My name is Junze Yin. I am a second-year Ph.D. student at Rice University, fortunate to be advised by Professor Maryam Aliakbarpour. I earned my M.A. and B.A. in Mathematics from Boston University, where I had the privilege of being advised by Professor Mark Kon. My research interests lie at the intersection of theoretical computer science and machine learning. Specifically, I am interested in numerical linear algebra, theoretical machine learning, large language models, and robust statistics.

CV

Research

Accepted Papers

• CoVE: Compressed Vocabulary Expansion Makes Better LLM-based Recommender Systems (Article link).
  Haochen Zhang, Tianyi Zhang, Junze Yin, Oren Gal, Anshumali Shrivastava, Vladimir Braverman
  ACL 2025 Findings

Accepted Papers (Author names in alphabetical order)

• Binary Hypothesis Testing for Softmax Models and Leverage Score Models. (Article link).
  Yuzhou Gu, Zhao Song, and Junze Yin
  ICML 2025
• The Expressibility of Polynomial based Attention Scheme. (Article link).
  Zhao Song, Chongxi Wang, Guangyi Xu, and Junze Yin
  KDD 2025
• Dynamic maintenance of kernel density estimation data structure: From practice to theory. (Article link).
  Jiehao Liang, Zhao Song, Zhaozhuo Xu, Junze Yin, and Danyang Zhuo
  UAI 2025
• A fast optimization view: reformulating single layer attention in LLM based on tensor and svm trick, and solving it in matrix multiplication time. (Article link).
  Yeqi Gao, Zhao Song, Weixin Wang, and Junze Yin
  UAI 2025
• Fast and Efficient Matching Algorithm with Deadline Instances (Article link).
  Zhao Song, Weixin Wang, Chenbo Yin, and Junze Yin
  CPAL 2025
• Efficient Alternating Minimization with Applications to Weighted Low Rank Approximation (Article link).
  Zhao Song, Mingquan Ye, Junze Yin, and Lichen Zhang
  ICLR 2025
• An Iterative Algorithm for Rescaled Hyperbolic Functions Regression (Article link).
  Yeqi Gao, Zhao Song, and Junze Yin
  AISTATS 2025
• Revisiting Quantum Algorithms for Linear Regressions: Quadratic Speedups without Data-Dependent Parameters (Article link).
  Zhao Song, Junze Yin, and Ruizhe Zhang
  QIP 2025
• Fast Dynamic Sampling for Determinantal Point Processes (Article link).
  Zhao Song, Junze Yin, Lichen Zhang, and Ruizhe Zhang
  AISTATS 2024
• Solving Attention Kernel Regression Problem via Pre-conditioner (Article link).
  Zhao Song, Junze Yin, and Lichen Zhang
  AISTATS 2024
• Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time (Article link).
  Yuzhou Gu, Zhao Song, Junze Yin, and Lichen Zhang
  ICLR 2024
• Dynamical fractal: Theory and case study (Article link).
  Junze Yin
  Chaos, Solitons & Fractals Volume 176, November 2023, 114190.
  Oral Presentation: JMM 2022, AMS Special Session on Geometry in the Mathematics of Data Science
  
• A Nearly-Optimal Bound for Fast Regression with $\ell_\infty$ Guarantee (Article link).
  Zhao Song, Mingquan Ye, Junze Yin, and Lichen Zhang
  ICML, 2023.