Home ➤ About ➤ Team ➤

Mr. Kavindu Warnakulasuriya

PhD Student at National University of Singapore

Aspiring Data Enthusiast | Problem Solver | Passionate Pianist
Hello there! I'm passionate about data and on a mission to make an impact. Currently, I'm on an exciting journey as a final-year undergraduate at the University of Moratuwa, exploring the world of data-driven solutions.
Research Interests: Natural Language Processing (NLP), Large Language Models (LLMs), Neural Machine Translation (NMT), Data Science
Here are a few examples of my work:

Evolution of Cooperation in LLM Agent Societies: Final year research project studying normative reasoning abilities of LLM agents in social dilemmas using the Smallville multi-agent simulation environment. We published a paper in the COINE 2025 international workshop.
Bus Arrival Prediction: This project incorporates topological features to enhance the accuracy of Bus Arrival Time Prediction and allows us to gain insights into crucial factors leading to bus delays using SHAP analysis. It's all about making your daily commute smoother and more efficient with the power of open-source collaboration. We published a paper in the esteemed IEEE ITSC 2024.

Check out my website and GitHub, displayed in my contact info, where I showcase my projects and ideas. It's like my creative playground, where I merge data with innovation.
Additionally, I am a big music fan. I very much enjoy playing the piano. I firmly believe in the power of teamwork. I thrive in collaborative environments and cherish the collective effort that goes into solving complex problems.
I approach challenges with optimism, believing every problem is an opportunity for growth. I'm not afraid to roll up my sleeves and work hard to achieve results.
I get excited about opportunities where I'm able to leverage big data to identify patterns and discover insights that have real-life impact.
Let's connect and explore the endless possibilities of data together. Whether you're a fellow data enthusiast or just curious to learn more, feel free to reach out to me at akwarnakulasuriya@gmail.com. I'm always up for a good data-driven conversation!

Keywords: Natural Language Processing | Machine Learning / Deep Learning | Sinhala |

Publications

Conference Papers

Kavindu Warnakulasuriya, Prabhash Dissanayake, Navindu De Silva, Stephen Cranefield, Bastin Tony Roy Savarimuthu, Surangika Ranathunga, and Nisansa de Silva, "Evolution of Cooperation in LLM-Agent Societies: A Preliminary Study Using Different Punishment Strategies", in Coordination, Organizations, Institutions, Norms, and Ethics for Governance of Multi-Agent Systems XVIII, Springer Nature Switzerland, 2026, pp. 115--133. doi: 10.1007/978-3-032-17542-7_7

Preprints

Surangika Ranathunga, Nisansa de Silva, Aloka Fernando, Kavindu Warnakulasuriya, Isuru Wijesiri, Menan Velayuthan, Charitha Rathnayaka, Thivaharan Varatharajan, Sajeevi Silva, Piumi Kandanaarachchi, and Uthayasanker Thayasivam, "EnSiTa-A Trilingual Multi-Domain Parallel Dataset and Benchmark for Domain-Specific Machine Translation", ResearchGate, 2026

Research Talks

04 09 2024

Using Large Language Models to Implement Normative Reasoning Capabilities of Autonomous Agents

Kavindu Warnakulasuriya, Prabhash Dissanayake, Navindu De Silva

View Info

Projects

Multi-domain Neural Machine Translation (NMT) System for Sinhala, Tamil, and English

Active

PI: Surangika Ranathunga

We propose to create a multi-domain Neural Machine Translation (NMT) System for Sinhala, Tamil, and English, the official languages of Sri Lanka.

LLM Multi-agent Systems

Active

PI: Nisansa de Silva

The LLM Multi-agent Systems project explores how large language models can be coordinated as interacting agents to perform complex reasoning, cooperation, and task execution in natural language environments.

Low-Resource Adaptation for NLP

Active

PI: Nisansa de Silva

We propose to advance natural language processing for low-resource settings by leveraging data augmentation, transfer learning, and model adaptation techniques to overcome the scarcity of annotated data and linguistic resources.

Sinhala Language Resources

Active

PI: Nisansa de Silva

We propose to build and analyze Sinhala language resources, datasets, and models to strengthen NLP research for this low-resource language, while connecting it to English and Tamil through bilingual lexicons, embeddings, and cross-lingual methods.