Zhenmei Shi
23 papers · 2022–2026 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
🐝 Cross-Pollinator (10) 🌈 Renaissance Researcher (5) 🌍 Conference Polyglot (8) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge
🌉
Interdisciplinary Bridge
🌍
Conference Polyglot
(8)
🤝
Dynamic Duo
(20)
👑
Triple Crown
🔥
Unstoppable
(5)
💎
Century Club
(23)
⚡
Prolific Year
(13)
🗃️
Keyword Collector
(67)
❓
The Questioner
(4)
Conferences
AISTATS (4)
ICLR (4)
ICML (4)
EMNLP (3)
NIPS (3)
WACV (3)
ICCV (1)
UAI (1)
Top co-authors
Research topics
Keywords
neural network
(3)
neural tangent kernel
(3)
semi-supervised learning
(2)
transformer architecture
(2)
error bound
(2)
novel class discovery
(2)
multimodal learning
(1)
semi-supervised clustering
(1)
contrastive learning
(1)
graph theory
(1)
spectral clustering
(1)
attention mechanism
(1)
lottery ticket hypothesis
(1)
privacy preservation
(1)
graph representation
(1)
semantic consistency
(1)
multi-modal learning
(1)
computational complexity
(1)
theoretical analysis
(1)
benchmark evaluation
(1)
Papers
T2VWorldBench: A Benchmark for Evaluating World Knowledge in Text-to-Video Generation
WACV 2026
Fundamental Limits of Visual Autoregressive Transformers: Universal Approximation Abilities
ICML 2025
NRFlow: Towards Noise-Robust Generative Modeling via High-Order Mechanism
UAI 2025
Differential Privacy Mechanisms in Neural Tangent Kernel Regression
WACV 2025
Looped ReLU MLPs May Be All You Need as Practical Programmable Computers
AISTATS 2025
When Can We Solve the Weighted Low Rank Approximation Problem in Truly Subquadratic Time?
AISTATS 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
Towards Infinite-Long Prefix in Transformer
EMNLP 2025
Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers
EMNLP 2025
Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective
ICCV 2025
Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference Policies
ICML 2025
Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix
ICLR 2025
Fourier Circuits in Neural Networks and Transformers: A Case Study of Modular Arithmetic with Multiple Inputs
AISTATS 2025
Why Larger Language Models Do In-context Learning Differently?
ICML 2024
Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models
NIPS 2024
Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning
ICLR 2024
A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning
NIPS 2023
Provable Guarantees for Neural Networks via Gradient Feature Learning
NIPS 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
Deep Online Fused Video Stabilization
WACV 2022
A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features
ICLR 2022