Joel is a senior staff research scientist at Google DeepMind and visiting professor at King's College London. He obtained his PhD from MIT where he studied computational neuroscience and machine learning with Tomaso Poggio. Joel is interested in reverse engineering human biological and cultural evolution to inform the development of artificial intelligence that is simultaneously human-like and human-compatible. In particular, Joel believes that theories of cooperation from fields like cultural evolution and institutional economics can be fruitfully applied to inform the development of ethical and effective artificial intelligence technology.

The Concordia Generative Social Simulation Platform

Concordia uses language models to create open-ended world simulations that work like tabletop role-playing games. We use it to construct rich agent-based models where simulated agents can interact through a natural language interface. We build Concordia environments to study the emergence of social-scale phenomena from the interactions of complex and capable individuals e.g. cooperation in mixed-motive social dilemma situations where the agents can talk to each other and interact with their world in natural language. We also use it as a playground to explore cognitive modeling ideas with generative agents.

Concordia is the context in which we developed our theory of appropriateness, and it is a core piece of infrastructure supporting our further work in this area. Of course, one need not buy our theory to use the platform. Concordia is helpful as a modeling platform for any part of computational social-cognitive science where it is desirable to have (1) incompletely specified game structures that may or may not feature explicit reward signals, (2) fully open-ended interactions (i.e.,  "large worlds" in the sense of Savage), (3) relatively complex agents, capable of conversing with one another in natural language, and (4) flexible mixing per environment of hand-coded "grounded" variables and open-ended "hallucinated" variables.

Concordia is open source: github repo.

Publications

• 1. Hertz, U., Köster, R., Janssen, M. and Leibo, J.Z. Beyond the matrix: Experimental approaches to studying cognitive agents in social-ecological systems (2025). Cognition 254, 105993.

  2. Guo, Z., Willis, R., Shi, S., Tomilin, T., Leibo, J.Z. and Du, Y. SocialJax: An Evaluation Suite for Multi-agent Reinforcement Learning in Sequential Social Dilemmas (2025). arXiv preprint arXiv:2503.14576 [cs.LG].

  3. Hammond L, Chan A, Clifton J, Hoelscher-Obermaier J, Khan A, McLean E, Smith C, Barfuss W, Foerster J, Gavenčiak T, Han TA, Hughes E, Kovařík V, Kulveit J, Leibo JZ, Oesterheld C, de Witt CS, Shah N, Wellman M, Bova P, Cimpeanu T, Ezell C, Feuillade-Montixi Q, Franklin M, Kran E, Krawczuk I, Lamparth M, Lauffer N, Meinke A, Motwani S, Reuel A, Conitzer V, Dennis M, Gabriel I, Gleave A, Hadfield G, Haghtalab N, Kasirzadeh A, Krier S, Larson K, Lehman J, Parkes DC, Piliouras G, Rahwan I. Multi-Agent Risks from Advanced AI (2025). arXiv preprint arXiv:250214143 [cs.MA].

  4. Sunehag, P. and Leibo, J.Z. Simulation Streams: A Programming Paradigm for Controlling Large Language Models and Building Complex Systems with Generative AI (2025). arXiv preprint arXiv:2501.18668 [cs.AI].

  5. Willis, R., Du, Y., Leibo, J.Z. and Luck, M. Will Systems of LLM Agents Cooperate: An Investigation into a Social Dilemma (2025). arXiv preprint arXiv:2501.16173 [cs.MA].

  6. Hou, X., Yuan, J., Leibo, J.Z. and Jaques, N. InvestESG: A multi-agent reinforcement learning benchmark for studying climate investment as a social dilemma (2025). ICLR 2025.

  7. Willis, R., Du, Y., Leibo, J.Z. and Luck, M. Quantifying the Self-Interest Level of Markov Social Dilemmas (2025). arXiv preprint arXiv:2501.16138 [cs.GT].

  8. Leibo, J.Z., Vezhnevets, A.S., Diaz, M., Agapiou, J.P., Cunningham, W.A., Sunehag, P., Haas, J., Koster, R., Duéñez-Guzmán, E.A., Isaac, W.S., Piliouras, G., Bileschi, S.M., Rahwan, I., Osindero, S. A theory of appropriateness with applications to generative artificial intelligence (2024). arXiv preprint arXiv:2412.19010 [cs.AI].

