|
I am an MS Student in data science at UC San Diego, working on efficient LLMs and ML systems. Before I joined UCSD, I spent two amazing years as a Data/Applied Scientist at Meesho in India. I have been instrumental in developing query understanding systems (search query correction, autocomplete), multimodal information retrieval models, and ranking systems for search in e-commerce. I have expertise in developing & deploying large-scale models and data pipelines serving 130M+ monthly active users. Working on ML models serving millions of users has shown me firsthand the importance of developing accurate models and ensuring they are efficient and scalable in real-world applications. I graduated from the Indian Institute of Technology, Guwahati, in 2022 with a major in Electronics and Communication Engineering and a minor in Mathematics. I also pursued research on investigating why language models struggle with temporal and numerical reasoning on semi-structured data. |
Publications
TRANSIENTTABLES: Evaluating LLMs’ Reasoning on Temporally Evolving Semi-structured Tables
Abhilash Shankarampeta*, Harsh Mahajan*, Tushar Kataria, Dan Roth, Vivek Gupta.
(Under Review), October 2024.
[code]
Exploring the numerical reasoning capabilities of language models: A comprehensive analysis on tabular data
Mubashara Akhtar*, Abhilash Shankarampeta*, Vivek Gupta, Arpit Patil, Oana Cocarascu, Elena Simperl.
Empirical Methods in Natural Language Processing (EMNLP), December 2023.
[pdf] [code]
Enhancing Tabular Reasoning with Pattern Exploiting Training
Abhilash Shankarampeta, Vivek Gupta, Shuo Zhang.
Asia-Pacific Chapter of the Association for Computational Linguistics (AACL), November 2022.
SUKI: Structured and Unstructured Knowledge Integration Workshop at NAACL, July 2022 (non-archival).
[pdf] [homepage] [slides] [poster] [media]
Few-Shot Class Incremental Learning with Generative Feature Replay
Abhilash Shankarampeta, Koichiro Yamauchi.
International Conference on Pattern Recognition Applications and Methods (ICPRAM), February 2021.
[pdf] [code]
Blog Posts
Embedding Based Retrieval for Semantic Search at Meesho
Mahendra Singh Meena and Abhilash Shankarampeta, December, 2023.