I am a final-year PhD student in the Computer Science department at the University of Oxford, advised by Prof. Varun Kanade and Prof. Phil Blunsom. My PhD is generously supported by Google DeepMind.
I am broadly interested in the theoretical and scientific understanding of deep learning models, and more generally in questions of learnability. In particular, I work on (i) Expressivity: understanding what tasks and functions architectures like Transformers or RNNs can theoretically represent; (ii) Learning theory: characterising the learnability of neural networks and automata with examples and/or query access; and (iii) Empirical learnability: understanding the algorithmic learning capabilities of neural sequence models and how we can improve them.
Last year, I was a student researcher at Google in Sunnyvale, where I worked on improving LLM agents. Before that, I interned at Cohere twice, where I worked on pretraining LLMs with non-Transformer architectures. Before joining Oxford, I spent two amazing years as a Research Fellow at Microsoft Research India, where I worked with Dr. Navin Goyal. I did my undergrad at BITS Pilani, India, graduating in 2019. If you are interested to chat about research or anything else, feel free to drop me an email.
Provably Learning Attention with Queries
, Kulin Shah, Michael Hahn, Varun Kanade
ICML 2026
pdf
abstract
Automata Learning and Identification of the Support of Language Models
, Michael Hahn, Varun Kanade
ICLR 2026
pdf
abstract
Separations in the Representational Capabilities of Transformers and Recurrent Architectures
, Michael Hahn, Phil Blunsom, Varun Kanade
NeurIPS 2024
pdf
abstract
Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions
, Arkil Patel, Phil Blunsom, Varun Kanade
ICLR 2024 Oral
pdf
code
abstract
On the Ability and Limitations of Transformers to Recognize Formal Languages
, Kabir Ahuja, Navin Goyal
EMNLP 2020
pdf
code
abstract
On the Practical Ability of RNNs to Recognize Hierarchical Languages
Best Short Paper Award
, Kabir Ahuja, Navin Goyal
COLING 2020
pdf
code
abstract
- Departmental Tutor for Computational Learning Theory, University of Oxford Fall 2023
- Departmental Tutor for Computational Learning Theory, University of Oxford Fall 2022
- Teaching assistant for Neural Networks and Fuzzy Logic, BITS Pilani Spring 2018
