I an a PhD candidate at Cornell University and am co-advised by Prof. Bart Selman and Prof. Carla P. Gomes. This is my Curriculum Vita.
I am broadly interested in using modern machine learning algorithms to solve hard combinatorial domains, such as PSPACE single-agent planning, plan optimization, and automated theorem proving. I aim to develop generalizable frameworks that can do long-term reasoning, global and hierarchical planning, and algorithm abstraction from plans.
I received my bachelor degree from Tsinghua University, where I was a member of Yao Class.
My main research interests lie within deep learning with cognitive aspect,
and I am particularly interested in the intersection between neuroscience and knowledge reasoning.
Publications and Manuscripts
- Dieqiao Feng, Carla P. Gomes, Bart Selman, Left Heavy Tails and the Effectiveness of the Policy and Value Networks in DNN-based best-first search for Sokoban Planning, NeurIPS, 2022.
- Dieqiao Feng, Carla P. Gomes, Bart Selman, A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances, NeurIPS, 2020.
- Dieqiao Feng, Carla P. Gomes, Bart Selman, Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement Learning, IJCAI, 2020.
- Dieqiao Feng, Carla P. Gomes, Bart Selman, Graph Value Iteration, preprint, 2022.
- Yiwei Bai, Dieqiao Feng, Carla P. Gomes, Zero Training Overhead Portfolios for Learning to Solve Combinatorial Problems and More Sustainable Computing, preprint, 2022.
- Shuchang Zhou, Taihong Xiao, Yi Yang, Dieqiao Feng, Qinyao He, Weiran He. GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data, BMVC, 2017.
- He Wen, Shuchang Zhou, Zhe Liang, Yuxiang Zhang, Dieqiao Feng, Xinyu Zhou, Cong Yao. Training Bit Fully Convolutional Network for Fast Semantic Segmentation, preprint, 2016.
Education / Experience
- 2012 - 2016: B.eng from Tsinghua University, Yao Class
- 2016.10 - Present: Research intern at Megvii (Face++), deep learning on text group
- 2015.1 - 2015.2: CUHK Undergraduate Winter School Program
- TUNet software development: product homepage
Awards
- First place in National Olympiad in Informatics (top 0.01%)
- Gold medal in ACM International Collegiate Programming Contest (ACM-ICPC)
- Google Code Gam final round 2015
