| Genegan: Learning object transfiguration and attribute subspace from unpaired data S Zhou, T Xiao, Y Yang, D Feng, Q He, W He arXiv preprint arXiv:1705.04932, 2017 | 113 | 2017 |
| Solving hard ai planning instances using curriculum-driven deep reinforcement learning D Feng, CP Gomes, B Selman arXiv preprint arXiv:2006.02689, 2020 | 29 | 2020 |
| A novel automated curriculum strategy to solve hard sokoban planning instances D Feng, CP Gomes, B Selman Advances in Neural Information Processing Systems 33, 3141-3152, 2020 | 21 | 2020 |
| A new perspective on building efficient and expressive 3D equivariant graph neural networks Y Du, L Wang, D Feng, G Wang, S Ji, CP Gomes, ZM Ma Advances in Neural Information Processing Systems 36, 2024 | 11 | 2024 |
| Training bit fully convolutional network for fast semantic segmentation H Wen, S Zhou, Z Liang, Y Zhang, D Feng, X Zhou, C Yao arXiv preprint arXiv:1612.00212, 2016 | 11 | 2016 |
| Weighted Sampling without Replacement for Deep Top- Classification D Feng, Y Du, CP Gomes, B Selman International Conference on Machine Learning, 9910-9920, 2023 | | 2023 |
| Deep Combinatorial Reasoning: From Games to Scientific Discovery D Feng Cornell University, 2023 | | 2023 |
| Left Heavy Tails and the Effectiveness of the Policy and Value Networks in DNN-based best-first search for Sokoban Planning D Feng, CP Gomes, B Selman Advances in Neural Information Processing Systems 35, 36295-36307, 2022 | | 2022 |
| Graph Value Iteration D Feng, CP Gomes, B Selman arXiv preprint arXiv:2209.09608, 2022 | | 2022 |
| The Remarkable Effectiveness of Combining Policy and Value Networks in A*-based Deep RL for AI Planning D Feng, CP Gomes, B Selman | | |
Bart SelmanProfessor of Computer Science, Cornell UniversityVerified email at cs.cornell.edu
