PGMax: Factor Graphs for Discrete Probabilistic Graphical Models and Loopy Belief Propagation in JAX.

Dileep George

Guangyao Zhou Antoine Dedieu Nishanth Kumar Wolfgang Lehrach Shrinu Kushagra Dileep George Miguel Lázaro-Gredilla PGMax: Factor Graphs for Discrete Probabilistic Graphical Models and Loopy Belief Propagation in JAX. 371:1-371:25 2024 25 J. Mach. Learn. Res. https://jmlr.org/papers/v25/23-1010.html db/journals/jmlr/jmlr25.html#ZhouDKLKGL24

Antoine Dedieu Wolfgang Lehrach Guangyao Zhou Dileep George Miguel Lázaro-Gredilla Learning Cognitive Maps from Transformer Representations for Efficient Planning in Partially Observed Environments. 2024 ICML https://proceedings.mlr.press/v235/dedieu24a.html https://openreview.net/forum?id=JUa5XNXuoT conf/icml/2024 db/conf/icml/icml2024.html#DedieuLZGL24 10287-10316 Miguel Lázaro-Gredilla Li Yang Ku Kevin P. Murphy Dileep George What type of inference is planning? 2024 NeurIPS http://papers.nips.cc/paper_files/paper/2024/hash/d39e3ae9a11b79691709a7a6e06a63d9-Abstract-Conference.html conf/nips/2024 db/conf/nips/neurips2024.html#Lazaro-Gredilla24

Antoine Dedieu Wolfgang Lehrach Guangyao Zhou Dileep George Miguel Lázaro-Gredilla Learning Cognitive Maps from Transformer Representations for Efficient Planning in Partially Observed Environments. 2024 abs/2401.05946 CoRR https://doi.org/10.48550/arXiv.2401.05946 db/journals/corr/corr2401.html#abs-2401-05946

Miguel Lázaro-Gredilla Li Yang Ku Kevin P. Murphy Dileep George What type of inference is planning? 2024 abs/2406.17863 CoRR https://doi.org/10.48550/arXiv.2406.17863 db/journals/corr/corr2406.html#abs-2406-17863 streams/journals/corr

Guangyao Zhou Nishad Gothoskar Lirui Wang Joshua B. Tenenbaum Dan Gutfreund Miguel Lázaro-Gredilla Dileep George Vikash K. Mansinghka 3D Neural Embedding Likelihood: Probabilistic Inverse Graphics for Robust 6D Pose Estimation. 21568-21579 2023 ICCV https://doi.org/10.1109/ICCV51070.2023.01977 conf/iccv/2023 db/conf/iccv/iccv2023.html#ZhouGWTGLGM23 Antoine Dedieu Guangyao Zhou Dileep George Miguel Lázaro-Gredilla Learning Noisy OR Bayesian Networks with Max-Product Belief Propagation. 7426-7448 2023 ICML https://proceedings.mlr.press/v202/dedieu23a.html conf/icml/2023 db/conf/icml/icml2023.html#DedieuZGL23 Sivaramakrishnan Swaminathan Antoine Dedieu Rajkumar Vasudeva Raju Murray Shanahan Miguel Lázaro-Gredilla Dileep George Schema-learning and rebinding as mechanisms of in-context learning and emergence. 2023 NeurIPS http://papers.nips.cc/paper_files/paper/2023/hash/5bc3356e0fa1753fff7e8d6628e71b22-Abstract-Conference.html conf/nips/2023 db/conf/nips/neurips2023.html#SwaminathanDRSL23

Ken Kansky Skanda Vaidyanath Scott Swingle Xinghua Lou Miguel Lázaro-Gredilla Dileep George PushWorld: A benchmark for manipulation planning with tools and movable obstacles. 2023 abs/2301.10289 CoRR https://doi.org/10.48550/arXiv.2301.10289 db/journals/corr/corr2301.html#abs-2301-10289

Antoine Dedieu Guangyao Zhou Dileep George Miguel Lázaro-Gredilla Learning noisy-OR Bayesian Networks with Max-Product Belief Propagation. 2023 abs/2302.00099 CoRR https://doi.org/10.48550/arXiv.2302.00099 db/journals/corr/corr2302.html#abs-2302-00099

