Jiajun He

Hello there! I’m Jiajun He (何佳峻)! I am a second-year PhD student in the Machine Learning Group at the University of Cambridge under the supervision of Prof. José Miguel Hernández-Lobato. My research focuses on probabilistic inference in generative models, particularly from a stochastic path-space perspective. I develop algorithms that use generative models to make probabilistic inference more efficient, while also using inference principles to make generative models more controllable. I developed

• Non-equilibrium (path-space) approaches for free energy estimation;
• Path-space parallel tempering (aka replica exchange) for accelerated sampling;
• Path-space inference for efficient, flexible generative model control.

I am also interested in information-theoretic approaches to compact representations and compression, as well as generative methods for scientific discovery and design.

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 obtained an MSc in Bioinformatics at University of Copenhagen in Denmark, where I worked with Prof. Thomas Wim Hamelryck, and a BSc in Biological Science at Tsinghua University in China, where I was supervised by Prof. Xuerui Yang.

I am an landscape photographer at the same time! You can explore my work on Instagram. I will keep it updated!