  9. Cook, J., Lu, C., Hughes, E., Leibo, J.Z. and Foerster, J. Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning (2024). Advances in Neural Information Processing Systems (NeurIPS), Vancouver BC. 2024.

  10. Trivedi, R., Khan, A., Clifton, J., Hammond, L., Duéñez-Guzmán, E.A., Chakraborty, D., Agapiou, J.P., Matyas, J., Vezhnevets, S., Pásztor, B., Ao, Y., Younis, O.G., Huang, J., Swain, B., Qin, H., Deng, M., Deng, Z., Erdoganaras, U., Jaques, N., Foerster J.N., Conitzer, V., Hernandez-Orallo, J., Hadfield-Menell, D., and Leibo, J.Z. Melting Pot Contest: Charting the Future of Generalized Cooperative Intelligence (2024). In The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track.

  11. Kurth-Nelson Z, Sullivan S, Leibo J.Z., Guitart-Masip M. Dynamic diversity is the answer to proxy failure (2024). Behavioral and Brain Sciences, 47, E77. doi:10.1017/S0140525X23002923

  12. Diaz, M., Leibo, J.Z. and Paull, L., Milnor-Myerson Games and The Principles of Artificial Principal-Agent Problems (2024). In Finding the Frame: An RLC Workshop for Examining Conceptual Frameworks.

  13. Amirova, A., Fteropoulli, T., Ahmed, N., Cowie, M.R. and Leibo, J.Z. Framework-based qualitative analysis of free responses of Large Language Models: Algorithmic fidelity (2024). PLOS ONE, 19(3), p.e0300024.

  14. Liu, S., Marris, L., Lanctot, M., Piliouras, G., Leibo, J.Z. and Heess, N. Neural Population Learning beyond Symmetric Zero-sum Games (2024). arXiv preprint arXiv:2401.05133 [cs.AI].

  15. Marris, L., Gemp, I., Liu, S., Leibo, J.Z. and Piliouras, G. Visualizing 2x2 Normal-Form Games: twoxtwogame LaTeX Package (2024). arXiv preprint arXiv:2402.16985 [cs.GT].

  16. Vezhnevets, A.S., Agapiou, J.P., Aharon, A., Ziv, R., Matyas, J., Duéñez-Guzmán, E.A., Cunningham, W.A., Osindero, S., Karmon, D. and Leibo, J.Z. Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia (2023). arXiv:2312.03664 [cs.AI]. Use Concordia for your own research: [GitHub].

  17. Duéñez-Guzmán, E.A., Sadedin, S., Wang, J.X., McKee, K.R. and Leibo, J.Z. A social path to human-like artificial intelligence (2023). Nature Machine Intelligence 5, 1181–1188.

  18. Brinkmann, L., Baumann, F., Bonnefon, JF.,  Derex, M, Müller, TF, Nussberger, AM, Czaplicka, A, Acerbi, A, Griffiths, TL, Henrich, J, Leibo, JZ, McElreath, R, Oudeyer, PY, Stray J, and Rahwan, I. Machine culture (2023). Nature Human Behavior 7, 1855–1868.

  19. Sadedin, S., Duéñez-Guzmán, E.A. and Leibo, J.Z. Emotions and courtship help bonded pairs cooperate, but emotional agents are vulnerable to deceit (2023). Proceedings of the National Academy of Sciences, 120(46), p.e2308911120.

  20. Yaman, A., Leibo, J.Z., Iacca, G. and Lee, S.W. The emergence of division of labor through decentralized social sanctioning (2023). Proc. R. Soc. B 290: 20231716.

  21. Du, Y., Leibo, J.Z., Islam, U., Willis, R. and Sunehag, P. A Review of Cooperation in Multi-agent Learning (2023). arXiv preprint arXiv:2312.05162 [cs.MA].

  22. Willis, R., Du, Y., Leibo, J.Z. and Luck, M. Resolving social dilemmas with minimal reward transfer (2023). arXiv preprint arXiv:2310.12928 [cs.GT].

  23. Reinecke, M.G., Mao, Y., Kunesch, M., Duéñez-Guzmán, E.A., Haas, J. and Leibo, J.Z.  The Puzzle of Evaluating Moral Cognition in Artificial Agents (2023). Cognitive Science, 47: e13315.