Guangyao Zhou Nishad Gothoskar Lirui Wang Joshua B. Tenenbaum Dan Gutfreund Miguel Lázaro-Gredilla Dileep George Vikash K. Mansinghka 3D Neural Embedding Likelihood for Robust Sim-to-Real Transfer in Inverse Graphics. 2023 abs/2302.03744 CoRR https://doi.org/10.48550/arXiv.2302.03744 db/journals/corr/corr2302.html#abs-2302-03744

J. Swaroop Guntupalli Rajkumar Vasudeva Raju Shrinu Kushagra Carter Wendelken Danny Sawyer Ishan Deshpande Guangyao Zhou Miguel Lázaro-Gredilla Dileep George Graph schemas as abstractions for transfer learning, inference, and planning. 2023 abs/2302.07350 CoRR https://doi.org/10.48550/arXiv.2302.07350 db/journals/corr/corr2302.html#abs-2302-07350

Miguel Lázaro-Gredilla Ishan Deshpande Sivaramakrishnan Swaminathan Meet Dave Dileep George Fast exploration and learning of latent graphs with aliased observations. 2023 abs/2303.07397 CoRR https://doi.org/10.48550/arXiv.2303.07397 db/journals/corr/corr2303.html#abs-2303-07397

Sivaramakrishnan Swaminathan Antoine Dedieu Rajkumar Vasudeva Raju Murray Shanahan Miguel Lázaro-Gredilla Dileep George Schema-learning and rebinding as mechanisms of in-context learning and emergence. 2023 abs/2307.01201 CoRR https://doi.org/10.48550/arXiv.2307.01201 db/journals/corr/corr2307.html#abs-2307-01201

Nishad Gothoskar Miguel Lázaro-Gredilla Yasemin Bekiroglu Abhishek Agarwal Joshua B. Tenenbaum Vikash K. Mansinghka Dileep George DURableVS: Data-efficient Unsupervised Recalibrating Visual Servoing via online learning in a structured generative model. 6674-6680 2022 ICRA https://doi.org/10.1109/ICRA46639.2022.9811607 conf/icra/2022 db/conf/icra/icra2022.html#GothoskarLBATMG22

Nishad Gothoskar Miguel Lázaro-Gredilla Yasemin Bekiroglu Abhishek Agarwal Joshua B. Tenenbaum Vikash K. Mansinghka Dileep George DURableVS: Data-efficient Unsupervised Recalibrating Visual Servoing via online learning in a structured generative model. 2022 abs/2202.03697 CoRR https://arxiv.org/abs/2202.03697 db/journals/corr/corr2202.html#abs-2202-03697

Guangyao Zhou Nishanth Kumar Miguel Lázaro-Gredilla Shrinu Kushagra Dileep George PGMax: Factor Graphs for Discrete Probabilistic Graphical Models and Loopy Belief Propagation in JAX. 2022 abs/2202.04110 CoRR https://arxiv.org/abs/2202.04110 db/journals/corr/corr2202.html#abs-2202-04110

Antoine Dedieu Miguel Lázaro-Gredilla Dileep George Sample-Efficient L0-L2 Constrained Structure Learning of Sparse Ising Models. 7193-7200 2021 AAAI https://doi.org/10.1609/aaai.v35i8.16884 conf/aaai/2021 db/conf/aaai/aaai2021.html#DedieuLG21 Miguel Lázaro-Gredilla Wolfgang Lehrach Nishad Gothoskar Guangyao Zhou Antoine Dedieu Dileep George Query Training: Learning a Worse Model to Infer Better Marginals in Undirected Graphical Models with Hidden Variables. 8252-8260 2021 AAAI https://doi.org/10.1609/aaai.v35i9.17004 conf/aaai/2021 db/conf/aaai/aaai2021.html#Lazaro-Gredilla21 Miguel Lázaro-Gredilla Antoine Dedieu Dileep George Perturb-and-max-product: Sampling and learning in discrete energy-based models. 928-940 2021 NeurIPS https://proceedings.neurips.cc/paper/2021/hash/07b1c04a30f798b5506c1ec5acfb9031-Abstract.html conf/nips/2021 db/conf/nips/neurips2021.html#Lazaro-Gredilla21

