Computational Neuroscience & Artificial Intelligence
Journal Articles & Conference Proceedings (*, ** = equal contribution)

• Cao R and Yamins D (2024). Explanatory models in neuroscience, Part 1: Taking mechanistic abstraction seriously. Cognitive Science Research.
• Cao R and Yamins D (2024). Explanatory models in neuroscience, Part 2: Functional intelligibility and the contravariance principle. Cognitive Science Research.
• Bria Long, Violet Xiang, Stefan Stojanov, Robert Z. Sparks, Zi Yin, Grace E. Keene, Alvin W. M. Tan, Steven Y. Feng, Chengxu Zhuang, Virginia A. Marchman, Daniel L. K. Yamins, Michael C. Frank (2024). The BabyView dataset: High-resolution egocentric videos of infants' and young children's everyday experiences. (in submission)
• Venkatesh R*, Chen H*, Feigelis K*, Bear D*, Jedoui K, Kotar K, Binder F, Lee W, Liu S, Smith KA, Fan JE, and Yamins D (2024). Understanding Physical Dynamics with Counterfactual World Modeling. 18th European Conference on Compute Vision (ECCV '24).
• Cross L, Xiang V, Bhatia A, Yamins D* and Haber N* (2024). Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models. (in submission)
• Margalit E, Lee H, Finzi D, DiCarlo JJ, Grill-Spector K, and Yamins D (2024). A unifying framework for functional organization in early and higher ventral visual cortex. Neuron (in press)
• Thobani I, Sagastuy-Brena J, Nayebi A, Cao R, and Yamins D (2024). Inter-animal transforms as a guide to model-brain comparison. ICLR 2024 Workshop on Representational Alignment.
• Wang H, Jedoui K, Venkatesh R, Binder F, Tenenbaum J, Fan J, Yamins D, and Smith K (2024). Probabilistic simulation supports generalizable intuitive physics. Proceedings of the 46th Annual Meeting of the Cognitive Science Society.
• Xue H, Torralba A, Tenenbaum J, Yamins D, Li Y, and Tung HY (2024). 3D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenes. Advances in Neural Information Processing Systems (36).
• Finzi D, Margalit E, Kay K*, Yamins D* and Grill-Spector K* (2023). A single computational objective drives specialization of streams in visual cortex. (in submission)
• Kotar K, Tian S, Yu HX, Yamins D and Wu J (2023). Are These the Same Apple? Comparing Images Based on Object Intrinsics. NeurIPS 2023.
• Kunin D, Sagastuy-Brena J, Gillespie L, Margalit E, Tanaka H, Ganguli S, and Yamins D (2023). Limiting Dynamics of SGD: Modified Loss, Phase Space Oscillations, and Anomalous Diffusion. Neural Computation (in press).
• Nayebi A*, Kong NCL*, Zhuang C, Gardner JL, Norcia AM, and Yamins D (2023). Mouse visual cortex as a limited resource system that self-learns an ecologically-general representation. PLoS Computational Biology (in press).
• Long B, Goodin S, Kachergis G, Marchman V, Radwan S, Sparks RZ, Xiang V, Zhuang C, Hsu O, Newman B, Yamins D, and Frank MC (2023). The BabyView camera: Designing a new head-mounted camera to capture children’s early social and visual environments. Behavioral Research Methods (2023): 1-12.
• Bonnen T, Wagner AD, and Yamins D (2023). Medial temporal cortex supports compositional visual interfaces. (in submission)
• Bear DM, Feigelis K, Chen H, Lee W, Venkatesh R, Kotar K, Durango A, and Yamins D (2023). Unifying (Machine) Vision via Counterfactual World Modeling. (in submission)
• Margalit E, Lee H, Finzi D, DiCarlo JJ, Grill-Spector K*, and Yamins D* (2023). A Unifying Principle for the Functional Organization of Visual Cortex (in submission)
• Doyle C, Shader S, Lau M, Sano M, Yamins D, and Haber N (2023). Developmental Curiosity and Social Interaction in Virtual Agents. Proceedings of the 45th Annual Conference of the Cognitive Science Society.
