2025

1. workshop

   Towards Training One-Step Diffusion Models Without Distillation   generation

   Mingtian Zhang^*, Jiajun He^*, Wenlin Chen^*, and 4 more authors

   In Workshop on Deep Generative Model in Machine Learning @ ICLR 2025

   arXiv Bib

   @inproceedings{zhang2025towards,
     title = {Towards Training One-Step Diffusion Models Without Distillation},
     author = {Zhang, Mingtian and He, Jiajun and Chen, Wenlin and Ou, Zijing and Hern{\'a}ndez-Lobato, Jos{\'e} Miguel and Sch{\"o}lkopf, Bernhard and Barber, David},
     year = {2025},
     booktitle = {Workshop on Deep Generative Model in Machine Learning @ ICLR 2025}
   }

2. 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

   arXiv Bib

   @inproceedings{he2025no,
     title = {No Trick, No Treat: Pursuits and Challenges Towards Simulation-free Training of Neural Samplers},
     author = {He, Jiajun and Du, Yuanqi and Vargas, Francisco and Zhang, Dinghuai and Padhy, Shreyas and OuYang, RuiKang and Gomes, Carla and Hern{\'a}ndez-Lobato, Jos{\'e} Miguel},
     year = {2025},
     booktitle = {Workshop on Frontiers in Probabilistic Inference: Sampling Meets Learning @ ICLR 2025}
   }

3. AISTATS

   Training Neural Samplers with Reverse Diffusive KL Divergence   sampling

   Jiajun He^*, Wenlin Chen^*, Mingtian Zhang^*, and 2 more authors

   In International Conference on Artificial Intelligence and Statistics (AISTATS)

   arXiv Bib Code

   @inproceedings{he2024training,
     title = {Training Neural Samplers with Reverse Diffusive KL Divergence},
     author = {He, Jiajun and Chen, Wenlin and Zhang, Mingtian and Barber, David and Hern{\'a}ndez-Lobato, Jos{\'e} Miguel},
     year = {2025},
     booktitle = {International Conference on Artificial Intelligence and Statistics (AISTATS)},
   }

2024

1. 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%]

   arXiv Bib Slides

   @inproceedings{he2024getting,
     title = {Getting Free Bits Back from Rotational Symmetries in LLMs},
     author = {He, Jiajun and Flamich, Gergely and Hern{\'a}ndez-Lobato, Jos{\'e} Miguel},
     year = {2024},
     booktitle = {Workshop on Machine Learning and Compression @ NeurIPS},
   }

2. 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)

   arXiv Bib Poster

   @inproceedings{he2024accelerating,
     title = {Accelerating Relative Entropy Coding with Space Partitioning},
     author = {He, Jiajun and Flamich, Gergely and Hern{\'a}ndez-Lobato, Jos{\'e} Miguel},
     year = {2024},
     booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
   }

3. 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)

   arXiv Bib Code Poster Slides

   @inproceedings{he2024recombiner,
     title = {RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations},
     author = {He, Jiajun and Flamich, Gergely and Guo, Zongyu and Hern{\'a}ndez-Lobato, Jos{\'e} Miguel},
     booktitle = {International Conference on Learning Representations (ICLR)},
     year = {2024},
   }

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 (NeurIPS)

   Spotlight at NeurIPS 2023

   arXiv Bib Code Poster Slides

   @inproceedings{guo2023compression,
     title = {Compression with bayesian implicit neural representations},
     author = {Guo, Zongyu and Flamich, Gergely and He, Jiajun and Chen, Zhibo and Hern{\'a}ndez-Lobato, Jos{\'e} Miguel},
     booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
     year = {2023},
   }

2. Mphil Thesis

   Data Compression with Variational Implicit Neural Representations   coding

   Jiajun He

   University of Cambridge

   PDF