Miguel Lázaro-Gredilla Antoine Dedieu Dileep George Perturb-and-max-product: Sampling and learning in discrete energy-based models. 2021 abs/2111.02458 CoRR https://arxiv.org/abs/2111.02458 db/journals/corr/corr2111.html#abs-2111-02458

Guangyao Zhou Wolfgang Lehrach Antoine Dedieu Miguel Lázaro-Gredilla Dileep George Graphical Models with Attention for Context-Specific Independence and an Application to Perceptual Grouping. 2021 abs/2112.03371 CoRR https://arxiv.org/abs/2112.03371 db/journals/corr/corr2112.html#abs-2112-03371

Dileep George Miguel Lázaro-Gredilla J. Swaroop Guntupalli From CAPTCHA to Commonsense: How Brain Can Teach Us About Artificial Intelligence. 554097 2020 14 Frontiers Comput. Neurosci. https://doi.org/10.3389/fncom.2020.554097 https://www.wikidata.org/entity/Q102065161 db/journals/ficn/ficn14.html#GeorgeLG20

Daniel P. Sawyer Miguel Lázaro-Gredilla Dileep George A Model of Fast Concept Inference with Object-Factorized Cognitive Programs. 2020 CogSci https://escholarship.org/uc/item/0zq2m13d conf/cogsci/2020 db/conf/cogsci/cogsci2020.html#SawyerLG20

Daniel P. Sawyer Miguel Lázaro-Gredilla Dileep George A Model of Fast Concept Inference with Object-Factorized Cognitive Programs. 2020 abs/2002.04021 CoRR https://arxiv.org/abs/2002.04021 db/journals/corr/corr2002.html#abs-2002-04021

Nishad Gothoskar Miguel Lázaro-Gredilla Abhishek Agarwal Yasemin Bekiroglu Dileep George Learning a generative model for robot control using visual feedback. 2020 abs/2003.04474 CoRR https://arxiv.org/abs/2003.04474 db/journals/corr/corr2003.html#abs-2003-04474

Nishad Gothoskar Miguel Lázaro-Gredilla Dileep George From proprioception to long-horizon planning in novel environments: A hierarchical RL model. 2020 abs/2006.06620 CoRR https://arxiv.org/abs/2006.06620 db/journals/corr/corr2006.html#abs-2006-06620

Miguel Lázaro-Gredilla Wolfgang Lehrach Nishad Gothoskar Guangyao Zhou Antoine Dedieu Dileep George Query Training: Learning and inference for directed and undirected graphical models. 2020 abs/2006.06803 CoRR https://arxiv.org/abs/2006.06803 db/journals/corr/corr2006.html#abs-2006-06803

Antoine Dedieu Miguel Lázaro-Gredilla Dileep George Sample-efficient L0-L2 constrained structure learning of sparse Ising models. 2020 abs/2012.01744 CoRR https://arxiv.org/abs/2012.01744 db/journals/corr/corr2012.html#abs-2012-01744

Dianhuan Lin J. Swaroop Guntupalli Dileep George Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programs. 2019 4 Sci. Robotics 26 https://doi.org/10.1126/scirobotics.aav3150 https://www.wikidata.org/entity/Q101157222 db/journals/scirobotics/scirobotics4.html#LinGG19

Antoine Dedieu Nishad Gothoskar Scott Swingle Wolfgang Lehrach Miguel Lázaro-Gredilla Dileep George Learning higher-order sequential structure with cloned HMMs. 2019 abs/1905.00507 CoRR http://arxiv.org/abs/1905.00507 db/journals/corr/corr1905.html#abs-1905-00507

Dileep George What can the brain teach us about building artificial intelligence? 2019 abs/1909.01561 CoRR http://arxiv.org/abs/1909.01561 db/journals/corr/corr1909.html#abs-1909-01561

Miguel Lázaro-Gredilla Wolfgang Lehrach Dileep George Learning undirected models via query training. 2019 abs/1912.02893 CoRR http://arxiv.org/abs/1912.02893 db/journals/corr/corr1912.html#abs-1912-02893