• Martinez J, Binder FJ, Wang H, Haber N, Fan J, and Yamins D (2023). Measuring and Modeling Physical Intrinsic Motivation. Proceedings of the 45th Annual Conference of the Cognitive Science Society.
• Finzi D, Margalit E, Kay K*, Yamins D*, and Grill-Spector K* (2022). Topographic DCNNs trained on a single self-supervised task capture the functional organization of cortex into visual processing streams. SVRHM 2022 Workshop @ NeurIPS 2022. (Best paper award.)
• Zhuang C, Xiang V, Bai Y, Jia X, Turk-Browne NB, Norman K, DiCarlo JJ, Yamins D (2022). How Well Do Unsupervised Learning Algorithms Model Human Real-time and Life-long Learning? Advances in Neural Information Processing Systems 35 (NeurIPS 2022, Datasets and Benchmarks Track)
• Chen H, Venkatesh R, Friedman Y, Wu J, Tenenbaum JB, Yamins D*, Bear D* (2022). Unsupervised Segmentation in Real-World Images via Spelke Object Inference. European Conference on Computer Vision (ECCV) (oral presentation)
• Nayebi A, Sagastuy-Brena J, Bear DM, Kar K, Kubilius J, Ganguli S, Sussillo D, DiCarlo J, Yamins D (2022). Recurrent Connections in the Primate Ventral Visual Stream Mediate a Trade-Off Between Task Performance and Network Size During Core Object Recognition. Neural Computation. Vol. 34 (8).
• Nayebi A, Attinger A, Campbell MG, Hardcastle K, Low IIC, Mallory CS, Mel GC, Sorscher B, Williams AH, Ganguli S, Giocomo LM, Yamins D (2021). Explaining heterogeneity in medial entorhinal cortex with task-driven neural networks. Advances in Neural Information Processing Systems 34 (NeurIPS 2021, spotlight).
• Bonnen T, Yamins D, Wagner AD (2021). When the ventral visual stream is not enough: A deep learning account of medial temporal lobe involvement in perception. Neuron.
• Bear DM*, Wang E*, Mrowca D*, Binder FJ*, Tung HY, Pramod RT, Holdaway C, Tao S, Smith K, Sun FY, Fei-Fei L, Kanwisher N, Tenenbaum JB, Yamins D**, Fan JE** (2021). Physion: Evaluating Physical Prediction from Vision in Humans and Machines. NeurIPS 2021 (Datasets and Benchmarks Track)
• Gan C, Schartz S, Alter S, Mrowca D, Schrimpf M, Traer J, De Freitas J, Kubilius J, Bhandaldar A, Haber N, Sano M, Kim K, Wang E, Lingelbach M, Curtis A, Feigelis K, Bear D, Gutfreund D, Cox DD, Torralba A, DiCarlo J, Tenenbaum J, McDermott J, Yamins D (2021). ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation. NeurIPS 2021 (Datasets and Benchmarks Track)
• Nayebi A, Kong NCL, Zhuang C, Gardner JL, Norcia AM, Yamins D (2021). Unsupervised Models of Mouse Visual Cortex. (in submission)
• Kachergis G, Radwan S, Long B, Fan JE, Lingelbach M, Bear D, Yamins D, Frank M (2021). Predicting children's and adults' preferences in physical interactions via physics simulation. In Proceedings of the 43rd Annual Conference of the Cognitive Science Society.
• Holdaway C, Bear D, Radwan S, Franl M, Yamins D, and Fan JE. (2021). Measuring and predicting variation in the interestingness of physical structures. In Proceedings of the 43rd Annual Meeting of the Cognitive Science Society.
