Ashok Vardhan Makkuva
 |
Postdoctoral researcher I am on the faculty job market this year! |
About Me
I am a postdoctoral researcher at EPFL, working with Michael Gastpar, Jason Lee, and Martin Jaggi. My research focuses on building principled and foundational AI frameworks that enable reliable and trustworthy AI systems. In particular, my work bridges theoretical insights and practical systems across two key research thrusts: (1) Thrust 1 — Algorithmic Frameworks for AI via Information-Theoretic Principles, and (2) Thrust 2 — Theoretical Foundations of AI via Structured Data. I have made fundamental contributions to these areas, with my research featured in top-tier machine learning conferences such as ICML and NeurIPS. A selection of key publications reflecting this theme includes: Fundamental limits of prompt compression, Attention with Markov, Local to Global, and Constant depth suffices.
Before joining EPFL, I got my Ph.D. in Electrical and Computer Engineering from UIUC, where I worked with Pramod Viswanath and Sewoong Oh. During my PhD, I had the pleasure of collaborating with and Sreeram Kannan, Founder and CEO of EigenLayer.
Prior to that, I graduated from IIT Bombay with a B. Tech. (Honors) in Electrical Engineering and Minors in Mathematics, where I worked with Vivek Borkar.
News
Dec 2024: Upcoming talks on our fundamental work on prompt compression at (i) Stanford IT Forum, hosted by Ayfer Ögzür and Tsachy Weissman, and (ii) Berkeley, hosted by Kannan Ramchandran .
Nov 2024: Amazing experience presenting our comprehensive body of work on Markovian analysis of transformers at ETH Zürich, hosted by Andreas Krause.
Sep 2024: Three papers to appear at NeurIPS 2024! One explores the fundamental limits of prompt compression and the other two provide a complete characterization of transformers when trained on Markovian inputs: Local to Global and Constant depth suffices.
Aug 2024: Excited to share that I will be giving a tutorial at NeurIPS 2024 with my amazing colleagues Bingbin Liu and Jason Lee, titled Sandbox for the Blackbox: How LLMs Learn Structured Data?