Publications
Bridging Semantics and Pragmatics in Information-Theoretic Emergent Communication, Eleonora Gualdoni, Mycal Tucker, Roger Levy, Noga Zaslavsky. SciL 2024.
An Information Bottleneck Characterization of the Understanding-Workload Tradeoff in Human-Centered Explainable AI, M. Tucker*, L Sanneman*, J. Shah. FaCCT 2024.
Human-Guided Complexity-Controlled Abstractions, M. Tucker*, A. Peng*, Eoin Kenny, Noga Zaslavsky, Pulkit Agrawal, J. Shah. NeurIPS 2023.
Increasing Brain-LLM Alignment via Information-Theoretic Compression, M. Tucker* and G. Tuckute*. NeurIPS workshop on Unifying Representations in Neural Models 2023.
Towards Interpretable Deep Reinforcement Learning with Human-friendly Prototypes, E. Kenny, M. Tucker, J. Shah. International Conference on Learning Representations 2023. (Notable paper)
Interpretable Learned Emergent Communication for Human-Agent Teams, S. Karten, M. Tucker, H. Li, S. Kailas, M. Lewis, K. Sycara. IEEE Transactions on Cognitive and Developmental Systems 2023.
Generalization and Translatability in Emergent Communication, M. Tucker, R. Levy, J. Shah, N. Zaslavsky. NeurIPS workshop on Information-Theoretic Principles in Cognitive Systems 2022. (Spotlight)
Trading off Utility, Informativeness, and Complexity in Emergent Communication, M. Tucker, R. Levy, J. Shah, N. Zaslavsky. NeurIPS 2022.
Towards Human-Agent Communication via the Information Bottleneck Principle , M. Tucker, J. Shah, R. Levy, N. Zaslavsky. RSS Workshop on Social Intelligence in Humans and Robots 2022.
Prototype Based Classification from Hierarchy to Fairness, M. Tucker, J. Shah. International Conference on Machine Learning (ICML) 2022.
When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes, M. Tucker, T. Eisape, P. Qian, R. Levy, J. Shah. North American Chapter of the Association of Computational Linguistics (NAACL) 2022.
Latent Space Alignment Using Adversarially Guided Self-Play, M. Tucker, Y. Zhou, J. Shah. International Journal of Human-Computer Interaction 2022.
Emergent Discrete Communication in Semantic Spaces, M. Tucker, H. Li, S. Agrawal, D. Hughes, M. Lewis, K. Sycara, J. Shah. NeurIPS 2021.
What if This Modified That? Syntactic Interventions via Counterfactual Embeddings, M. Tucker, P. Qian, and R. Levy. IJCNLP Findings 2021.
Adversarially Guided Self-Play for Learning Social Conventions, M. Tucker, Y. Zhou, and J. Shah. 2020.
Learning Unknown Groundings for Natural Language Interaction with Mobile Robots, M. Tucker, D. Aksaray, R. Paul, GJ Stein, and N. Roy. International Symposium of Robotics Research 2017.