Published multiple academic papers such as 'Efficient Encoders for Streaming Sequence Tagging' (EACL 2023), 'Can Sequence-to-Sequence Transformers Naturally Understand Sequential Instructions?' (StarSEM 2023), etc.
Research Experience
Worked at Google, dedicated to improving the quality of the Gemini model and participated in several research projects, including developing features that enhanced the natural conversation experience between users and the Google Assistant.
Education
Earned a Ph.D. from the University of Pennsylvania under the guidance of Prof. Dan Roth; also holds an undergraduate degree in Computer Science and Engineering from the Indian Institute of Technology at Kanpur.
Background
A Staff Research Scientist and Manager at Google, focusing on improving the core model quality of Gemini, with a particular emphasis on enhancing its ability to follow instructions and engage in multi-turn conversations. Prior to this, contributed to the development of features that enabled users to have more natural conversations with the Google Assistant.