• Cao R & Yamins D (2021). Explanatory models in neuroscience: Part 1 -- taking mechanistic abstraction seriously. (in submission)
• Cao R & Yamins D (2021). Explanatory models in neuroscience: Part 2 -- constraint-based intelligibility. (in submission)
• Kunin D, Sagastuy-Brena J, Ganguli S, Yamins D, & Tanaka H (2020). Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics. In Proceedings of the International Conference on Learning Representations (ICLR, 2021)
• Nayebi A*, Srivastava S*, Ganguli S, & Yamins D (2020). Identifying Learning Rules From Neural Network Observables. In Advances in Neural Information Processing Systems (NeurIPS 2020, spotlight presentation)
• Lee H, Margalit E, Jozwik KM, Cohen MA, Kanwisher N, Yamins D, & DiCarlo JJ (2020). Topographic deep artificial neural networks reproduce the hallmarks of the primate inferior temporal cortex face processing network. (in submission)
• Bear DM, Fan C, Mrowca D, Li Y, Alter S, Nayebi A, Schwartz J, L Fei-Fei, Wu J, Tenenbaum JB, & Yamins D (2020). Learning Physical Graph Representations from Visual Scenes. In Advances in Neural Information Processing Systems (NeurIPS 2020, oral presentation)
• Zhuang C, Yan S, Nayebi A, Schrimpf M, Frank M, DiCarlo JJ, & Yamins D (2020). Unsupervised Neural Network Models of the Ventral Visual Stream. Proceedings of the National Academy of Sciences 118(3)
• Tanaka H*, Kunin D*, Yamins D, & Ganguli S (2020). Pruning neural networks without any data by iteratively conserving synaptic flow. In Advances in Neural Information Processing Systems (NeurIPS 2020)
• Kim KH, Sano M, De Freitas J, Haber N*, & Yamins D* (2020). Active World Model Learning in Agent-rich Environments with Progress Curiosity. And see extended ArXiv version here. International Conference on Machine Learning (ICML) 2020.
• Curtis A, Xin M, Arumugam D, Feigelis K, & Yamins D (2020). Flexible and Efficient Long-Range Planning Through Curious Exploration. International Conference on Machine Learning (ICML) 2020
• Kunin D*, Nayebi A*, Sagastuy-Brena J*, Ganguli S, Bloom J, & Yamins D (2020). Two Routes to Scalable Credit Assignment Without Weight Symmetry. International Conference on Machine Learning (ICML) 2020
• Sano M, De Freitas J, Haber N*, & Yamins D* (2020). Learning in Social Enviroments with Curious Neural Agents. Proceedings of the 42th Annual Conference of the Cognitive Science Society.
• Li Y, Lin T, Yi K, Bear D, Yamins D, Wu J, Tenenbaum JB, & Torralba A (2020). Visual Grounding of Learned Physical Models. International Conference on Machine Learning (ICML) 2020 (to appear)
• Wu M, Zhuang C, Mosse M, Yamins D, & Goodman N (2020). Conditional Negative Sampling for Contrastive Learning of Visual Representations.   Proceedings of the International Conference on Learning Representations (ICLR, 2021)
• Zhuang C, She T, Andonian A, Mark MS, & Yamins D (2020). Unsupervised Learning from Video with Deep Neural Embeddings.   Computer Vision and Pattern Recognition (CVPR) 2020
• Fan JE, Wammes JD, Gunn JB, Yamins D, Norman KA, & Turk-Browne NB (2020). Relating Visual Production and Recognition of Objects in Human Visual Cortex. Journal of Neuroscience. 40(8), pp. 1710-1721.
• Yamins D (2019). An Optimization-Based Approach to Understanding Sensory Systems. (in The Cognitive Neurosciences, 6th e, Poeppel D, Mangun G, & Gazzaniga M, eds)
• Kubilius J, Schrimpf M, Kar K, Rajalingham R, Hong H, Majaj N, Issa E, Bashivan P, Prescott-Roy J, Schmidt K, Nayebi A, Bear D, Yamins D, & DiCarlo JJ (2019). Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs In Advances in Neural Information Processing Systems (NeurIPS) 31
• Zhuang C, Ding X, Murli D, & Yamins D (2019). Local Label Propagation for Large-Scale Semi-Supervised Learning.  (in submission)
• Zhuang C, Zhai AL, & Yamins D (2019). Local Aggregation for Unsupervised Learning of Visual Embeddings.  In Proceedings of the IEEE Conference on Computer Vision (ICCV) 2019 (oral presentation)
• Mrowca D*, Zhuang C*, Wang E*, Haber N, Fei-Fei L, Tenenbaum JB, & Yamins D (2018). Flexible Neural Representation for Physics Prediction. In Advances in Neural Information Processing Systems (NeurIPS) 31
• Nayebi A*, Bear D*, Kubilius J*, Kar K, Ganguli S, Sussillo D, DiCarlo JJ, & Yamins D (2018). Task-Driven Convolutional Recurrent Models of the Visual System. In Advances in Neural Information Processing Systems (NeurIPS) 31
• Haber N*, Mrowca D*, Li Fei-Fei, and Yamins D (2018).  Learning to Play with Intrinsically-Motivated Self-Aware Agents. In Advances in Neural Information Processing Systems (NeurIPS) 31
• Kell AJE*, Yamins D*, Shook EN, Norman-Haignere S, and McDermott JH (2018). A Task-Optimized Neural Network Replicates Human Auditory Behavior, Predicts Brain Responses, and Reveals a Cortical Processing Hierarchy. Neuron. 98(3), pp. 630-644.
