Pranjal Aggarwal

Senior Undergrad@Indian Institute of Technology, Delhi

prof_pic2.jpg

I am a final-year undergraduate at IIT Delhi, My research interests lies primarily in enhancing the reasoning and code generation capabilities of deep learning models [1], improving the efficiency and cost-quality optimization of foundational models [2], and studying and improving learning methods for foundational models [3]. I am also interested in applications of Machine Learning and currently also working on Generative Engines, the new paradigm of search [4]. I am currently being advised by Prof. Mausam. I am also currently working under the guidance of Prof. Karthik Narasimhan. Previously I have been fortunate to be advised by Prof. Chetan Arora, Prof. Krithika Rangarajan and Prof. Pengtao Xie.

news

Nov 16, 2023 Our pre-print : “GEO: Generative Engine Optimization’ is now available! Find it here. We propose a new task of content optimization in upcoming Generative Engines!
Oct 22, 2023 Our Work: “Automix: Automatically mixing Language Models’ accepted in RoFO-Mo Workshop @ Neurips’23. Check it here.
Oct 7, 2023 Our Paper: “Let’s Sample Step by Step: Adaptive-Consistency for Efficient Reasoning & Coding with LLMs’ accepted in Empirical Methods in Natural Language Processing ‘23 (Oral).
May 30, 2023 Our Paper: “Let’s Sample Step by Step: Adaptive-Consistency for Efficient Reasoning with LLMs’ accepted in ACL’23: NLRSE Workshop.
Apr 28, 2023 Our work SemSup-XC is accepted at ICML 2023. SemSup-XC achieves state-of-the-art results on extreme classification.
Dec 22, 2022 Presenting Winning Solution for MLMAC (ML Model Attribution Challenge) at Secure & Trustworthy Machine Learning’23.