Nicholas Hay Michael Stark 0003 Alexander Schlegel Carter Wendelken Dennis Park Eric Purdy Tom Silver D. Scott Phoenix Dileep George Behavior Is Everything: Towards Representing Concepts with Sensorimotor Contingencies. 2018 AAAI https://doi.org/10.1609/aaai.v32i1.11547 conf/aaai/2018 db/conf/aaai/aaai2018.html#Hay0SWPPSPG18 1861-1870

Dileep George Alexander Lavin J. Swaroop Guntupalli David A. Mély Nick Hay Miguel Lázaro-Gredilla Cortical Microcircuits from a Generative Vision Model. 2018 abs/1808.01058 CoRR http://arxiv.org/abs/1808.01058 db/journals/corr/corr1808.html#abs-1808-01058

Miguel Lázaro-Gredilla Dianhuan Lin J. Swaroop Guntupalli Dileep George Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programs. 2018 abs/1812.02788 CoRR http://arxiv.org/abs/1812.02788 db/journals/corr/corr1812.html#abs-1812-02788

Austin Stone Hua-Yan Wang Michael Stark 0003 Yi Liu 0055 D. Scott Phoenix Dileep George Teaching Compositionality to CNNs. 732-741 2017 CVPR https://doi.org/10.1109/CVPR.2017.85 https://doi.ieeecomputersociety.org/10.1109/CVPR.2017.85 conf/cvpr/2017 db/conf/cvpr/cvpr2017.html#StoneW0LPG17 Ken Kansky Tom Silver David A. Mély Mohamed Eldawy Miguel Lázaro-Gredilla Xinghua Lou Nimrod Dorfman Szymon Sidor D. Scott Phoenix Dileep George Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics. 1809-1818 2017 ICML http://proceedings.mlr.press/v70/kansky17a.html conf/icml/2017 db/conf/icml/icml2017.html#KanskySMELLDSPG17

Austin Stone Hua-Yan Wang Michael Stark 0003 Yi Liu 0055 D. Scott Phoenix Dileep George Teaching Compositionality to CNNs. 2017 abs/1706.04313 CoRR http://arxiv.org/abs/1706.04313 db/journals/corr/corr1706.html#StoneWSLPG17

Ken Kansky Tom Silver David A. Mély Mohamed Eldawy Miguel Lázaro-Gredilla Xinghua Lou Nimrod Dorfman Szymon Sidor D. Scott Phoenix Dileep George Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics. 2017 abs/1706.04317 CoRR http://arxiv.org/abs/1706.04317 db/journals/corr/corr1706.html#KanskySMELLDSPG17

Xinghua Lou Ken Kansky Wolfgang Lehrach C. C. Laan Bhaskara Marthi D. Scott Phoenix Dileep George Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training Data. 2793-2801 2016 NIPS https://proceedings.neurips.cc/paper/2016/hash/23ad3e314e2a2b43b4c720507cec0723-Abstract.html http://papers.nips.cc/paper/6071-generative-shape-models-joint-text-recognition-and-segmentation-with-very-little-training-data conf/nips/2016 db/conf/nips/nips2016.html#LouKLLMPG16

Miguel Lázaro-Gredilla Yi Liu 0055 D. Scott Phoenix Dileep George Hierarchical compositional feature learning. 2016 abs/1611.02252 CoRR http://arxiv.org/abs/1611.02252 db/journals/corr/corr1611.html#Lazaro-Gredilla16

Hua-Yan Wang Anna Chen Yi Liu 0055 Dileep George D. Scott Phoenix A backward pass through a CNN using a generative model of its activations. 2016 abs/1611.02767 CoRR http://arxiv.org/abs/1611.02767 db/journals/corr/corr1611.html#WangCLGP16

Stuart Russell 0001 Tom Dietterich Eric Horvitz Bart Selman Francesca Rossi 0001 Demis Hassabis Shane Legg Mustafa Suleyman Dileep George D. Scott Phoenix Letter to the Editor: Research Priorities for Robust and Beneficial Artificial Intelligence: An Open Letter. 2015 36 AI Mag. 4 https://doi.org/10.1609/aimag.v36i4.2621 db/journals/aim/aim36.html#RussellDHSRHLSG15 3-4