  24. Vinitsky, E., Köster, R., Agapiou, J.P., Duéñez-Guzmán, E.A., Vezhnevets, A.S., and Leibo, J.Z. A learning agent that acquires social norms from public sanctions in decentralized multi-agent settings (2023). Collective Intelligence, 2(2).

  25. Burnell R, Schellaert W, Burden J, Ullman TD, Martinez-Plumed F, Tenenbaum JB, Rutar D, Cheke LG, Sohl-Dickstein J, Mitchell M, Kiela D, Shanahan M, Voorhees EM, Cohn AG, Leibo JZ, and Hernandez-Orallo J. Rethink reporting of evaluation results in AI (2023). Science, 380(6641):136–138,  2023.  doi:  10.1126/science.adf6369.

  26. Mao, Y., Reinecke, M.G., Kunesch, M., Duéñez-Guzmán, E.A., Comanescu, R., Haas, J. and Leibo, J.Z. Doing the right thing for the right reason: Evaluating artificial moral cognition by probing cost insensitivity (2023). arXiv:2305.18269 [cs.AI].

  27. Madhushani, U., McKee, K.R., Agapiou, J.P., Leibo, J.Z., Everett, R., Anthony, T., Hughes, E., Tuyls, K. and Duéñez-Guzmán, E.A. Heterogeneous Social Value Orientation Leads to Meaningful Diversity in Sequential Social Dilemmas (2023). arXiv:2305.00768 [cs.MA].

  28. Sunehag, P., Vezhnevets, A.S., Duéñez-Guzmán, E., Mordach, I. and Leibo, J.Z. Diversity Through Exclusion (DTE): Niche Identification for Reinforcement Learning through Value-Decomposition (2023). arXiv:2302.01180 [cs.AI].

  29. Agapiou, J.P., Vezhnevets, A.S., Duéñez-Guzmán, E.A., Matyas, J., Mao, Y., Sunehag, P., Köster, R., Madhushani, U., Kopparapu, K., Comanescu, R., Strouse, D.J., Johanson, M.B., Singh, S., Haas, J., Mordatch, I., Mobbs, D., and Leibo, J.Z. Melting Pot 2.0 (2022). arXiv:2211.13746 [cs.MA]. [blog post]. Use Melting Pot for your own research: [GitHub].

  30. Lee, J.H., Leibo, J.Z., An, S.J. and Lee, S.W. Importance of prefrontal meta control in human-like reinforcement learning (2022). Frontiers in Computational Neuroscience, 16, p.181.

  31. Leibo, J.Z., Köster, R., Vezhnevets, A.S., Duénez-Guzmán, E.A., Agapiou, J.P. and Sunehag, P. What is the simplest model that can account for high-fidelity imitation? (2022). Behavioral and Brain Sciences, 45, E261. doi:10.1017/S0140525X22001364

  32. Leibo, J.Z., Vezhnevets, A., Eckstein, M., Agapiou, J., & Duéñez-Guzmán, E. Learning agents that acquire representations of social groups (2022). Behavioral and Brain Sciences, 45, E111. doi:10.1017/S0140525X21001357

  33. Johanson, M.B., Hughes, E., Timbers, F. and Leibo, J.Z. Emergent Bartering Behaviour in Multi-Agent Reinforcement Learning (2022). arXiv:2205.06760 [cs.AI], 2022. [blog post].

  34. Köster, R., Hadfield-Menell, D., Everett, R., Weidinger, L., Hadfield, G.K. and Leibo, J.Z. Spurious normativity enhances learning of compliance and enforcement behavior in artificial agents (2022). Proceedings of the National Academy of Sciences, 119(3). [blog post].

  35. Kopparapu, K., Duéñez-Guzmán, E.A., Matyas, J., Vezhnevets, A.S., Agapiou, J.P., McKee, K.R., Everett, R., Marecki, J., Leibo, J.Z. and Graepel, T. Hidden Agenda: a Social Deduction Game with Diverse Learned Equilibria. (2022). arXiv:2201.01816 [cs.AI], 2022.

  36. Yaman A, Bredeche N, Çaylak O, Leibo J.Z., Lee S.W. Meta-control of social learning strategies (2022). PLOS Computational Biology 18(2): e1009882.

