Publications Google Scholar โ†’

  • SciRAG: A Retrieval-Focused Fine-Tuning Strategy for Scientific Documents
    Charangan Vasantharajan (Advisor: Kirubarajan Thia)
    Master's Thesis (MASc), McMaster University, 2025
  • MedBERT: A Pre-trained Language Model for Biomedical Named Entity Recognition
    C Vasantharajan, KZ Tun, H Thi-Nga, S Jain, T Rong, and CE Siong
    APSIPA ASC, 2022
    Code
  • Party Extraction from Legal Contract Using Contextualized Span Representations of Parties
    S Sivapiran, C Vasantharajan, and U Thayasivam
    RANLP, 2023

Patents

System and method for Fine Tuning of Large Language Models

US Patent Application ยท 2025

B Sathianathan, L Jothivincent, S Tharumarasa, C Vasantharajan

Apparatuses, Systems, and Methods for Creating Artificial Intelligence Agents and Routes

US Patent Application ยท 2025

B Sathianathan, C Vasantharajan

Apparatuses, Systems, and Methods for Generating AI Workflows

US Patent Application ยท 2025

B Sathianathan, C Vasantharajan

Language Independent Textual Extraction

US App. 18/590,347 ยท 2024

B Sathianathan, C Vasantharajan, S Jacob

Theses

MASc, Electrical & Computer Engineering

2023 to 2025

McMaster University, Hamilton, ON

  • Thesis: SciRAG, RAG for scientific PDFs with LaTeX-equation parsing, advised by Prof. Thia Kirubarajan: 85% context recall, 94% semantic similarity, 70% GSM8k accuracy.

BSc Engineering (Hons.), Computer Science & Engineering

2018 to 2023

University of Moratuwa, Sri Lanka ยท First Class Honours

  • Thesis: entity extraction for legal contracts on a 1,000-contract dataset: 94.2% exact match, +6.2% over baseline.
ยฉ 2026 Charangan Vasantharajan