About Me

I am an associate professor of computer science at the University of British Columbia and a Canada CIFAR AI Chair at Mila. I direct the Programming Languages for Artificial Intelligence (PLAI) research group. I also am a founder of Inverted AI, a PLAI group spin-out focused on advanced simulation technology for the autonomous vehicle industry.


Research Interests

My primary research areas include deep generative modeling, amortized inference, probabilistic programming, reinforcement learning, and applied probabilistic machine learning. My research interests range from the development of new probabilistic models and inference algorithms to real-world applications. My research contributions include probabilistic programming systems, new models and inference algorithms, and novel applications of such models to problems in autonomous driving, computational neuroscience, vision, natural language processing, robotics, and reinforcement learning.

Selected Publications

  1. van de Meent, J.-W., Paige, B., Yang, H., & Wood, F. (2018). An introduction to probabilistic programming. ArXiv Preprint ArXiv:1809.10756. PDF
      title = {An introduction to probabilistic programming},
      author = {van de Meent, Jan-Willem and Paige, Brooks and Yang, Hongseok and Wood, Frank},
      journal = {arXiv preprint arXiv:1809.10756},
      year = {2018}
  2. Masrani, V., Le, T. A., & Wood, F. (2019). The Thermodynamic Variational Objective. ArXiv Preprint ArXiv:1907.00031. PDF
      title = {The Thermodynamic Variational Objective},
      author = {Masrani, Vaden and Le, Tuan Anh and Wood, Frank},
      journal = {arXiv preprint arXiv:1907.00031},
      year = {2019}
  3. Le, T. A., Kosiorek, A. R., Siddharth, N., Teh, Y. W., & Wood, F. (2019). Revisiting Reweighted Wake-Sleep for Models with Stochastic Control Flow. PDF
      title = {Revisiting Reweighted Wake-Sleep for Models with Stochastic Control Flow},
      author = {Le, Tuan Anh and Kosiorek, Adam R and Siddharth, N and Teh, Yee Whye and Wood, Frank},
      year = {2019},
      publisher = {Association for Uncertainty in Artificial Intelligence}
  4. Siddarth, N., Paige, B., Desmaison, A., van de Meent, J. W., Goodman, N., Kohli, P., Wood, F., & Torr, P. H. S. (2017). Learning Disentangled Representations with Semi-Supervised Deep Generative Models. NIPS. PDF
      title = {Learning Disentangled Representations with Semi-Supervised Deep Generative Models},
      author = {Siddarth, N. and Paige, B. and Desmaison, A. and van~de~Meent, J.W. and Goodman, N. and Kohli, P. and Wood, F. and Torr, P.H.S},
      booktitle = {NIPS},
      year = {2017}
  5. Le, T. A., Baydin, A. G., & Wood, F. (2017). Inference Compilation and Universal Probabilistic Programming. AISTATS. PDF
      author = {Le, Tuan Anh and Baydin, Atılım Güneş and Wood, Frank},
      booktitle = {AISTATS},
      title = {Inference {C}ompilation and {U}niversal {P}robabilistic {P}rogramming},
      year = {2017},
      file = {../assets/pdf/le2016inference.pdf},
      link = {https://arxiv.org/abs/1610.09900}

Prospective students

I am always looking for excellent, academically-motivated, AI-inspired PhD students. Please visit the departmental web page for prospective students to apply. An excellent strategy for getting an offer to work with me is to propose research in your proposal that extends and explicitly cites recent work of my own. Better still, working with me beforehand is a major leg up. Direct email to me about becoming a student at UBC is unlikely to get a reply.


I am constantly looking for postdocs with strong programming languages, statistics, and applied machine learning skills. Please contact me directly including a brief (one paragraph or so) proposed research plan related to my recent research and funding (see my CV for current funding details). Contact without research plans is unlikely to get a reply.


The intersection of Canada, British Columbia, Vancouver, and UBC is an amazingly interesting place to start a technology company. Contact me directly if you are interested in maintaining an academic affiliation while starting, while sitting beside a world-class machine learning team, a machine learning startup in Vancouver. Please familiarize yourself with MITACS Accelerate and explain where you will source initial investment in the first email. Contact without concrete and attainable funding plans is unlikely to get a reply.


I was one of the initial developers of the Anglican probabilistic programming language and am a co-author of one of the first book length treatments of probabilistic programming, a pre-print of which is on arXiv.