Recent Papers including Neural Symbolic Reasoning, Logical Reasoning, Visual Reasoning, natural language reasoning and any other topics connecting deep learning and reasoning.
[1] Yoshua Bengio,From System 1 Deep Learning to System 2 Deep Learning [pdf]
[2] Yann Lecun, Self-Supervised Learning [pdf]
[1] Saxton, David, et al. Analysing mathematical reasoning abilities of neural models. arXiv preprint arXiv:1904.01557 (2019).[pdf]
[2] Ortega, Pedro A., et al. Meta-learning of sequential strategies. arXiv preprint arXiv:1905.03030 (2019).[pdf]
[3] Lample, Guillaume, and François Charton. Deep learning for symbolic mathematics. arXiv preprint arXiv:1912.01412 (2019).[pdf]
[4] Zhuo, Tao, and Mohan Kankanhalli. Solving Raven's Progressive Matrices with Neural Networks. arXiv preprint arXiv:2002.01646 (2020).[pdf]
[5] Zheng, Kecheng, Zheng-Jun Zha, and Wei Wei. Abstract Reasoning with Distracting Features. Advances in Neural Information Processing Systems. 2019. [pdf]
[6] van Steenkiste, Sjoerd, et al. Are Disentangled Representations Helpful for Abstract Visual Reasoning?. Advances in Neural Information Processing Systems. 2019. [pdf]
[7] Dong, Honghua, et al. Neural logic machines. arXiv preprint arXiv:1904.11694 (2019). [pdf]
[8] Zhang, Chi, et al. Learning perceptual inference by contrasting. Advances in Neural Information Processing Systems. 2019.[pdf]
[9] Santoro, Adam, et al. Measuring abstract reasoning in neural networks. International Conference on Machine Learning. 2018.[pdf]
[10] Wang, Po-Wei, et al. SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver. arXiv preprint arXiv:1905.12149 (2019).
[11] Manhaeve, Robin, et al. Deepproblog: Neural probabilistic logic programming. Advances in Neural Information Processing Systems. 2018.[pdf]
[13] van Steenkiste, Sjoerd, et al. Are Disentangled Representations Helpful for Abstract Visual Reasoning?. Advances in Neural Information Processing Systems. 2019. [pdf]
[14] Dai, Wang-Zhou, et al. Bridging machine learning and logical reasoning by abductive learning. Advances in Neural Information Processing Systems. 2019. [pdf] [code]
[1] Santoro, Adam, et al. Measuring abstract reasoning in neural networks. International Conference on Machine Learning. 2018.[pdf]
[2] Zhang, Chi, et al. Raven: A dataset for relational and analogical visual reasoning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019.[pdf]
[3] Zheng, Kecheng, Zheng-Jun Zha, and Wei Wei. Abstract Reasoning with Distracting Features. Advances in Neural Information Processing Systems. 2019.[pdf]
[4] Hill, Felix, et al. "Learning to make analogies by contrasting abstract relational structure." arXiv preprint arXiv:1902.00120 (2019).[pdf]
[5] Hu, Sheng, et al. Hierarchical Rule Induction Network for Abstract Visual Reasoning. arXiv preprint arXiv:2002.06838 (2020). [pdf]
[6] Zhang, Chi, et al. Learning perceptual inference by contrasting." Advances in Neural Information Processing Systems. 2019. [pdf]
[7] van Steenkiste, Sjoerd, et al. Are Disentangled Representations Helpful for Abstract Visual Reasoning?. Advances in Neural Information Processing Systems. 2019.[pdf]
[8] Zhuo, Tao, and Mohan Kankanhalli. Solving Raven's Progressive Matrices with Neural Networks. arXiv preprint arXiv:2002.01646 (2020). [pdf]
[9] Wang, Duo, Mateja Jamnik, and Pietro Lio. Abstract diagrammatic reasoning with multiplex graph networks. (2020). [pdf]
[10] Steenbrugge, Xander, et al. Improving generalization for abstract reasoning tasks using disentangled feature representations. arXiv preprint arXiv:1811.04784 (2018). [pdf]
[1] Han, Chi, et al. Visual Concept-Metaconcept Learning. Advances in Neural Information Processing Systems. 2019. [pdf]
[2] Mao, Jiayuan, et al. Program-Guided Image Manipulators. Proceedings of the IEEE International Conference on Computer Vision. 2019.[pdf]
[3] Mao, Jiayuan, et al. The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision. arXiv preprint arXiv:1904.12584 (2019). [pdf]
[4] Tian, Yonglong, et al. Learning to infer and execute 3d shape programs. arXiv preprint arXiv:1901.02875 (2019). [pdf]
[5] Liu, Yunchao, et al. Learning to describe scenes with programs. (2018). [pdf]
