news

May 3, 2026 🎉 Paper “Kalman Linear Attention: Parallel Bayesian Filters For Efficient Language Modelling” accepted at the International Conference on Machine Learning 2026. Joint work with Cameron, Aidan, Andras, Elliot and Amos. arXiv
Feb 11, 2026 New preprint on Parallel Bayesian Filters For Efficient Language Modelling is out! Also accepted at the 1st Workshop on Epistemic Intelligence in Machine Learning (EIML) at EurIPS 2025.
Oct 11, 2024 Our new paper on Adaptive World Models and Non-Stationary RL accepted at NeurIPS 2024 Adaptive Foundation Models Workshop.
Nov 15, 2023 Gave a talk on “Multi Time Scale World Models” at MILA Robot Learning Seminar. Video Link
Sep 21, 2023 PhD work “Multi Time Scale World Models” accepted in NeurIPS 2023 as a Spotlight (Top 3% of all submitted papers).
Jan 21, 2022 PhD work “Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios” accepted in ICLR 2022.
Oct 1, 2020 PhD work “Action Conditional Recurrent Kalman Networks For Forward and Inverse Dynamics Learning” accepted in Conference on Robot Learning(CoRL) 2020. Video
Apr 15, 2019 Our Paper “Zero Shot Knowledge Distillation in Deep Networks” with Gaurav and Konda Reddy got accepted in ICML 2019.