Zhenmei Shi

On Fine-Grained I/O Complexity of Attention Backward Passes

Can Language Models Compose Skills In-Context?

T2VPhysBench: A First‑Principles Benchmark for Physical Consistency in Text‑to‑Video Generation

Text-to-Image Diffusion Models Cannot Count, and Prompt Refinement Cannot Help

RoPE Attention Can Be Trained in Almost Linear Time

Theoretical Constraints on the Expressive Power of RoPE-based Tensor Attention Transformers

Exploring the Frontiers of Softmax: Provable Optimization, Applications in Diffusion Model, and Beyond

Training Tensor Attention Efficiently: From Cubic to Almost Linear Time

Advancing the understanding of fixed point iterations in deep neural networks: a detailed analytical study

Circuit Complexity Bounds for Visual Autoregressive Model

Neural Algorithmic Reasoning for Hypergraphs with Looped Transformers

HOFAR: High-Order Augmentation of Flow Autoregressive Transformers

RichSpace: Enriching Text-to-Video Prompt Space via Text Embedding Interpolation

Theoretical Guarantees for High Order Trajectory Refinement in Generative Flows

Your Vision-Language Model Can’t Even Count to 20: Exposing the Failures of VLMs in Compositional Counting

T2VTextBench: A Human Evaluation Benchmark for Textual Control in Video Generation Models

DPBloomfilter: Securing Bloom Filters with Differential Privacy

Training Multi-Layer Transformers in Almost Linear Time

Visual Autoregressive Transformers Must Use $\Omega(n^2 d)$ Memory

On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis

Modern Hopfield Networks Cannot Solve $\mathsf{NC}^1$-Hard Problems

Provably Efficient High-Order Flow Matching in Pixel Space

High-Order Matching for One-Step Shortcut Diffusion Models

Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score Learning

Fine-grained Attention I/O Complexity: Comprehensive Analysis for Backward Passes

Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference Policies

Differential Privacy of Cross-Attention with Provable Guarantee

Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time

Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix

Tensor Attention Training: Provably Efficient Learning of Higher-order Transformers

Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction

Towards Infinite-Long Prefix in Transformer

Fundamental Limits of Visual Autoregressive Transformers: Universal Approximation Abilities

Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers

HSR-Enhanced Sparse Attention Acceleration