Hello world!
I am the Lead ML Engineer at ParadigmAI. In 2026 I was a visiting researcher at KIXLAB, the human–computer interaction lab at KAIST. I also lead the second phase of the Colombo HCI Lab's deepfake detection project for South Asia. I graduated from UCSC with an honours degree in Computer Science, and I have submitted my M.Sc thesis in Data Science & AI at UoM, on prescribed perception for open-world reinforcement learning agents; the defense is still to come.
My research interests primarily lie in the intersection of reinforcement learning and computer games. I am particularly interested in studying about intelligent agents that improve with experience.
In a much broader sense, I like to work on theoretical and application research topics involving artificial intelligence.
Research Interests
Reinforcement Learning | Machine Learning | Artificial Intelligence | Game Theory | Computer Games | Computer VisionNews
I attended the Google Summer of Code 2026 Mentor Summit in Munich, Germany, representing C2SI as a GSoC mentor. Google fully funded my attendance.
I started leading the second phase of the deepfake detection project at the Colombo HCI Lab, collecting South Asian deepfake data and building detection models on it. Our phase 1 survey of deepfake detection for South Asia is now under review at ACM Computing Surveys.
I concluded my visiting research position at KIXLAB. The main output is Workflow Editor, a prototype that pairs an agent's written report with the provenance graph behind it, so every figure stays traceable to the computation that produced it.
I submitted my M.Sc thesis at UoM, "From Sensors to Perception: Prescription over Search in Open-World Reinforcement Learning Agents", supervised by Dr. Thanuja D. Ambegoda.
My paper Affordable Winner's-Curse Correction: Paired-Offset Reevaluation for Hyperparameter Search on a Single GPU was accepted at the GlobalSouthAI workshop at IJCAI-ECAI 2026, held in Bremen, Germany.