Interpretability is a Kind of Safety: An Interpreter-based Ensemble for Adversary Defense J Wang, Y Wu, M Li, X Lin, J Wu, C Li Proceedings of the 26th ACM SIGKDD International Conference on Knowledge …, 2020 | 14 | 2020 |
Learning Generalizable Behavior via Visual Rewrite Rules Y Xie, M Li, S Yu, M Littman arXiv preprint arXiv:2112.05218, 2021 | 1 | 2021 |
Towards Sample Efficient Agents through Algorithmic Alignment (Student Abstract) M Li, ML Littman Proceedings of the AAAI Conference on Artificial Intelligence 35 (18), 15827 …, 2021 | 1* | 2021 |
Causally Aligned Curriculum Learning M Li, J Zhang, E Bareinboim The Twelfth International Conference on Learning Representations (ICLR 2024), 2023 | | 2023 |
Are L2 adversarial examples intrinsically different? M Li, J Wang, Y Wu arXiv preprint arXiv:2002.12527, 2020 | | 2020 |
Replication of “When to Trust Your Model: Model-Based Policy Optimization” X Jiang, Q Chen, S Han, M Li, J Dong, R Zhang | | |