Joy Wongkamjan
University of Maryland wwongkam@umd.edu

University of Maryland
wwongkam@umd.edu
Hi! I am Wichayaporn Wongkamjan or Joy in short (using a nickname is very common for Thai people, so I am good with any name👍). I am currently a 4th-year Computer Science Ph.D. student at the University of Maryland and advised by Prof. Jordan Boyd Graber and Prof. Furong Huang. My research interest lies at the intersection of Reinforcement Learning, NLP, and Human-AI interactions. In recent years, I have been working on Human-AI interactions in strategic-based game (e.g. Diplomacy) studying persuasion, deception, and ensuring best practices for AI advising human for complex tasks.
AI research 🎮
As far as I remember, I have been into video games since young and consider it a permanent hobby! I have always been curious about game development and did a senior project in my Bachelor creating a 2D side-scrolling puzzle game. Later than that I was introduced to AI/ML and that really motivated me to dive deep into deep learning research.
Thanks to Prof. Jordan Boyd Graber and Prof. Furong Huang, I have a chance to join ALLAN-UMD (under DARPA-SHADE) in my 1st-2nd year of PhD student. Mostly I have been experimenting on AI communicating with humans and AI themselves. To my surprise, formulating such complex games like Diplomacy into mathematic forms is really challenging and there are estimated solutions with modern deep learning training (e.g. trained by human data, regret minimization in RL) and finetuning (e.g. finetune LLM with human preferences). Not only that, while working through that, I am also amazed by Meta’s Cicero! Behind those human-like conversations and strategies, there are more than >10 models in corporate in them and require tons of hours to train and finetune. This really motivates me and drives me to solve other problems in Diplomacy and other complex settings.
Overall, these are challenges in human-AI research that I have been looking onward:
- AI generalist as human assistance
- Human-AI corporations activating super-human performance
- Improving AI communication strategys to be on par with humans
news
May 30, 2025 | Our paper CTRL-D is accepted ACL Findings 2025! |
---|
selected publications
- What if Red Can Talk? Dynamic Dialogue Generation Using Large Language ModelsWordplay: When Language Meets Games (ACL Workshop), 2024
- Live in the Moment: Learning Dynamics Model Adapted to Evolving PolicyInternational Conference on Machine Learning (ICML) , 2023