  37. McKee, K.R., Leibo, J.Z., Beattie, C. and Everett, R., Quantifying the effects of environment and population diversity in multi-agent reinforcement learning (2022). Autonomous Agents and Multi-Agent Systems, 36(1), pp.1-16.

  38. Leibo, J.Z., Duéñez-Guzmán, E.A., Vezhnevets, A., Agapiou, J.P., Sunehag, P., Koster, R., Matyas, J., Beattie, C., Mordatch, I. and Graepel, T. Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot (2021). In International Conference on Machine Learning (ICML) (pp. 6187-6199). PMLR. [blog post]. Use Melting Pot for your own research: [GitHub].

  39. Mobbs, D., Wise, T., Suthana, N., Guzmán, N., Kriegeskorte, N. and Leibo, J.Z. Promises and challenges of human computational ethology (2021). Neuron (2021).

  40. Duéñez-Guzmán, E.A., McKee, K.R., Mao, Y., Coppin, B., Chiappa, S., Vezhnevets, A.S., Bakker, M.A., Bachrach, Y., Sadedin, S., Isaac, W., Tuyls, K., and Leibo J.Z. Statistical discrimination in learning agents (2021). arXiv:2110.11404 [cs.LG], 2021.

  41. Bakker, M.A., Everett, R., Weidinger, L., Gabriel, I., Isaac, W.S., Leibo, J.Z. and Hughes, E., Modelling Cooperation in Network Games with Spatio-Temporal Complexity (2021). arXiv:2102.06911 [cs.MA], 2021.

  42. McKee KR, Hughes E, Zhu TO, Chadwick MJ, Köster R, Castaneda AG, Beattie C, Graepel T, Botvinick M, Leibo JZ. Deep reinforcement learning models the emergent dynamics of human cooperation (2021). arXiv:2103.04982 [cs.MA], 2021.

  43. Vezhnevets, A., Wu, Y., Eckstein, M., Leblond, R. and Leibo, J.Z.OPtions as REsponses: Grounding behavioural hierarchies in multi-agent reinforcement learning (2020). In International Conference on Machine Learning (ICML) (pp. 9733-9742). PMLR.

  44. Dafoe, A., Hughes, E., Bachrach, Y., Collins, T., McKee, K.R., Leibo, J.Z., Larson, K. and Graepel, T. Open Problems in Cooperative AI (2020). arXiv:2012.08630 [cs.AI], 2020.

  45. Beattie, C., Köppe, T., Duéñez-Guzmán, E.A. and Leibo, J.Z. DeepMind Lab2D (2020). arXiv:2011.07027 [cs.AI], 2020.

  46. Köster, R., McKee, K.R., Everett, R., Weidinger, L., Isaac, W.S., Hughes, E., Duéñez-Guzmán, E.A., Graepel, T., Botvinick, M. and Leibo, J.Z. Model-free conventions in multi-agent reinforcement learning with heterogeneous preferences (2020). arXiv:2010.09054 [cs.MA], 2020.

  47. Bachrach, Y., Everett, R., Hughes, E., Lazaridou, A., Leibo, J.Z., Lanctot, M., Johanson, M., Czarnecki, W.M. and Graepel, T. Negotiating team formation using deep reinforcement learning. (2020). Artificial Intelligence, 288, p.103356.

  48. Hughes, E., Anthony, T. W., Eccles, T., Leibo, J. Z., Balduzzi, D., and Bachrach, Y. Learning to Resolve Alliance Dilemmas in Many-Player Zero-Sum Games (2020). Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems (AA-MAS 2020). Auckland, New Zealand. 2020.

  49. McKee KR, Gemp I, McWilliams B, Duéñez-Guzmán EA, Hughes E, Leibo JZ. Social Diversity and Social Preferences in Mixed-Motive Reinforcement Learning (2020). Proceedings of the 19th International Conference on Autonomous Agents and Multiagent Systems (AA-MAS 2020). Auckland, New Zealand. 2020.

  50. Tuyls, K., Perolat, J., Lanctot, M., Hughes, E., Everett, R., Leibo, J.Z., Szepesvári, C. and Graepel, T., Bounds and dynamics for empirical game theoretic analysis (2020). Autonomous Agents and Multi-Agent Systems, 34(1), p.7.

