I am currently a professor at EPFL and lead the CLAIRE research lab. I was a staff research scientist at Google DeepMind, working on the intersection of reinforcement learning, foundation models, novel architectures and training paradigms, safety + alignment, and natural language understanding. During my time at DeepMind, I led or co-led several projects, ranging from the next generation of sequence modeling architectures, alignment, and safety to offline RL.

​​

I am interested in building agents that can learn from a feedback signal (often weak, sparse, and noisy in the real world) while utilizing unlabeled data available in the environment. I am interested in improving our understanding of the existing algorithms and developing new ones to enable real-world applications with positive social impact. I am particularly fascinated by the scientific applications of machine learning algorithms. I enjoy working in a multi/cross-disciplinary team and am often inspired by neuroscience, biology, and cognitive sciences when working on algorithmic solutions.  

​

I finished my Ph.D. under the supervision of Yoshua Bengio at MILA.

​

I defended my thesis "Learning and time: on using memory and curricula for language understanding" in 2018 with Christopher Manning as my external examiner. Currently, the research topics that I am working on include but are not limited to reinforcement learning, offline RL, large-scale deep architectures (or foundational models. as they call it these days), and representation learning (including self-supervised learning, new architectures, causal representations, etc.) I have served as an area chair and reviewer to significant machine learning conferences such as ICML, NeurIPS, ICLR, and journals like Nature and JMLR. I  have published at numerous influential conferences and journals such as Nature, JMLR, NeurIPS, ICML, ICLR, ACL, EMNLP, etc... I gave the Memory augmented neural networks tutorial in EMNLP 2018. My work has received the best paper award at the Nonconvex Optimization workshop at NeurIPS and an honorable mention for best paper at ICML 2019. ​I have co-organized seven workshops at the top machine learning conferences such as NeurIPS, ICML, and ICLR.

​