Xiaoyu Li

According to our database, Xiaoyu Li authored at least 31 papers between 2024 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Exploring the Limits of KV Cache Compression in Visual Autoregressive Transformers.

Bo Chen, Xiaoyu Li, Yekun Ke, Yingyu Liang, Zhenmei Shi, Zhao Song

CoRR, March, 2025

Time and Memory Trade-off of KV-Cache Compression in Tensor Transformer Decoding.

Yifang Chen, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song, Yu Tian

CoRR, March, 2025

Theoretical Guarantees for High Order Trajectory Refinement in Generative Flows.

Chengyue Gong, Xiaoyu Li, Yingyu Liang, Jiangxuan Long, Zhenmei Shi, Zhao Song, Yu Tian

CoRR, March, 2025

Scaling Law Phenomena Across Regression Paradigms: Multiple and Kernel Approaches.

Yifang Chen, Xuyang Guo, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song

CoRR, March, 2025

On Computational Limits of FlowAR Models: Expressivity and Efficiency.

Chengyue Gong, Yekun Ke, Xiaoyu Li, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song

CoRR, February, 2025

Force Matching with Relativistic Constraints: A Physics-Inspired Approach to Stable and Efficient Generative Modeling.

Yang Cao, Bo Chen, Xiaoyu Li, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Mingda Wan

CoRR, February, 2025

Universal Approximation of Visual Autoregressive Transformers.

Yifang Chen, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song

CoRR, February, 2025

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

Yuefan Cao, Xiaoyu Li, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Jiahao Zhang

CoRR, February, 2025

High-Order Matching for One-Step Shortcut Diffusion Models.

Bo Chen, Chengyue Gong, Xiaoyu Li, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Mingda Wan

CoRR, February, 2025

Neural Algorithmic Reasoning for Hypergraphs with Looped Transformers.

Xiaoyu Li, Yingyu Liang, Jiangxuan Long, Zhenmei Shi, Zhao Song, Zhen Zhuang

CoRR, January, 2025

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

Yuefan Cao, Chengyue Gong, Xiaoyu Li, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song

CoRR, January, 2025

On the Computational Capability of Graph Neural Networks: A Circuit Complexity Bound Perspective.

Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song, Wei Wang, Jiahao Zhang

CoRR, January, 2025

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

Yekun Ke, Xiaoyu Li, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song

CoRR, January, 2025

Circuit Complexity Bounds for Visual Autoregressive Model.

Yekun Ke, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song

CoRR, January, 2025

NRFlow: Towards Noise-Robust Generative Modeling via High-Order Mechanism.

Bo Chen, Chengyue Gong, Xiaoyu Li, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song, Mingda Wan, Xugang Ye

Proceedings of the Conference on Uncertainty in Artificial Intelligence, 2025

Fast John Ellipsoid Computation with Differential Privacy Optimization.

Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song, Junwei Yu

Proceedings of the Conference on Parsimony and Learning, 2025

The Computational Limits of State-Space Models and Mamba via the Lens of Circuit Complexity.

Yifang Chen, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song

Proceedings of the Conference on Parsimony and Learning, 2025

Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent.

Bo Chen, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024

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

Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song, Mingda Wan

CoRR, 2024

Fast Gradient Computation for RoPE Attention in Almost Linear Time.

Yifang Chen, Jiayan Huo, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song

CoRR, 2024

Grams: Gradient Descent with Adaptive Momentum Scaling.

Yang Cao, Xiaoyu Li, Zhao Song

CoRR, 2024

On the Expressive Power of Modern Hopfield Networks.

Xiaoyu Li, Yuanpeng Li, Yingyu Liang, Zhenmei Shi, Zhao Song

CoRR, 2024

Circuit Complexity Bounds for RoPE-based Transformer Architecture.

Bo Chen, Xiaoyu Li, Yingyu Liang, Jiangxuan Long, Zhenmei Shi, Zhao Song

CoRR, 2024

Advancing the Understanding of Fixed Point Iterations in Deep Neural Networks: A Detailed Analytical Study.

Yekun Ke, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song

CoRR, 2024

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

Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song, Yufa Zhou

CoRR, 2024

Quantum Speedups for Approximating the John Ellipsoid.

Xiaoyu Li, Zhao Song, Junwei Yu

CoRR, 2024

A Tighter Complexity Analysis of SparseGPT.

Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song

CoRR, 2024

Fast John Ellipsoid Computation with Differential Privacy Optimization.

Jiuxiang Gu, Xiaoyu Li, Yingyu Liang, Zhenmei Shi, Zhao Song, Junwei Yu

CoRR, 2024

DiHAN: A Novel Dynamic Hierarchical Graph Attention Network for Fake News Detection.

Ya-Ting Chang, Zhibo Hu, Xiaoyu Li, Shuiqiao Yang, Jiaojiao Jiang, Nan Sun

Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, 2024

Faster Sampling Algorithms for Polytopes with Small Treewidth.

Yekun Ke, Xiaoyu Li, Zhao Song, Tianyi Zhou

Proceedings of the IEEE International Conference on Big Data, 2024

Fast Second-order Method for Neural Networks under Small Treewidth Setting.

Xiaoyu Li, Jiangxuan Long, Zhao Song, Tianyi Zhou

Proceedings of the IEEE International Conference on Big Data, 2024