Changyu Chen

I am a Ph.D. candidate in Computer Science at Singapore Management University (SMU), fortunate to be advised by Prof. Pradeep Varakantham and Prof. Arunesh Sinha. Prior to this, I earned my Master's degree in Systems and Project Management from Nanyang Technological University (NTU), and my Bachelor's degree in Civil Engineering from Zhejiang University.

Research: My research interests lie in the intersection of generative modelling and autonomous decision making.

News

June 18, 2024	Recent work: Bootstrapping Language Models with DPO Implicit Rewards is accepted by ICML 2024 Workshop on Models of Human Feedback for AI Alignment.
Dec 22, 2023	I received Singapore Data Science Consortium Dissertation Research Fellowship 2023 from Singapore Data Science Consortium.
Sep 22, 2023	Recent work: Generative Modelling of Stochastic Actions with Arbitrary Constraints in Reinforcement Learning is accepted by NeurIPS 2023.
Aug 21, 2023	I joined Sea AI lab (SAIL) as a research intern and my research is related to alignment of large language models.
Dec 01, 2021	Recent work: Multiscale Generative Models: Improving Performance of a Generative Model Using Feedback from Other Dependent Generative Models is accepted by AAAI 2022.
March 21, 2021	I received Academic Excellence Award 2021 from NTU.

Preprints

Bootstrapping Language Models with DPO Implicit Rewards
Changyu Chen^*, Zichen Liu^*, Chao Du^†, Tianyu Pang, Qian Liu, Arunesh Sinha^†, Pradeep Varakantham^†, Min Lin
arXiv, 2024
arXiv / code

Selected Publications

	Generative Modelling of Stochastic Actions with Arbitrary Constraints in Reinforcement Learning Changyu Chen, Ramesha Karunasena, Thanh Hong Nguyen, Arunesh Sinha, Pradeep Varakantham NeurIPS, 2023 project page / arXiv / code
	Multiscale Generative Models: Improving Performance of a Generative Model Using Feedback from Other Dependent Generative Models Changyu Chen, Avinandan Bose, Shih-Fen Cheng, Arunesh Sinha, AAAI, 2022 arXiv / code

^† denotes corresponding author
^* denotes equal contribution

Thank Jon Barron for sharing his website's source code.