| Tacticzero: Learning to prove theorems from scratch with deep reinforcement learning M Wu, M Norrish, C Walder, A Dezfouli Advances in Neural Information Processing Systems 34, 2021 | 49 | 2021 |
| Semi-Supervised Partial Label Learning via Confidence-Rated Margin Maximization WWML Zhang | 30 | 2020 |
| Verified decision procedures for modal logics M Wu, R Goré 10th International Conference on Interactive Theorem Proving (ITP 2019), 2019 | 11 | 2019 |
| A bi-directional extensible interface between lean and mathematica RY Lewis, M Wu Journal of Automated Reasoning 66 (2), 215-238, 2022 | 9 | 2022 |
| Reinforcement learning for interactive theorem proving in HOL4 M Wu, M Norrish, C Walder, A Dezfouli 5th Conference on Artificial Intelligence and Theorem Proving, 2020 | 3 | 2020 |
| Neural Network-Guided Synthesis of Recursive List Functions N Kobayashi, M Wu International Conference on Tools and Algorithms for the Construction and …, 2023 | 1 | 2023 |
| Latent Action Space for Efficient Planning in Theorem Proving M Wu, Y Wu 6th Conference on Artificial Intelligence and Theorem Proving, 2021 | 1 | 2021 |
| Learning Heuristics for Template-based CEGIS of Loop Invariants with Reinforcement Learning M Wu, T Tsukada, H Unno, T Sekiyama, K Suenaga arXiv preprint arXiv:2107.09766, 2021 | | 2021 |
| 10th International Conference on Interactive Theorem Proving (ITP 2019) J Andronick, K Buzzard, M Dixon, M Abdulaziz, C Gretton, M Norrish, ... Schloss Dagstuhl-Leibniz-Zentrum für Informatik GmbH, 2019 | | 2019 |
Christian WalderGoogle DeepMind在 google.com 的电子邮件经过验证
