About
I am a Master’s student in Computer Science at the University of North Carolina at Chapel Hill, with a strong background in machine learning, fairness-aware AI, and large language models. My research focuses on developing fair and robust machine learning systems, with particular emphasis on bias mitigation in personality computing and multi-modal learning.
Research Interests
My research focuses on fairness-aware machine learning and large language model alignment. I am particularly interested in:
- Bias Mitigation in Multi-modal ML Models: Developing novel fairness loss functions and neural architecture search methods to improve generalization across demographic groups
- Personality Computing: Building personalized models for automatic personality recognition using deep learning architectures
- LLM Evaluation and Alignment: Evaluating and improving fairness, robustness, and safety of large language models across multiple languages
- Multi-Persona Debate Simulation: Creating frameworks to assess environmental and ethical alignment in LLMs
My work combines deep learning, neural architecture search, and fairness metrics to address bias and improve model generalization in real-world applications.
Current Position
Master of Science in Computer Science
Department of Computer Science
University of North Carolina at Chapel Hill
Aug 2025 – May 2027 (Expected)
Education
- M.S. in Computer Science, University of North Carolina at Chapel Hill (GPA: 4.0/4.0), Aug 2025 – May 2027
- B.S. in Computer Science and Engineering, National Institute of Technology, Tiruchirappalli (GPA: 3.9/4.0, Rank 9/150), May 2019 – May 2023
Recent News
- Apr 2026: Paper “When Identity Overrides Incentives: Representational Choices as Governance Decisions in Multi-Agent LLM Systems” accepted at ACM FAccT 2026!
- Jan 2026: Paper “When Identity Overrides Incentives: Representational Choices as Governance Decisions in Multi-Agent LLM Systems” posted on arXiv (arXiv:2601.10102)
- Dec 2024: Paper “Towards Generalised and Incremental Bias Mitigation in Personality Computing” accepted at IEEE Transactions on Affective Computing
- Aug 2023: Paper “Optimized Reversible Cellular Automata Based Clustering” published at AUTOMATA’23
- Oct 2023: Paper “Generalised Bias Mitigation for Personality Computing” presented at ACM MM conference
- Oct 2022: Paper “Learning Personalised Models for Automatic Self-Reported Personality Recognition” published in PMLR
Contact
Feel free to reach out if you’re interested in collaboration, have questions about my research, or would like to discuss opportunities. You can find my contact information in the sidebar or on my CV.