Hiren Madhu

I am a third year PhD student at Yale CS, advised by Professor Smita Krishnaswamy and Professor Rex Ying.

In summer 2026, I was an AI intern at NetApp in San Jose, mentored by Kiran Srinivasan, where I worked on grounding LLMs in relational time-series data.

Earlier, I was an ECE pre-doctoral research fellow in Electrical Communication Engineering Department at the Indian Institute of Science, Bengaluru, after finishing my MTech in Artificial Intelligence there. I worked with Sundeep Prabhakar Chepuri on unsupervised representation learning for simplicial complexes.

I began my research journey at LDRP Institute of Technology and Research (BE in Computer Engineering) under the guidance of Sandip Modha and Thomas Mandl, where I focused on the detection of hate speech in public conversational threads on social media.

My research interests are foundation models, representation learning, and geometric deep learning — in particular, encoding geometric inductive biases into foundation models. Recently, this has meant hyperbolic representations for language models and retrieval, and graph foundation models for spatial omics. Previously, I worked on simplicial representation learning without labels.

Self picture

What have I been up to?