Viswonathan Manoranjan

Chapel Hill, NC

I am a Master’s student in Computer Science at the University of North Carolina at Chapel Hill. I work on multimodal models of human behavior, including gesture, affect, and personality, with a focus on whether these models represent people faithfully or only plausibly. My thesis research is with Prof. Xiaoming Liu (Computer Vision Lab) on semantic evaluation of co-speech gesture generation.

I am also a Visiting Scholar at the University of Texas at Austin for Summer 2026, working with Prof. Desmond Ong on diagnostic sycophancy in clinical LLMs.

I have had the pleasure of collaborating with researchers working on LLMs and related areas, including Prof. Tianlong Chen (Trustworthy AI; Fall 2025, Spring 2026) and Prof. Snigdha Chaturvedi (Social NLP; Fall 2025, Spring 2026). Earlier, I worked with Prof. Neil Gaikwad (Society-Centered AI).

Previously, I was a Software Engineer at Wells Fargo, after an internship there in Consumer and Small Business Banking. I graduated from the National Institute of Technology, Tiruchirappalli ranked top 10 in 2023, during which I had the opportunity to collaborate with Prof. Kamalika Bhattacharjee (Cellular Automata), Prof. Hanan Salam (Affective Computing), and Prof. Oya Celiktutan (Social Robotics).

I am always glad to hear from people working on evaluation, alignment, or multimodal human behavior. Feel free to reach out.

Outside of research, I am a self-taught pianist, an avid soccer player, and a gym enthusiast.

Recent News

Research

My research interests are in multimodal human behavior, semantic evaluation of generative models, and language model alignment and evaluation.

2026

2. Manoranjan,V.,&Gaikwad,S. (2026). When Identity Overrides Incentives: Representational Choices as Governance Decisions in Multi-Agent LLM Systems. In Proceedings of the ACM Conference on Fairness, Accountability, and Transparency.
   Link
4. Manoranjan,V.,Gupta,A.,Vijjini,A., and 2 more (2026). SHARD: Safe and Helpful Alignment via Self-Reframing Distillation. In Findings of the Association for Computational Linguistics: EMNLP 2026.
   To appear

2024

2. Jiang*,J.,Manoranjan*,V.,Salam,H., and 1 more (2024). Towards Generalised and Incremental Bias Mitigation in Personality Computing. IEEE Transactions on Affective Computing, 15(4), 2192–2203. * Equal contribution
   Link

2023

2. Jiang*,J.,Manoranjan*,V.,Salam,H., and 1 more (2023). Generalised Bias Mitigation for Personality Computing. In Proceedings of the 1st International Workshop on Multimodal and Responsible Affective Computing, ACM Multimedia 2023. * Equal contribution
   Link
4. Manoranjan,V.,Rao,G.,Vaidhianathan,S., and 1 more (2023). Optimized Reversible Cellular Automata Based Clustering. In Cellular Automata and Discrete Complex Systems. AUTOMATA 2023. Springer.
   Link

2022

2. Salam,H.,Manoranjan,V.,Jiang,J., and 1 more (2022). Learning Personalised Models for Automatic Self-Reported Personality Recognition. In Understanding Social Behavior in Dyadic and Small Group Interactions. PMLR.
   Link