• Fan JE, Yamins D, Turk-Browne NB (2018). Common Object Representations for Visual Production and Recognition. Cog. Sci. doi:10.1111/cogs.12676
• Feigelis KT, Sheffer B, & Yamins D (2018).  Modular Continual Learning in a Unified Visual Environment. In: Proceedings of the International Conference on Learning Representations (ICLR, 2018).
• Zhuang C, Kubilius J, Hartmann M, & Yamins D (2017).  Toward Goal-Driven Neural Network Models for the Rodent Whisker-Trigeminal System. In Advances in Neural Information Processing Systems (NIPS) 30, pp. 2552-2562
• Hong H*, Yamins D*, Majaj N, & DiCarlo JJ (2016).   Explicit information for category-orthogonal object properties increases along the ventral stream. Nature Neuroscience.  19, pp. 613-622.
• Yamins D & DiCarlo JJ (2016). Eight open problems in the computational modeling of higher sensory cortex. Current Opinion in Neurobiology, 37 pp. 144-120. 
• Yamins D & DiCarlo JJ (2016).  Using goal-driven deep learning models to understand sensory Scortex.   Nature Neuroscience, 19, pp. 356–365.
• Fan JE, Yamins D, &Turk-Browne, N (2015). Common object representations for visual recognition and production. Proceedings of the 37th Annual Conference of the Cognitive Science Society.
• Afraz A, Yamins D, & DiCarlo JJ (2015). Neural Mechanisms Underlying Visual Object Recognition. In Cold Spring Harbor symposia on quantitative biology. 79, pp. 99-107. Cold Spring Harbor Laboratory Press.
• Seibert D, Yamins D, Ardila D, Hong H, DiCarlo JJ, & Gardner JL (2014).  A Performance-Optimized Model of Neural Responses Across the Ventral Visual Stream.  (submitted)
• Yamins D*, Hong H*, Cadieu C, Solomon EA, Seibert D, & DiCarlo JJ (2014).   Performance-Optimized Hierarchical Models Predict Neural Responses in Higher Visual Cortex.  Proceedings of the National Academy of Sciences 111(23), pp. 8619-8624. doi: 10.1073/pnas.1403112111
• Yamins D*, Hong H*, Cadieu CF, & DiCarlo JJ  (2013). Hierarchical Modular Optimization of Convolutional Networks Achieves Representations Similar to Macaque IT and Human Ventral Stream. In Advances in Neural Information Processing Systems (NIPS), 26, pp. 3093-3101.
• Cadieu CF, Hong H, Yamins D, Pinto N, Majaj NJ, & DiCarlo JJ. (2013) The Neural Representation Benchmark and its Evaluation on Brain and Machine. In: Proceedings of the International Conference on Learning Representations (ICLR, 2013). 
• Bergstra J, Yamins D, & Cox D. (2013). Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures.  Journal of Machine Learning Research, 28(1), pp. 115-123.

Conference Abstracts

• Feigelis KT & Yamins D. (Sep. 2017). A Useful Motif for Flexible Task Learning in an Embodied Two-Dimensional Visual Environment. Cognitive Computational Neuroscience 2017.