  51. Balduzzi David, Czarnecki WM., Anthony TW, Gemp IM, Hughes E, Leibo JZ, Piliouras G, and Graepel T. Smooth markets: A basic mechanism for organizing gradient-based learners (2020). International Conference on Learning Representations (ICLR). Addis Ababa, Ethiopia.

  52. Leibo JZ, Hughes E, Lanctot M, Graepel T. Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Research (2019). arXiv:1903.00742 [cs.AI], 2019.

  53. Leibo JZ, Perolat J, Hughes E, Wheelwright S, Marblestone AH, Duéñez-Guzmán E, Sunehag P, Dunning I, Graepel T. Malthusian Reinforcement Learning (2019). Proceedings of the 18th International Conference on Autonomous Agents and Multiagent Systems (AA-MAS 2019). Montreal, Quebec. 2019.

  54. Fortunato, M., Tan, M., Faulkner, R., Hansen, S., Badia, A.P., Buttimore, G., Deck, C., Leibo, J.Z. and Blundell, C., Generalization of Reinforcement Learners with Working and Episodic Memory (2019).  arXiv preprint arXiv:1910.13406. [cs.LG, cs.AI, stat.ML], 2019.

  55. Deverett B, Faulkner R,  Fortunato M,  Wayne G,  Leibo JZ. Interval timing in deep reinforcement learning agents (2019).  Advances in Neural Information Processing Systems (NeurIPS), Vancouver BC. 2019.

  56. Sunehag P,  Lever G, Liu S, Merel J, Heess N,  Leibo JZ,  Hughes E,  Eccles T,  Graepel T. Reinforcement Learning Agents acquire Flocking and Symbiotic Behaviour in Simulated Ecosystems (2019). Conference on Artificial Life (ALIFE), 2019.

  57. Wang JX,  Hughes E, Fernando C, Czarneck WM,  Duenez-Guzman EA,  Leibo JZ. Evolving intrinsic motivations for altruistic behavior (2019). Proceedings of the 18th International Conference on Autonomous Agents and Multiagent Systems (AA-MAS 2019). Montreal, Quebec. 2019.

  58. Jaques N,  Lazaridou A,  Hughes E, Gulcehre C , Ortega PA, Strouse DJ,  Leibo JZ, de Freitas N. Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning (2019).  International Conference on Machine Learning. 2019.

  59. Eccles T,  Hughes E,  Kramár J, Wheelwright S, Leibo JZ. Learning Reciprocity in Complex Sequential Social Dilemmas (2019).. arXiv:1903.08082 [cs.MA]. 2019.

  60. Lee JH, Seymour B, Leibo JZ, An SJ, Lee SW. Toward high-performance, memory-efficient, and fast reinforcement learning—Lessons from decision neuroscience (2019). Sci. Robot. 4 (2019): eaav2975.

  61. Jaderberg M, Czarnecki WM, Dunning I, Marris L, Lever G, Castaneda AG, Beattie C, Rabinowitz NC, Morcos AS, Ruderman A, Sonnerat N, Green T, Deason L, Leibo JZ, Silver D, Hassabis D, Kavukcuoglu K, and Graepel T. Human-level performance in 3D multiplayer games with population-based reinforcement learning (2019) Science. 2019 May 31;364(6443):859-65.

  62. Schmitt S, Hudson JJ, Zidek A, Osindero S, Doersch C, Czarnecki WM, Leibo JZ, Kuttler H, Zisserman A, Simonyan K, SM  Eslami. Kickstarting Deep Reinforcement Learning (2018).  arXiv:1803.03835 [cs.LG].

  63. Wang JX, Kurth-Nelson Z, Kumaran D, Tirumala D, Soyer H, Leibo JZ, Hassabis D, Botvinick M. Prefrontal cortex as a meta-reinforcement learning system (2018). Nature Neuroscience. volume 21, pages 860–868 (2018).

  64. Leibo JZ, Poggio T. Perception: biological and computational principles (2018). in Living machines: A handbook of research in biomimetics and biohybrid systems. Oxford University Press.

  65. Wayne G, Hung CC,  Amos D, Mirza M, Ahuja A, Grabska-Barwinska A, Rae J, Mirowski P,  Leibo JZ, Santoro A, Gemici M,  Reynolds M, Harley T, Abramson J, Mohamed S, Rezende D, Saxton D, Cain A, Hillier C,  Silver D, Kavukcuoglu K, Botvinick M, Hassabis D, Lillicrap T. Unsupervised Predictive Memory in a Goal-Directed Agent (2018). arXiv preprint arXiv:1803.10760 [cs.LG].

