Nicolas

Nicolas Huynh

Email

LinkedIn

Google Scholar

Github

I am a fourth-year PhD student in Machine Learning at the University of Cambridge (department of Applied Mathematics and Theoretical Physics), supervised by Mihaela van der Schaar. Previously, I earned a Diplome d'ingénieur from Ecole Polytechnique (majoring in applied mathematics) and a MSc in Machine Learning from Ecole Normale Supérieure Paris-Saclay.

My research focuses on LLMs for scientific discovery, using language models to uncover interpretable rules and hypotheses; generative modeling of temporal and biological data; learning from human feedback through preference-based reward learning; and data-centric AI for evaluating, curating, and augmenting data.

Publications

(* denotes equal contribution)

LLMs for scientific discovery

Using language models to discover interpretable rules and generate hypotheses from complex data.

  • AI discovery of sequence rules for RNA polymerase II pausing revises the pause-release model of gene activation
    Nova Fong, Nicolas Huynh, Benjamin Erickson, Ryan Sheridan, Srinivas Ramachandran, Mihaela van der Schaar, David Bentley
    bioRxiv preprint, 2026
    [Paper]
  • Interpretable DNA Sequence Classification via Dynamic Feature Generation in Decision Trees
    Nicolas Huynh, Krzysztof Kacprzyk, Ryan Sheridan, David Bentley, Mihaela van der Schaar
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2026
    [Paper]
  • Decision Tree Induction Through LLMs via Semantically-Aware Evolution
    Tennison Liu*, Nicolas Huynh*, Mihaela van der Schaar
    International Conference on Learning Representations (ICLR), 2025
    [Paper]

Generative modeling

Developing generative models for temporal and biological data, and studying how to learn evolving distributions from limited observations.

  • Active Timepoint Selection for Learning Measure-Valued Trajectories
    Nicolas Huynh*, Mihaela van der Schaar
    International Conference on Machine Learning (ICML), 2026
    [Paper]
  • CellBRIDGE: Learning Cellular Trajectories via Interaction-Aware Alignment
    Silas Ruhrberg Estevez*, Nicolas Huynh*, Tennison Liu, Roderik Kortlever, Gerard Evan, David Bentley, Mihaela van der Schaar
    International Conference on Machine Learning (ICML), 2026
    [Paper]
  • Time Series Diffusion in the Frequency Domain
    Jonathan Crabbé*, Nicolas Huynh*, Jan Stanczuk, Mihaela van der Schaar
    International Conference on Machine Learning (ICML), 2024
    [Paper]

Learning from human feedback

Learning reward functions from human preferences and selecting informative comparisons for learning and optimization.

  • Active Preference-Based Gaussian Process Regression for Reward Learning and Optimization
    Erdem Bıyık, Nicolas Huynh, Mykel J. Kochenderfer, Dorsa Sadigh
    International Journal of Robotics Research (IJRR)
    [Paper]
  • Active Preference-Based Gaussian Process Regression for Reward Learning
    Erdem Bıyık*, Nicolas Huynh*, Mykel J. Kochenderfer, Dorsa Sadigh
    Robotics: Science and Systems (RSS),  2020
    [Paper]

Data-centric AI

Improving learning through data evaluation, curation, and generation, particularly when observations are limited.

  • Improving Treatment Effect Estimation with LLM-Based Data Augmentation
    Nicolas Huynh*, Julianna Piskorz*, Jeroen Berrevoets, Max Ruiz Luyten, Mihaela van der Schaar
    ICML Workshop on Foundation Models for Structured Data, 2025
    [Paper]
  • Curated LLM: Synergy of LLMs and Data Curation for Tabular Augmentation in Ultra low-data Regimes
    Nabeel Seedat*, Nicolas Huynh*, Boris van Breugel, Mihaela van der Schaar
    International Conference on Machine Learning (ICML), 2024
    [Paper]
  • You Can't Handle the (Dirty) Truth: Data-centric Insights Improve Pseudo-labeling
    Nabeel Seedat*, Nicolas Huynh*, Fergus Imrie, Mihaela van der Schaar
    Journal of Data-centric Machine Learning Research (DMLR)
    [Paper]
  • DAGnosis: Localized Identification of Data Inconsistencies using Structures
    Nicolas Huynh, Jeroen Berrevoets, Nabeel Seedat, Jonathan Crabbé, Zhaozhi Qian, Mihaela van der Schaar
    International Conference on Artificial Intelligence and Statistics (AISTATS), 2024
    [Paper]

Other publications

  • GraphCite: Citation Intent Classification in Scientific Publications via Graph Embeddings
    Dan Berrebbi*, Nicolas Huynh*, Oana Balalau
    The Web Conf, 2nd International Workshop on Scientific Knowledge: Representation, Discovery, and Assessment, 2022
    [Paper]