news

Apr 30, 2026 Our latest work (together with Doina Precup and Blake Richards) on continual reinforcement learning and biologically inspired memory systems, “Balancing Plasticity and Stability with Fast and Slow Successor Features,” has been accepted to International Conference on Machine Learning (ICML) 2026. See you in Seoul, Korea! 🇰🇷🧠🚀
Apr 23, 2026 Gave an invited research talk at New York University in Marcelo Mattar’s lab on continual reinforcement learning, predictive representations, and biologically inspired learning systems.
Apr 21, 2026 Visited the Zuckerman Institute at Columbia University to discuss recent work on continual reinforcement learning and computational neuroscience.
Mar 24, 2026 Participated in the Foundation Models Winter School in Amsterdam, exploring recent advances in foundation models. Hosted by Ellis unit Amsterdam 🇳🇱
Feb 20, 2026 Excited to share that I have successfully defended my PhD thesis! Thank you to my examiners, Prof. Mark Crowley (University of Waterloo), Prof. Ross Otto (McGill) and my advisors Blake and Doina!
Jan 17, 2026 Excited to kickstart the new year to share that our work on “Do Successor Features resemble Hippocampal Place Cells?” has been accepted at Cosyne 2026! See you all in Portugal! 🇵🇹🧠🚀
Nov 24, 2025 Announcement_11
Nov 20, 2025 Announcement_10
Nov 13, 2025 Announcement_9
Nov 12, 2025 Announcement_8
Oct 20, 2025 Announcement_7
Sep 28, 2025 Announcement_6
Mar 10, 2025 Invited by the Integrate and Fire Seminar organisers at McGill University to share my perspective on the discussion theme of the night, “How Intelligent is AI?” Through sharing my own work on reinforcement learning, I presented some evidence which showed that agents learned solely on rewards can obtain some form of intelligence.
Jan 30, 2025 Announcement_4
Sep 28, 2024 Announcement_1
Sep 25, 2024 My first research paper titled “Learning Successor Features the Simple Way,” on which I am the primary first author, co-authored with Arna Ghosh, Christos Kaplanis, Blake Richards and Doina Precup, has been accepted to the Neural Information Processing Systems conference (NeurIPS) a top-tier machine learning conference with a very selective 25.8% acceptance rate. Check out the blogpost and the paper! 🎉
Feb 29, 2024 Presented our recent work on Continual RL using Successor Features @ Computational and Systems Neuroscience (COSYNE) in Lisbon, Portugal, with a selective 51.6% acceptance rate. 🇵🇹🧠