Dexun Li dexunli.2019@phdcs.smu.edu.sg | |

About

Greetings! I am currently a fifth-year Ph.D. candidate at the School of Computing and Information Systems, My research interests include Multi-armed Bandits, Reinforcement Learning, Optimization, RLHF, and Generative Models. My primary objective is to develop robust models that consider real-world constraints, thereby facilitating efficient decision-making in environments with limited resources. Currently, I am particularly enthusiastic about the exploration and understanding of the Large Language Model’s immense potential in a wide range of practical applications.

I am very fortunate to be advised by Prof. Pradeep VARAKANTHAM of CARE.AI Lab from the School of Computing and Information Systems, SMU. You can find my CV here: Curriculum Vitae. I'm actively seeking new job opportunities and I appreciate you taking the time to visit my personal homepage. Feel free to reach out to me!
-

News

[12/2023] I have finished my internship at Search&Recommendation AI lab!

[5/2023] One paper accepted to IJCAI 2023.

[12/2022] I have passed my Ph.D. thesis proposal :)

Papers

A Hierarchical Approach to Environment Design with Generative Trajectory Modeling
Dexun Li, Pradeep Varakantham
Preprint, 2023
(Paper) (Website) (Code)

Marginal Benefit Induced Unsupervised Environment Design
Dexun Li, Wenjun Li, Pradeep Varakantham
Preprint, 2024
(Paper) (Website)

Avoiding Starvation of Arms in Restless Multi-Armed Bandits
Dexun Li, Pradeep Varakantham
The International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2023 premier paper
(ArXiv)

Workshop Papers

Hidden State Approximation in Recurrent Neural Networks Using Continuous Particle Filtering
Dexun Li, Pradeep Varakantham
IJCAI, DSO, 2021
(ArXiv) (Code)