei, Yingyu Liang:
A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features. CoRR abs/2206.01717 (2022) - 2021
- [i3]Zhenmei Shi, Fuhao Shi, Wei-Sheng Lai, Chia-Kai Liang, Yingyu Liang:
Deep Online Fused Video Stabilization. CoRR abs/2102.01279 (2021)
2010 – 2019
- 2019
- [i2]Zhenmei Shi, Haoyang Fang, Yu-Wing Tai, Chi-Keung Tang:
DAWN: Dual Augmented Memory Network for Unsupervised Video Object Tracking. CoRR abs/1908.00777 (2019) - [i1]Zhaoyang Yang, Zhenmei Shi, Xiaoyong Shen, Yu-Wing Tai:
SF-Net: Structured Feature Network for Continuous Sign Language Recognition. CoRR abs/1908.01341 (2019)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2025-02-20 20:43 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