Dileep George Jeff Hawkins Towards a Mathematical Theory of Cortical Micro-circuits. 2009 5 PLoS Comput. Biol. 10 https://doi.org/10.1371/journal.pcbi.1000532 https://www.wikidata.org/entity/Q21145351 db/journals/ploscb/ploscb5.html#GeorgeH09

Dileep George How to make computers that work like the brain. 420-423 2009 DAC https://doi.org/10.1145/1629911.1630024 conf/dac/2009 db/conf/dac/dac2009.html#George09 Dileep George Hierarchical Temporal Memory: Theory and Applications. 6643 2006 EMBC (Supplement) https://doi.org/10.1109/IEMBS.2006.260909 https://www.wikidata.org/entity/Q51969158 conf/embc/2006suppl db/conf/embc/embc2006suppl.html#George06

Dileep George Friedrich T. Sommer Computing with inter-spike interval codes in networks of integrate and fire neurons. 415-420 2005 65-66 Neurocomputing https://doi.org/10.1016/j.neucom.2004.10.038 db/journals/ijon/ijon65.html#GeorgeS05

Dileep George Jeff Hawkins A hierarchical Bayesian model of invariant pattern recognition in the visual cortex. 1812-1817 2005 IJCNN https://doi.org/10.1109/IJCNN.2005.1556155 conf/ijcnn/2005 db/conf/ijcnn/ijcnn2005.html#GeorgeH05 streams/conf/ijcnn Dileep George Kazumi Saito Pat Langley Stephen D. Bay Kevin R. Arrigo Discovering Ecosystem Models from Time-Series Data. 141-152 https://doi.org/10.1007/978-3-540-39644-4_13 2003 conf/dis/2003 Discovery Science db/conf/dis/dis2003.html#GeorgeSLBA03 Kazumi Saito Dileep George Stephen D. Bay Jeff Shrager Inducing Biological Models from Temporal Gene Expression Data. 468-469 https://doi.org/10.1007/978-3-540-39644-4_47 2003 conf/dis/2003 Discovery Science db/conf/dis/dis2003.html#SaitoGBS03 Pat Langley Dileep George Stephen D. Bay Kazumi Saito Robust Induction of Process Models from Time-Series Data. 432-439 2003 conf/icml/2003 ICML db/conf/icml/icml2003.html#LangleyGBS03 http://www.aaai.org/Library/ICML/2003/icml03-058.php Abhishek Agarwal Kevin R. Arrigo Stephen D. Bay Yasemin Bekiroglu Anna Chen Meet Dave Antoine Dedieu Ishan Deshpande Thomas G. DietterichTom Dietterich Nimrod Dorfman Mohamed Eldawy Nishad Gothoskar J. Swaroop Guntupalli Dan Gutfreund Demis Hassabis Jeff Hawkins Nicholas Hay Nick Hay Eric Horvitz Ken Kansky Li Yang Ku Nishanth Kumar Shrinu Kushagra C. C. Laan Pat Langley Alexander Lavin Miguel Lázaro-Gredilla Shane Legg Wolfgang Lehrach Dianhuan Lin Yi Liu 0055 Xinghua Lou Vikash Mansinghka 0001Vikash K. Mansinghka Bhaskara Marthi David A. Mély Kevin Murphy 0002Kevin P. Murphy Dennis Park D. Scott Phoenix Eric Purdy Rajkumar Vasudeva Raju Francesca Rossi 0001 Stuart Russell 0001 Kazumi Saito Daniel P. Sawyer Danny Sawyer Alexander Schlegel Bart Selman Murray Shanahan Jeff Shrager Szymon Sidor Tom Silver Friedrich T. Sommer Michael Stark 0003 Austin Stone Mustafa Suleyman Sivaramakrishnan Swaminathan Scott Swingle Joshua B. Tenenbaum Skanda Vaidyanath Hua-Yan Wang Lirui Wang Carter Wendelken Guangyao Zhou