Zhenmei Shi
23 papers · 2022–2026 · 8 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge Β· Silver π Conference Polyglot Β· Silver πΊοΈ Taxonomy Completionist (44) π€ Dynamic Duo (20)
π€
Dynamic Duo
(20)
β‘
Prolific Year Β· Prolific
π
Century Club Β· Bronze
β
The Questioner
(4)
ποΈ
Keyword Collector
(112)
π₯
Unstoppable Β· Bronze
Top co-authors
Research topics
Machine Learning
(16)
Deep Learning
(14)
Artificial Intelligence
(12)
Core AI
(11)
Optimization & Theory Β· Machine Learning
(10)
Architectures
(7)
Core Methods
(6)
Learning Types Β· Machine Learning
(6)
Optimization & Theory Β· Deep Learning
(4)
Computer Science
(3)
Computer Vision
(3)
Application Areas
(3)
Learning Types Β· Deep Learning
(3)
Models
(3)
Mathematics & Optimization
(2)
Keywords
neural network
(4)
large language model
(3)
neural tangent kernel
(3)
transformer architecture
(3)
representation learning
(2)
learning theory
(2)
foundation model
(2)
in-context learning
(2)
novel class discovery
(2)
contrastive learning
(2)
semi-supervised learning
(2)
feature learning
(2)
error bound
(2)
transformer
(2)
universal approximation
(2)
expressive power
(2)
attention matrix
(2)
spectral clustering
(1)
few-shot learning
(1)
differential privacy
(1)
Papers
T2VWorldBench: A Benchmark for Evaluating World Knowledge in Text-to-Video Generation
WACV 2026
Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix
ICLR 2025
Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent
AISTATS 2025
Circuit Complexity Bounds for RoPE-based Transformer Architecture
EMNLP 2025
Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers
EMNLP 2025
Differential Privacy Mechanisms in Neural Tangent Kernel Regression
WACV 2025
Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference Policies
ICML 2025
Fourier Circuits in Neural Networks and Transformers: A Case Study of Modular Arithmetic with Multiple Inputs
AISTATS 2025
Fundamental Limits of Visual Autoregressive Transformers: Universal Approximation Abilities
ICML 2025
Looped ReLU MLPs May Be All You Need as Practical Programmable Computers
AISTATS 2025
NRFlow: Towards Noise-Robust Generative Modeling via High-Order Mechanism
UAI 2025
Towards Infinite-Long Prefix in Transformer
EMNLP 2025
Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective
ICCV 2025
When Can We Solve the Weighted Low Rank Approximation Problem in Truly Subquadratic Time?
AISTATS 2025
Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models
NeurIPS 2024
Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning
ICLR 2024
Why Larger Language Models Do In-context Learning Differently?
ICML 2024
A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning
NeurIPS 2023
Provable Guarantees for Neural Networks via Gradient Feature Learning
NeurIPS 2023
The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning
ICLR 2023
When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysis
ICML 2023
A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features
ICLR 2022
Deep Online Fused Video Stabilization
WACV 2022