Hello! I am Varun, a pre-doctoral researcher at Google DeepMind, India. I am fortunate to work with brilliant researchers in the Machine Learning Optimizations team led by Dr. Prateek Jain. I am broadly interested in making current language models reason better with fundamental solutions. Over the past few years, I have worked on a variety of problems as a budding researcher. Most recently, I worked on extracting unsupervised feedback from text to improve LLMs at various tasks with Dr. Karthikeyan Shanmugam and Dr. Arun Suggala. I also worked on speeding up LLM inference with Dr. Praneeth Netrapalli. Before that, I collaborated with Prof. Vivek Gupta on supplementing LLMs with knowledge graphs and testing the reasoning abilities of Visual LLMs. I also spent a summer at Amazon Science, modeling customer demographics through their behavioral history. My interest in machine learning and its applications stems from my relentless participation in hackathons and challenges. Along with numerous kaggle wins, my team also placed second in Amazon Machine learning challenge 2021. After working on diverse and exciting real-world problems, my curious self pursued the path of research to dive deeper into the fundamental aspects of machine learning and language. |
Education and Experience
News and Timeline
2024
-
Dec
Attending NeurIPS 2024 in Vancouver, Canada! -
Oct
Presenting Time-Reversed LLMs, an awesome work with Karthikeyan, Arun, Rahul and Sravanti,
Won the spotlight award at NeurIPS 2024! 🎉 -
Sep
Presenting FreeNets, a short work with Rahul Madhavan.
Accepted to ICOMP 2024! 🎉 -
Aug
Presenting FlowVQA, work with Shubhankar Singh and Prof. Vivek Gupta ,
Accepted to ACL 2024 Findings! 🎉 -
Feb
Presenting HiRE, an inference efficiency approach developed with Praneeth and Yashas. [Preprint]
2023
-
July
Joining Machine learning optimizations team at Google Research, India!