Hey there! I am a final year PhD student in Computer Science at the University of California, Los Angeles working on Natural Language Processing. I am being adviced by Prof. Nanyun Peng and Prof. Kai-Wei Chang. I’ve been awarded the Bloomberg Data Science Ph.D. Fellowship, Amazon Science Hub Fellowship, UCLA Computer Science Fellowship, and NAACL 2024 Best Paper Nomination. I am on the job market looking for active roles in Applied Research teams.

My research focuses on improving the planning and reasoning capabilities of Large Language Models (LLMs), with focus on long-context understanding and efficiency. These include, but not limited to (1) parallel exploration for efficient search for planning, (2) personalizing LLM generations through target signals, (3) using fine-tuning and preference-tuning to drive LLM efficiency, and (4) unconstraining LLM and context compression to improve long-context reasoning. I’ve applied these methods and frameworks in my works across a wide range of tasks spanning Information Extraction (IE), Question Answering (QA) and Code Generation; in a diverse set of domains like biomedical, social media, news, code; and multilingually spanning 40+ languages.

I graduated as a Masters student (MLT) from Language Technologies Institute (LTI) at Carnegie Mellon University. There, I was advised by Prof. Alan W. Black and worked on topics like style transfer and code-switched dialogue systems. Previously, I received my undergraduate degree – Bachelor of Technology in Computer Science – from IIT Bombay. As part of my thesis, I worked on Language Modelling for code-switched language under the guidance of Prof. Preethi Jyothi.

In Summer 2025, I interned at Bloomberg AI as part of my Bloomberg Data Science Internship. Previously, I have interned at Meta Gen AI (Summer 2024) and Amazon Lab 126 (Summer 2022). Before, I worked full-time for a year in the Machine Learning team at Amazon.

---

Updates