[6] Yi, Kexin, et al. Neural-symbolic vqa: Disentangling reasoning from vision and language understanding. Advances in Neural Information Processing Systems. 2018. [pdf]
[1] Jaques, Miguel, Michael Burke, and Timothy Hospedales. Physics-as-inverse-graphics: Joint unsupervised learning of objects and physics from video. arXiv preprint arXiv:1905.11169 (2019). [pdf]
[2] Bakhtin, Anton, et al. Phyre: A new benchmark for physical reasoning. Advances in Neural Information Processing Systems. 2019. [pdf]
[3] Ye Y, Gandhi D, Gupta A, et al. Object-centric Forward Modeling for Model Predictive Control[J]. arXiv preprint arXiv:1910.03568, 2019. [pdf]
[4] Veerapaneni R, Co-Reyes J D, Chang M, et al. Entity Abstraction in Visual Model-Based Reinforcement Learning[J]. arXiv preprint arXiv:1910.12827, 2019.[pdf]
[5] Janner M, Levine S, Freeman W T, et al. Reasoning about physical interactions with object-oriented prediction and planning[J]. arXiv preprint arXiv:1812.10972, 2018.[pdf]
[6] Kossen J, Stelzner K, Hussing M, et al. Structured Object-Aware Physics Prediction for Video Modeling and Planning[J]. arXiv preprint arXiv:1910.02425, 2019. [pdf]
[7] Watters N, Matthey L, Bosnjak M, et al. Cobra: Data-efficient model-based rl through unsupervised object discovery and curiosity-driven exploration[J]. arXiv preprint arXiv:1905.09275, 2019.[pdf]
[8] Li Y, He H, Wu J, et al. Learning Compositional Koopman Operators for Model-Based Control[J]. arXiv preprint arXiv:1910.08264, 2019.[pdf]
[9] Kulkarni T D, Gupta A, Ionescu C, et al. Unsupervised learning of object keypoints for perception and control[C]//Advances in Neural Information Processing Systems. 2019: 10723-10733. [pdf]
[10] Kipf T, van der Pol E, Welling M. Contrastive Learning of Structured World Models[J]. arXiv preprint arXiv:1911.12247, 2019. [pdf]
[11] Chang M B, Ullman T, Torralba A, et al. A compositional object-based approach to learning physical dynamics[J]. arXiv preprint arXiv:1612.00341, 2016. [pdf]
[12] Sanchez-Gonzalez A, Godwin J, Pfaff T, et al. Learning to Simulate Complex Physics with Graph Networks[J]. arXiv preprint arXiv:2002.09405, 2020.[pdf]
[13] Battaglia P, Pascanu R, Lai M, et al. Interaction networks for learning about objects, relations and physics[C]//Advances in neural information processing systems. 2016: 4502-4510. [pdf]
[14] Watters N, Zoran D, Weber T, et al. Visual interaction networks: Learning a physics simulator from video[C]//Advances in neural information processing systems. 2017: 4539-4547. [pdf]
[15] Cranmer M, Greydanus S, Hoyer S, et al. Lagrangian Neural Networks[J]. arXiv preprint arXiv:2003.04630, 2020. [pdf]
[16] Sanchez-Gonzalez A, Heess N, Springenberg J T, et al. Graph networks as learnable physics engines for inference and control[J]. arXiv preprint arXiv:1806.01242, 2018. [pdf]
[17] Li Y, Wu J, Tedrake R, et al. Learning particle dynamics for manipulating rigid bodies, deformable objects, and fluids[J]. arXiv preprint arXiv:1810.01566, 2018.[pdf]
[1] Schlag, Imanol, and Jürgen Schmidhuber. Learning to reason with third order tensor products. Advances in neural information processing systems. 2018.[pdf]
[1] Johnson, Justin, et al. Clevr: A diagnostic dataset for compositional language and elementary visual reasoning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017. [pdf]
[2] Zellers, Rowan, et al. From recognition to cognition: Visual commonsense reasoning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019.[pdf]
[3] Zhang, Wenhe, et al. Machine Number Sense: A Dataset of Visual Arithmetic Problems for Abstract and Relational Reasoning. Pythagoras 100.300 (1818).[pdf]
[4] Santoro, Adam, et al. Measuring abstract reasoning in neural networks. International Conference on Machine Learning. 2018.[pdf]
[5] Zhang, Chi, et al. Raven: A dataset for relational and analogical visual reasoning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019.[pdf]
[6] Bakhtin, Anton, et al. Phyre: A new benchmark for physical reasoning. Advances in Neural Information Processing Systems. 2019. [pdf]
[7] Baradel, Fabien, et al. COPHY: Counterfactual Learning of Physical Dynamics. arXiv preprint arXiv:1909.12000 (2019). [pdf]