Awesome Abstraction and Reasoning

A curated list of abstraction and reasoning. Inspired by awesome-deep-vision, awesome-adversarial-machine-learning, awesome-deep-learning-papers, awesome-architecture-search, awesome-self-supervised-learning, awesome-self-supervised-learning-for-graphs, awesome-graph-self-supervised-learning-based-recommendation

Maintainers - Ais, Andreas

⚠️ This repo is still in the process of curating, some links might be dropped in the next update. Please use this list with caution

Please feel free to contact us if you have any trouble or discussion via pull requests

[TOC]

Table of Contents

• Papers
  • ARC-based
  • Bongard
  • Natural Language for Visual Reasoning
  • Raven's Progressive Matrices
  • Additional Reads
• Videos
• Other Materials
  • Kaggle
  • Books
  • Blogs

Papers

ARC-based

1. Chollet, F. (2019). On the Measure of Intelligence. arXiv. https://doi.org/10.48550/arXiv.1911.01547 (repo)
2. Acquaviva, S., Pu, Y., Kryven, M., Sechopoulos, T., Wong, C., Ecanow, G. E., Nye, M., Tessler, M. H., & Tenenbaum, J. B. (2021). Communicating Natural Programs to Humans and Machines. arXiv. https://doi.org/10.48550/arXiv.2106.07824 (repo)
3. Ferré, S. (2021). First Steps of an Approach to the ARC Challenge based on Descriptive Grid Models and the Minimum Description Length Principle. arXiv. https://doi.org/10.48550/arXiv.2112.00848

Bongard

1. Nie, W., Yu, Z., Mao, L., Patel, A. B., Zhu, Y., & Anandkumar, A. (2020). Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning. arXiv. https://doi.org/10.48550/arXiv.2010.00763 (repo)

Natural Language for Visual Reasoning

1. IconQA: Lu, P., Qiu, L., Chen, J., Xia, T., Zhao, Y., Zhang, W., Yu, Z., Liang, X., & Zhu, S. (2021). IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning. arXiv. https://doi.org/10.48550/arXiv.2110.13214 (repo) (website)
2. GQA: Hudson, D. A., & Manning, C. D. (2019). GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering. arXiv. https://doi.org/10.48550/arXiv.1902.09506 (repo) (website)
3. NLVR: Suhr, A., Zhou, S., Zhang, A., Zhang, I., Bai, H., & Artzi, Y. (2018). A Corpus for Reasoning About Natural Language Grounded in Photographs. arXiv. https://doi.org/10.48550/arXiv.1811.00491 (repo) (Website)
4. DVQA: Kafle, K., Price, B., Cohen, S., & Kanan, C. (2018). DVQA: Understanding Data Visualizations via Question Answering. arXiv. https://doi.org/10.48550/arXiv.1801.08163 (repo) (website)
5. FigureQA: Kahou, S. E., Michalski, V., Atkinson, A., Kadar, A., Trischler, A., & Bengio, Y. (2017). FigureQA: An Annotated Figure Dataset for Visual Reasoning. arXiv. https://doi.org/10.48550/arXiv.1710.07300 (website) (repo)
6. CLEVR: Johnson, J., Hariharan, B., Zitnick, C. L., & Girshick, R. (2016). CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning. arXiv. https://doi.org/10.48550/arXiv.1612.06890 (website) (repo)
7. VQA: Goyal, Y., Khot, T., Batra, D., & Parikh, D. (2016). Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering. arXiv. https://doi.org/10.48550/arXiv.1612.00837 (website)
8. VQA: Zhang, P., Goyal, Y., Batra, D., & Parikh, D. (2015). Yin and Yang: Balancing and Answering Binary Visual Questions. arXiv. https://doi.org/10.48550/arXiv.1511.05099 (website)
9. VQA: Agrawal, A., Lu, J., Antol, S., Mitchell, M., Zitnick, C. L., Batra, D., & Parikh, D. (2015). VQA: Visual Question Answering. arXiv. https://doi.org/10.48550/arXiv.1505.00468 (website)

Raven's Progressive Matrices

1. I-RAVEN: Hu, S., Ma, Y., Liu, X., Wei, Y., & Bai, S. (2020). Stratified Rule-Aware Network for Abstract Visual Reasoning. arXiv. https://doi.org/10.48550/arXiv.2002.06838 (repo)
2. RAVEN: Zhang, C., Gao, F., Jia, B., Zhu, Y., & Zhu, S. (2019). RAVEN: A Dataset for Relational and Analogical Visual rEasoNing. arXiv. https://doi.org/10.48550/arXiv.1903.02741 (website) (repo)
3. PGM: Barrett, D. G., Hill, F., Santoro, A., Morcos, A. S., & Lillicrap, T. (2018). Measuring abstract reasoning in neural networks. arXiv. https://doi.org/10.48550/arXiv.1807.04225 (website) (repo)

Additional Reads

1. Christina M. Funke, Judy Borowski, Karolina Stosio, Wieland Brendel, Thomas S. A. Wallis, Matthias Bethge; Five points to check when comparing visual perception in humans and machines. Journal of Vision 2021;21(3):16. doi: https://doi.org/10.1167/jov.21.3.16.
2. Miikkulainen, R., Forrest, S. A biological perspective on evolutionary computation. Nat Mach Intell 3, 9–15 (2021). https://doi.org/10.1038/s42256-020-00278-8

Videos

1. Learn Data Science by Doing Kaggle Competitions: Abstraction and Reasoning Challenge (ARC)
2. Modular Learning and Reasoning on ARC

Other Materials

Kaggle

1. Abstraction and Reasoning Challenge

• Solution by Alexander Fritzler (repo)

Books

1. Andrews, K. (2020). How to Study Animal Minds (Elements in the Philosophy of Biology). Cambridge: Cambridge University Press. doi:10.1017/9781108616522

Blogs

1. Padilla, P (2022) .The Abstraction and Reasoning Challenge (ARC), Pablo Padilla's Blog. Link

Contribute

Contributions welcome! Read the contribution guidelines first.