Research

Research Interests

I am broadly interested in the development of large language models and other machine learning methods. My recent work has focused on post-training LLMs for code generation, including for visual answers and generative UIs. Previously, I developed an alignment approach for LLM-as-a-Judge applications, and worked on personalized content recommendations using LLMs.

In my academic work I've focused on deep generative models, change point detection, data parsing, matrix factorization, multiclass SVMs, and sparse regression, among other things. Because my research is often focused on developing methods that work well in the real world, I have also created easy-to-use software packages for most of my research projects.

To learn more, please check out my resume.

Publications

Please refer to Google Scholar for a more complete list.

Articles:

  • Vision-Guided Iterative Refinement for Frontend Code Generation (PDF)
    , , , , ,
    ICLR 2026 Workshop on AI with Recursive Self-Improvement (RSI), .
    ▸ Show abstract
  • Enabling User Agency in Scalable Content Recommendations with Large Language Models (PDF)
    , , , , ,
    Proceedings of the 25th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2026), .
    ▸ Show abstract
  • Aligning Black-box Language Models with Human Judgments (PDF)
    , , ,
    Findings of the Association for Computational Linguistics: NAACL 2025, .
    ▸ Show abstract
  • Efficient Pointwise-Pairwise Learning-to-Rank for News Recommendation (PDF)
    , , ,
    Findings of the Association for Computational Linguistics: EMNLP 2024, .
    ▸ Show abstract
  • AI Assistants: A Framework for Semi-Automated Data Wrangling (PDF)
    , , , , ,
    IEEE Transactions on Knowledge and Data Engineering, 35(9):92959306, .
    ▸ Show abstract
  • On Memorization in Probabilistic Deep Generative Models (PDF)
    ,
    Advances in Neural Information Processing Systems, 34:2791627928, .
    ▸ Show abstract
  • Probabilistic Sequential Matrix Factorization (PDF)
    , , ,
    Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, (PMLR 130):34843492, .
    ▸ Show abstract
  • An Evaluation of Change Point Detection Algorithms (PDF)
    ,
    arXiv preprint 2003.06222, .
    ▸ Show abstract
  • Wrangling Messy CSV Files by Detecting Row and Type Patterns (HTMLPDF)
    , ,
    Data Mining and Knowledge Discovery, 33:17991820, .
    ▸ Show abstract
  • Fast Meta-Learning for Adaptive Hierarchical Classifier Design (PDF)
    ,
    arXiv preprint 1711.03512, .
    Code: Python
    ▸ Show abstract
  • SparseStep: Approximating the Counting Norm for Sparse Regularization (PDF)
    , ,
    arXiv preprint 1701.06967, .
    Code: R
    ▸ Show abstract
  • GenSVM: A Generalized Multiclass Support Vector Machine (PDF)
    ,
    Journal of Machine Learning Research, 17(224):142, .
    Code: CRPython
    ▸ Show abstract

Dissertation:

  • Algorithms for Multiclass Classification and Regularized Regression (PDF)
    Erasmus University Rotterdam, .
    ▸ Show abstract

Software

I aim to make my research accessible by providing software packages for the methods I develop.

  • CleverCSV. Implements the method from this paper. PyPI - GitHub.
  • SmartSVM. Implements the SmartSVM classifier from this paper. PyPI - GitHub.
  • SparseStep. Implements the SparseStep method from this paper. CRAN - GitHub.
  • GenSVM. Implements the GenSVM method from this paper. PyPI - CRAN - GitHub.
  • Abed. Tool for benchmarking ML methods on compute clusters. PyPI - GitHub.
  • SyncRNG. The same random numbers in R and Python. CRAN - PyPI - GitHub.