Scholar
Kumar Tanmay
Google Scholar ID: vNKua5AAAAAJ
MIT | Harvard University | Microsoft Research | Stanford University | IIT Kharagpur
Citations & Impact
Citations
658
H-index
9
i10-index
9
Publications
15
Co-authors
12
list available
Publications
Resume (English only)
Academic Achievements
- Published multiple research papers on Large Language Models, including 'sPhinX: Sample Efficient Multilingual Instruction Fine-Tuning Through N-shot Guided Prompting' and 'Do Moral Judgment and Reasoning Capability of LLMs Change with Language? A Study using the Multilingual Defining Issues Test'. Some papers have been accepted at conferences such as LREC-COLING 2024 and EACL 2024.
Research Experience
- Graduate Research Assistant in the Multisensory Intelligence Research Group at MIT Media Lab, supervised by Prof. Paul Liang; previously, Graduate Research Assistant at Harvard’s Data and Knowledge Exploration Lab (DTaK), co-supervised by Prof. Finale Doshi-Velez and Prof. Wei Wei Pan; worked as a Research Fellow/Engineer at Microsoft Research India (R&D) as part of the Turing team.
Education
- Graduated with a Bachelor's degree in Electrical Engineering, and minor in Computer Science, from IIT Kharagpur in 2022; currently pursuing a Master's degree in Computer Science and Statistics at Harvard University.
Background
- Currently pursuing a Master's degree in Computer Science and Statistics at Harvard University, specializing in Artificial Intelligence. Research focuses on understanding the limitations and capabilities of contemporary AI systems, particularly Large Language Models (LLMs), through mechanistic interpretability and model behavior control techniques like model editing and representation engineering. Aims to ensure these models are secure and unbiased.
Miscellany
- Taught a workshop course in Practical NLP and Large Language Models (LLMs) for bachelor's students at the Indian Institute of Science (IISc) as part of Kotak-IISc AI-ML Centre in September 2023.
