selected publications

(*) denotes equal contribution

You can find full list of my publications and recent works on my Google Scholar.

2025

  1. arXiv
    FEAT: Free energy Estimators with Adaptive Transport   Monte Carlo
    Jiajun He*, Yuanqi Du*, Francisco Vargas, and 4 more authors
  2. arXiv
    Accelerated Parallel Tempering via Neural Transports   Monte Carlo
    Leo Zhang*, Peter Potaptchik*Jiajun He*, and 5 more authors
  3. ICML
    Progressive Tempering Sampler with Diffusion   Monte Carlo
    Severi Rissanen*, RuiKang OuYang*Jiajun He, and 4 more authors
    In International Conference on Machine Learning
  4. FPI @ ICLR
    No Trick, No Treat: Pursuits and Challenges Towards Simulation-free Training of Neural Samplers   Monte Carlo
    Jiajun He*, Yuanqi Du*, Francisco Vargas, and 5 more authors
    In Workshop on Frontiers in Probabilistic Inference: Sampling Meets Learning @ ICLR 2025
  5. AISTATS
    Training Neural Samplers with Reverse Diffusive KL Divergence   Monte Carlo
    Jiajun He*, Wenlin Chen*, Mingtian Zhang*, and 2 more authors
    In International Conference on Artificial Intelligence and Statistics

2024

  1. 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
  2. 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

2023

  1. NeurIPS
    Compression with bayesian implicit neural representations   coding
    Zongyu Guo*, Gergely Flamich*Jiajun He, and 2 more authors
    In Advances in Neural Information Processing Systems
    Spotlight at NeurIPS 2023
  2. Mphil Thesis
    Data Compression with Variational Implicit Neural Representations   coding
    Jiajun He
    University of Cambridge