publications

2024

1. 

   Training Neural Samplers with Reverse Diffusive KL Divergence

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

   2024

   arXiv Bib

   @unpublished{he2024training,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 = {2024},
   }

2. 

   Getting Free Bits Back from Rotational Symmetries in LLMs

   Jiajun He, Gergely Flamich, and José Miguel Hernández-Lobato

   2024

   arXiv Bib

   @unpublished{he2024getting,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},
   }

3. 

   Efficient and Unbiased Sampling of Boltzmann Distributions via Consistency Models

   Fengzhe Zhang^*, Jiajun He^*, Laurence I. Midgley, and 2 more authors

   In Workshop on Machine Learning and the Physical Sciences @ NeurIPS, 2024

   arXiv Bib

   @inproceedings{zhang2024efficient,
     title = {Efficient and Unbiased Sampling of Boltzmann Distributions via Consistency Models},
     author = {Zhang, Fengzhe and He, Jiajun and Midgley, Laurence I. and Antorán, Javier and Hern{\'a}ndez-Lobato, Jos{\'e} Miguel},
     year = {2024},
     booktitle = {Workshop on Machine Learning and the Physical Sciences @ NeurIPS},
   }

4. 

   Accelerating Relative Entropy Coding with Space Partitioning

   Jiajun He, Gergely Flamich, and José Miguel Hernández-Lobato

   In Advances in Neural Information Processing Systems (NeurIPS), 2024

   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)},
   }

5. 

   Bidirectional Consistency Models

   Liangchen Li^*, and Jiajun He^*

   In Workshop on Structured Probabilistic Inference & Generative Modeling @ ICML, 2024

   arXiv Bib PDF Code Poster

   @inproceedings{li2024bidirectional,
     title = {Bidirectional Consistency Models},
     author = {Li, Liangchen and He, Jiajun},
     booktitle = {Workshop on Structured Probabilistic Inference & Generative Modeling @ ICML},
     year = {2024},
   }

6. 

   RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations

   Jiajun He^*, Gergely Flamich^*, Zongyu Guo, and 1 more author

   In International Conference on Learning Representations (ICLR), 2024

   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. 

   Compression with bayesian implicit neural representations

   Zongyu Guo^*, Gergely Flamich^*, Jiajun He, and 2 more authors

   In Advances in Neural Information Processing Systems (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. 

   Data Compression with Variational Implicit Neural Representations

   Jiajun He

   University of Cambridge, 2023

   PDF