  66. Hughes E*, Leibo JZ*, Phillips MG, Tuyls K, Duenez-Guzman EA, Garcia Castaneda A, Dunning I, Zhu T, McKee KR, Koster R, Roff H, Graepel T. Inequity aversion improves cooperation in intertemporal social dilemmas (2018).  Advances in Neural Information Processing Systems 3330-3340 (* = authors contributed equally).

  67. Cao K,  Lazaridou A, Lanctot M, Leibo JZ, Tuyls K, Clark S. Emergent Communication through Negotiation (2018). International Conference on Learning Representations . Vancouver, Canada.

  68. Tuyls K,  Perolat J, Lanctot M, Leibo JZ, Graepel T. A Generalised Method for Empirical Game Theoretic Analysis (2018). arXiv preprint arxiv:1803.06376 [cs.GT].

  69. Leibo JZ, de Masson d'Autume C, Zoran D, Amos D, Beattie C, Anderson K, García Castañeda A, Sanchez M, Green S, Gruslys A, Legg S, Hassabis D, Botvinick MM.Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agents (2018). arXiv preprint arXiv:1801.08116 [bibtex](press)

  70. Tuyls K, Perolat J, Lanctot M, Ostrovski G, Savani R, Leibo JZ, Ord T, Graepel T, Legg S;Symmetric Decomposition of Asymmetric Games (2018). Scientific reports 8, 1; [bibtex] (press)

  71. Hester T, Vecerik M, Pietquin O, Lanctot M, Schaul T, Piot B, Sendonaris A, Dulac-Arnold G, Osband I, Agapiou J, Leibo JZ, Gruslys A.Deep Q-learning from Demonstrations (2018). Association for the Advancement of Artificial Intelligence (AAAI). New Orleans, LA. USA. [bibtex]

  72. Sunehag P, Lever G, Gruslys A, Czarnecki WM, Zambaldi V, Jaderberg M, Lanctot M, Sonnerat N, Leibo JZ, Tuyls K, and Graepel T. Value-Decomposition Networks For Cooperative Multi-Agent Learning Based On Team Reward (2018). Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems (pp. 2085-2087)

  73. Perolat J*, Leibo JZ*, Zambaldi V, Beattie C, Tuyls K, and Graepel T.A multi-agent reinforcement learning model of common-pool resource appropriation. (2017). Advances in Neural Information Processing Systems (NIPS). Long Beach CA, USA (* = authors contributed equally) [bibtex]

  74. Leibo JZ, Zambaldi V, Lanctot M, Marecki J, Graepel T. Multi-agent Reinforcement Learning in Sequential Social Dilemmas (2017). Proceedings of the 16th International Conference on Autonomous Agents and Multiagent Systems (AA-MAS 2017). Sao Paulo Brazil.  [bibtex] [blog post]

  75. Matthew Botvinick, David G. T. Barrett, Peter Battaglia, Nando de Freitas, Darshan Kumaran , Joel Z Leibo , Timothy Lillicrap , Joseph Modayil , Shakir Mohamed , Neil C. Rabinowitz , Danilo J. Rezende , Adam Santoro , Tom Schaul , Christopher Summerfield , Greg Wayne , Theophane Weber , Daan Wierstra , Shane Legg, and Demis Hassabis Building machines that learn and think for themselves (2017). Behavioral and Brain Sciences 40.

  76. Leibo JZ, Liao Q, Anselmi F, Freiwald WA, Poggio T.  View-Tolerant Face Recognition and Hebbian Learning Imply Mirror-Symmetric Neural Tuning to Head Orientation (2017). Current Biology 27, 1-6   , January 9, 2017. [bibtex] (press)

  77. Jaderberg M, Mnih V, Czarnecki WM, Schaul T, Leibo JZ, Silver D, Kavukcuoglu K. Reinforcement Learning with Unsupervised Auxiliary Tasks (2017).  International Conference on Learning Representations (ICLR). Toulon, France. [bibtex]

  78. Mutch J, Anselmi F, Tacchetti A, Rosasco L, Leibo JZ, Poggio T. Invariant Recognition Predicts Tuning of Neurons in Sensory Cortex (2017). Computational and Cognitive Neuroscience of Vision (Q. Zhao ed.) Springer Science+Business Media Singapore. DOI 10.1007/978-981-10-0213-7_5. [bibtex]

