Publication

Found 13 results
Author Title Type [ Year(Asc)]
Filters: Author is Kevin A Smith  [Clear All Filters]
2022
Li, Y. et al. An approximate representation of objects underlies physical reasoning. psyArXiv (2022). at <https://psyarxiv.com/vebu5/>
2021
Shu, T. et al. AGENT: A Benchmark for Core Psychological Reasoning. Proceedings of the 38th International Conference on Machine Learning (2021).
Allen, K. et al. Meta-strategy learning in physical problem solving: the effect of embodied experience. bioRxiv (2021).PDF icon 2021.07.08.451333v2.full_.pdf (3.05 MB)
Bass, I., Smith, K. A., Bonawitz, E. & Ullman, T. Partial Mental Simulation Explains Fallacies in Physical Reasoning. psyArXiv (2021). at <https://psyarxiv.com/y4a8x>
Du, Y., Smith, K. A., Ullman, T., Tenenbaum, J. B. & Wu, J. Unsupervised Discovery of 3D Physical Objects. International Conference on Learning Representations (2021). at <https://openreview.net/forum?id=lf7st0bJIA5>
2020
Smith, K. A. et al. The fine structure of surprise in intuitive physics: when, why, and how much?. Proceedings of the 42th Annual Meeting of the Cognitive Science Society - Developing a Mind: Learning in Humans, Animals, and Machines, CogSci 2020, virtual, July 29 - August 1, 2020 (Denison, S., Mack, M., Xu, Y. & Armstrong, B. C.) (2020). at <https://cogsci.mindmodeling.org/2020/papers/0761/index.html>
Allen, K., Smith, K. A. & Tenenbaum, J. B. Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoning. Proceedings of the National Academy of Sciences 201912341 (2020). doi:10.1073/pnas.1912341117PDF icon 1912341117.full_.pdf (2.15 MB)
2019
Smith, K. A. et al. Modeling Expectation Violation in Intuitive Physics with Coarse Probabilistic Object Representations. 33rd Conference on Neural Information Processing Systems (NeurIPS 2019) (2019). at <http: //physadept.csail.mit.edu/>PDF icon ADEPT_NeurIPS.pdf (11.07 MB)
2018
Toussaint, M., Allen, K., Smith, K. A. & Tenenbaum, J. B. Differentiable physics and stable modes for tool-use and manipulation planning. Robotics: Science and Systems 2018 (2018).PDF icon ToussaintEtAl_DiffPhysStable.pdf (1.97 MB)
Belbute-Peres, Fde Avila, Smith, K. A., Allen, K., Tenenbaum, J. B. & Kolter, Z. End-to-end differentiable physics for learning and control. Advances in Neural Information Processing Systems 31 (NIPS 2018) (2018).PDF icon 7948-end-to-end-differentiable-physics-for-learning-and-control.pdf (794.17 KB)
2017
Gerstenberg, T., Zhou, L., Smith, K. A. & Tenenbaum, J. B. Faulty Towers: A counterfactual simulation model of physical support. Proceedings of the 39th Annual Conference of the Cognitive Science Society (2017).PDF icon Faulty Towers A counterfactual simulation model of physical support, Gerstenberg et al., 2017.pdf (8.75 MB)
2016
Peres, F., Smith, K. A. & Tenenbaum, J. B. Rapid Physical Predictions from Convolutional Neural Networks. Neural Information Processing Systems, Intuitive Physics Workshop (2016). at <http://phys.csail.mit.edu/papers/9.pdf>PDF icon Rapid Physical Predictions - NIPS Physics Workshop Poster (1.47 MB)
2014
Amir, N. et al. Abstracts of the 2014 Brains, Minds, and Machines Summer Course. (2014).PDF icon CBMM-Memo-024.pdf (2.86 MB)