IMG_8239.jpg

Jiajun He

PhD student in machine learning,
University of Cambridge. Curriculum Vitae



Hello there! I’m Jiajun He (何佳峻)! I am a first-year PhD in the Machine Learning Group at the University of Cambridge under the supervision of Prof. José Miguel Hernández-Lobato. My research interests focus on probabilistic methods. Specifically, I am interested in developing accelerated algorithms for relative entropy coding in compression, and designing neural samplers for sampling from unnormalized densities.

Previously, I completed my MPhil in Machine Learning and Machine Intelligence from University of Cambridge, where I graduated with distinction as the first of the cohort. For my MPhil dissertation, I worked with Prof. José Miguel Hernández-Lobato and Gergely Flamich on data compression with Implicit Neural Representations. Prior to that, I obained an MSc in Bioinformatics at University of Copenhagen in Denmark, and a BSc in Biological Science at Tsinghua University in China.

I am an landscape photographer in my spare time. Feel free to explore my works on Instagram. I will do my best to keep it updated!

Selected Publications [ view more ]

  1. workshop
    No Trick, No Treat: Pursuits and Challenges Towards Simulation-free Training of Neural Samplers   sampling
    Jiajun He*, Yuanqi Du*, Francisco Vargas, and 5 more authors
    In Workshop on Frontiers in Probabilistic Inference: Sampling Meets Learning @ ICLR 2025
  2. workshop
    Getting Free Bits Back from Rotational Symmetries in LLMs   coding
    Jiajun He, Gergely Flamich, and José Miguel Hernández-Lobato
    In Workshop on Machine Learning and Compression @ NeurIPS
    Oral at Compression Workshop @ NeurIPS 2024 [Top 4%]
  3. NeurIPS
    Accelerating Relative Entropy Coding with Space Partitioning   coding
    Jiajun He, Gergely Flamich, and José Miguel Hernández-Lobato
    In Advances in Neural Information Processing Systems (NeurIPS)
  4. ICLR
    RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations   coding
    Jiajun He*, Gergely Flamich*, Zongyu Guo, and 1 more author
    In International Conference on Learning Representations (ICLR)