  79. Beattie C, Leibo JZ, Teplyashin D, Ward T,  Wainwright M, Küttler H, Lefrancq A, Green S, Valdés V, Sadik A, Schrittwieser J, Anderson K, York S, Cant M, Cain A, Bolton A, Gaffney S, King H, Hassabis D, Legg S, Petersen S. DeepMind Lab (2016). arXiv:1612.03801 [cs.AI].  [bibtex] [blog post]

  80. Wang JX, Kurth-Nelson Z, Tirumala D, Soyer H, Leibo JZ, Munos R, Blundell C, Kumaran D, Botvinick M.  Learning to reinforcement learn (2016).  arXiv:1606.04460 [cs.LG]. [bibtex]

  81. Ba J, Hinton G, Mnih V, Leibo JZ, Ionescu C.  Using Fast Weights to Attend to the Recent Past (2016).  Advances in Neural Information Processing Systems (NIPS). Barcelona, Spain. [bibtex]

  82. Blundell C, Uria B, Pritzel A, Li Y, Ruderman A, Leibo, JZ, Rae JW, Wierstra D, Hassabis D.  Model-Free Episodic Control (2016).  arXiv:1606.04460 [stat.ML]. [bibtex]

  83. Liao Q, Leibo JZ, Poggio T.  How Important is Weight Symmetry in Backpropagation? (2016).   Proceedings of the thirtieth Association for the Advancement of Artificial Intelligence conference (AAAI). Phoenix, AZ. [bibtex]

  84. Leibo JZ, Cornebise J, Gomez S, Hassabis D.  Approximate Hubel-Wiesel Modules and the Data Structures of Neural Computation (2015).  arXiv:1512.08457 [cs.NE]. [bibtex]

  85. Leibo JZ, Liao Q, Anselmi F, Poggio T. The invariance hypothesis implies domain-specific regions in visual cortex (2015).  PLoS Computational Biology vol. 11. no. 10. e1004390 [bibtex]

  86. Anselmi F, Leibo JZ, Rosasco L, Mutch J, Tacchetti A, Poggio T. Unsupervised Learning of Invariant Representations (2015).  Theoretical Computer Science doi:10.1016/j.tcs.2015.06.048

  87. Liao Q, Leibo JZ and Tomaso Poggio T. Unsupervised learning of clutter-resistant visual representations from natural videos (2014). CBMM Memo No. 023. arXiv:1409.3879v1 . September 2014 [bibtex]

  88. Leibo JZ, Liao Q, Poggio T.  Subtasks of Unconstrained Face Recognition (2014).   9th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. (VISAPP). Lisbon, Portugal. [bibtex]--- VISAPP presentation here --- Dataset available here

  89. Isik L, Meyers EM, Leibo JZ, Poggio T. The dynamics of invariant object recognition in the human visual system (2014). Journal of Neurophysiology vol. 111 no. 1 91-102 [bibtex]

  90. Liao Q, Leibo JZ, Mroueh Y, Poggio T. Can a biologically-plausible hierarchy effectively replace face detection, alignment, and recognition pipelines? (2013) arXiv:1311.4082, March 26, 2014.  [bibtex]

  91. Anselmi F, Leibo JZ, Rosasco L, Mutch J, Tacchetti A, Poggio T. Unsupervised Learning of Invariant Representations in Hierarchical Architectures (2013). arXiv:1311.4158, November 17, 2013. [bibtex]

  92. Liao Q, Leibo JZ, Poggio T.  Learning invariant representations and applications to face verification (2013).  Advances in Neural Information Processing Systems (NIPS). Lake Tahoe, NV. [bibtex]

  93. Leibo JZ. The Invariance Hypothesis and the Ventral Stream (2013).  MIT PhD thesis. [bibtex]

  94. Kim H,  Wohlwend J,  Leibo JZ,  Poggio T.  Body-form and body-pose recognition with a hierarchical model of the ventral stream (2013).    MIT-CSAIL-TR-2013-013,  CBCL-312. [bibtex]

  95. Poggio T, Mutch J, Anselmi F, Rosasco L, Leibo JZ, Tacchetti A.  The computational magic of the ventral stream: sketch of a theory (and why some deep architectures work) (2012).   MIT-CSAIL-TR-2012-035.

