Xiaoyu Li

Dynamic Kernel Graph Sparsifiers

A Dynamic Low-Rank Fast Gaussian Transform

Training Overparametrized Neural Networks in Sublinear Time

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

Decoupling Sign and Magnitude in Optimization with Adaptive Momentum Scaling

RoPE Attention Can Be Trained in Almost Linear Time

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

Accept More, Reject Less: Reducing up to 19% Unnecessary Desk-Rejections over 11 Years of ICLR Data

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

Circuit Complexity Bounds for Visual Autoregressive Model

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

Differentially Private Lewis Weight Computation

Theoretical Guarantees for High Order Trajectory Refinement in Generative Flows

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

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

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

Dynamic Weighted Projection Maintenance with $\ell^p$-Lewis Weight

High-Order Matching for One-Step Shortcut Diffusion Models

Provably Efficient High-Order Flow Matching in Pixel Space

Efficient $k$-Sparse Band–Limited Interpolation with Improved Approximation Ratio

Discrepancy Minimization in Input-Sparsity Time

Deterministic Sparse Fourier Transform for Continuous Signals with Frequency Gap

Faster Algorithms for Structured John Ellipsoid Computation

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

Fundamental Limits of Visual Autoregressive Transformers: Universal Approximation Abilities