| Interpreting and boosting dropout from a game-theoretic view H Zhang, S Li, Y Ma, M Li, Y Xie, Q Zhang arXiv preprint arXiv:2009.11729, 2020 | 46 | 2020 |
| Does a neural network really encode symbolic concepts? M Li, Q Zhang International conference on machine learning, 20452-20469, 2023 | 20 | 2023 |
| Interpreting and disentangling feature components of various complexity from DNNs J Ren, M Li, Z Liu, Q Zhang International Conference on Machine Learning, 8971-8981, 2021 | 20 | 2021 |
| Defining and quantifying the emergence of sparse concepts in dnns J Ren, M Li, Q Chen, H Deng, Q Zhang Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2023 | 18 | 2023 |
| Visualizing the Emergence of Intermediate Visual Patterns in DNNs M Li, S Wang, Q Zhang Thirty-Fifth Conference on Neural Information Processing Systems, 2021 | 12 | 2021 |
| Towards axiomatic, hierarchical, and symbolic explanation for deep models J Ren, M Li, Q Chen, H Deng, Q Zhang | 11 | 2021 |
| Defining and quantifying and-or interactions for faithful and concise explanation of dnns M Li, Q Zhang arXiv preprint arXiv:2304.13312, 2023 | 5 | 2023 |
| Explaining how a neural network play the go game and let people learn H Zhou, H Tang, M Li, H Zhang, Z Liu, Q Zhang arXiv preprint arXiv:2310.09838, 2023 | 3 | 2023 |
| Towards theoretical analysis of transformation complexity of ReLU DNNs J Ren, M Li, M Zhou, SH Chan, Q Zhang International Conference on Machine Learning, 18537-18558, 2022 | 2 | 2022 |
| Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts? W Shen, L Cheng, Y Yang, M Li, Q Zhang arXiv preprint arXiv:2304.01083, 2023 | 1 | 2023 |