  96. Isik L*, Leibo JZ*, Poggio T.  Learning and disrupting invariance in visual recognition with a temporal association rule (2012).   Front. Comput. Neurosci. 6:37. doi: 10.3389/fncom.2012.00037 (* = authors contributed equally). Commentary by Bart and Hegdé: here. [bibtex]

  97. Tan C, Leibo JZ, Poggio T.  Throwing Down the Visual Intelligence Gauntlet (2012).   Machine Learning for Computer Vision; eds: Cipolla R, Battiato S, Farinella GM. Springer: Studies in Computational Intelligence Vol. 411. [bibtex]

  98. Leibo JZ, Mutch J, Poggio T.  Why The Brain Separates Face Recognition From Object Recognition (2011).  Advances in Neural Information Processing Systems (NIPS). Granada, Spain.  [bibtex]

  99. Isik L, Leibo JZ, Mutch J, Lee SW, Poggio T.  A hierarchical model of peripheral vision (2011).  MIT-CSAIL-TR-2011-031, CBCL-300. [bibtex]

  100. Mutch J, Leibo JZ, Smale S, Rosasco L, Poggio T.  Neurons that confuse mirror-symmetric object views (2010).  MIT-CSAIL-TR-2010-062, CBCL-295.  [bibtex]

  101. Leibo JZ, Mutch J, Rosasco L, Ullman S, Poggio T.  Learning generic invariances in object recognition: translation and scale (2010). MIT-CSAIL-TR-2010-061, CBCL-294. [bibtex]

Selected (old) conference abstracts

• 1. Liao Q, Leibo JZ, Poggio T. Invariant Face Recognition in the Presence of Clutter (2014). Society for Neuroscience (823.20/II15). Washington DC.

  2. Leibo JZ, Anselmi F, Mutch J, Ebihara AF, Freiwald W, Poggio T. View-invariance and mirror-symmetric tuning in a model of the macaque face-processing system (2013). Computational and Systems Neuroscience (I-54). Salt Lake City, UT.

  3. Isik L, Meyers EM, Leibo JZ, Poggio T. Timing of invariant object recognition in the human visual system (2013). Computational and Systems Neuroscience (II-51). Salt Lake City, UT.

  4. Leibo JZ, Mutch J, Poggio T. Invariance to learned transformations in the ventral stream from V1 to AM (2012). Society for Neuroscience (263.05/Y14). New Orleans LA.

  5. Isik L, Meyers EM, Leibo JZ, Poggio T. Detecting invariant visual signals with MEG decoding (2012). Society for Neuroscience (262.14/X15). New Orleans LA.

  6. Kim H, Leibo JZ, Poggio T. Pose estimation and pose-invariant recognition with an extended hierarchical model of the ventral stream (2012). Society for Neuroscience (263.01/Y10). New Orleans LA.

  7. Ko EY, Leibo JZ, Poggio T. A hierarchical model of perspective-invariant scene identification (2011). Society for Neuroscience (486.16/OO26). Washington DC.

  8. Isik L, Leibo JZ, Lee S, Mutch J, Poggio T.  A hierarchical model of peripheral vision (2011). Society for Neuroscience (485.24/OO8). Washington DC.

  9. Leibo JZ, Mutch J, Poggio T.  Learning to discount transformations as the computational goal of visual cortex (2011). Presented at FGVC/CVPR 2011. Colorado Springs, CO. Available from Nature Precedings at dx.doi.org/10.1038/npre.2011.6078.1

  10. Lee SW, Leibo JZ, Mutch J, Poggio T.  Tuning errors and pooling errors in hierarchical models of object recognition (2011).  Computational and Systems Neuroscience (III-11).  Salt Lake City, UT.

  11. Leibo JZ, Mutch J, Poggio T.  How can cells in the anterior medial face patch be viewpoint invariant? (2011). Computational and Systems Neuroscience (III-10).  Salt Lake City UT. Availabe from Nature Precedings at dx.doi.org/10.1038/npre.2011.5845.1

  12. Leibo JZ, Mutch J, Rosasco L, Ullman S, Poggio T. The puzzle of initial invariance in object recognition (2010). Society for Neuroscience (675.2/LL10). San Diego CA.