Venktesh Viswanathan (Venktesh V)

I am a Biträdande lektor (Assistant Professor) at Stockholm University. My research aims to develop robust and efficient pipelines for complex knowledge intensive tasks to assist in wide range of real-world applications like healthcare, education, research and tackling disinformation. My research his entails building robust and efficient Retrieval Augmented Generation (RAG) pipelines powered by Large Language Models (LLMs) through theoretically grounded advances in Machine Learning (ML) that bridge the retrieval and reasoning gaps. Towards realizing this vision, I have developed theoretically grounded sample-efficient algorithms for compute-optimal test time scaling at retrieval and reasoning stages. My work also involves developing robust LLM-feedback approaches based on uncertainty quantification to improve retrieval and reasoning at inference time. The resulting works have been published at ICML, WWW, WSDM, ECIR, CIKM, EMNLP, NAACL and SIGIR. I also regularly serve as Reviewer for NAACL,ACL,EMNLP,SIGKDD,SIGIR,AAAI,CIKM,WSDM,WWW,ECIR. Apart from publications my work has been deployed at scale for real-world impactful applications like Live-factchecking of US presidential and EU debates by Factiverse AI, Norway.

Previously I was a Postdoctoral Researcher in the Web Information Systems (WIS) at Delft University of Technology (TU Delft).

During my PhD, I worked on building efficient NLP and IR pipelines for content curation in online learning platforms. I was one fo the first members of Applied Data Science lab (https://ads-ai.github.io/) at IIIT-D. I independently executed several research projects such as concept retrieval, content tagging, question generation and question complexity identification from conceptualization to execution in an end to end manner. During my PhD, I was the sole first author in 4 full papers and co first-author in 2 other papers at top venues like IEEE TKDE ‘24, CIKM ‘23, ECML-PKDD’21 ‘22, AIED ‘22 and ECIR ‘22.