• Kell A*, Yamins D*, Norman-Haignere S, & McDermott J. (Feb. 2016) Speech-trained neural networks behave like human listeners and reveal a hierarchy in auditory cortex. COSYNE 2016.
• Fan JE, Yamins D, & Turk-Browne, N.  Dynamic visual feedback is sufficient to improve drawing.  Poster at Vision Sciences Society (VSS) Annual Meeting, May 2016.
• Kell A*, Yamins D*, Norman-Haignere S, Seibert D, Hong H, DiCarlo JJ, & McDermott J. Computational similarities between visual and auditory cortex studied with convolutional neural networks, fMRI, and electrophysiology.  Poster at Vision Sciences Society (VSS) Annual Meeting, May 2015.  Journal of vision, 15(12), p. 1093.
• Yamins D, Cohen M, Hong H, Kanwisher N, & DiCarlo JJ.  The Emergence of Face-Selective Units in a Model that Has Never Seen a Face.  Talk at Vision Sciences Society (VSS) Annual Meeting, May 2015.   Journal of vision, 15(12), p. 754.
• Tian M, Yamins D, & Grill-Spector K. (2015). Learning invariant object representations: asymmetric transfer of learning across line drawings and 3D cues. Abstract at Vision Sciences Society (VSS) Annual Meeting, May 2015.  Journal of vision, 15(12), p. 1088.
• Kell A*, Yamins D*, Norman-Haignere S, & McDermott J. Functional organization of auditory cortex revealed by neural networks optimized for auditory tasks. Talk at Society for Neuroscience (SfN) Annual Meeting, October 2015.
• Fan JE, Yamins D, & Turk-Browne, N. How drawing shapes object representations. Poster presented at the Vision Sciences Society (VSS) Annual Meeting, May 2015. Journal of vision, 15(12), p. 44.
• Yamins D, Hong H, & DiCarlo, JJ. Emergence of identity-independent object properties in vetral visual cortex.  COSYNE 2015
• Yamins D*, Kell A*, Norman-Haignere S & McDermott J.  Using Speech-optimized convolutional neural networks to understand auditory cortex. COSYNE 2015
• Fan JE, Yamins D, DiCarlo JJ, & Turk-Browne NB (2014). Mapping Core Similarity Among Visual Objects Across Image Modalities.  To appear in Proceedings of SIGGRAPH 2014.   
• Yamins D*, Hong H*, Seibert D, and DiCarlo JJ (2014).  Predicting IT and V4 Neural Responses With Performance-Optimized Neural Networks.  Computational Systems Neuroscience (COSYNE)
• Hong H*, Yamins D*, Majaj NJ, & DiCarlo JJ (2014). IT Cortex Contains a General-purpose Visual Object Representation.  Computational Systems Neuroscience (COSYNE). 
• Hong H*, Solomon EA*, Yamins D*, & DiCarlo, JJ (2014).  Large-scale Characterization of a Universal and Compact Visual Perceptual Space.  Vision Science Society (VSS).  
• Yamins D, Hong H, Solomon, E, & DiCarlo JJ (2013).  Ventral Stream Models That Solve Hard Object Recognition Tasks Natuarllay Exhibit Neural Consistency. Computational Systems Neuroscience (COSYNE). 

Data Analysis

• Angelino E, Yamins D, & Seltzer M (2010). StarFlow: A Script-Centric Data Analysis Environment. Proceedings of International Provenance and Annotation Workshop (IPAW), pp. 236-250.

Spatially Distributed Multiagent Systems

• Yamins D & Nagpal R (2008).  Automated Global-to-Local Programming in 1-D Spatial Multiagent Systems.  Intl. Conf on Autonomous Agents and Multi-Agent Systems (AAMAS), pp. 615-622.
• Yamins D (2008).   A Theory of Local-to-Global Algorithms for One-Dimensional Spatial Multiagent Systems.   PhD Thesis, Harvard University. 
• Yamins D (2006). The emergence of global properties from local interactions: static properties and one-dimensional patterns. Intl. Conf on Autonomous Agents and Multi-Agent Systems (AAMAS), pp. 1122-1124
• McLurkin J & Yamins D. (2005) Dynamic Task Assignment in Robot Swarms. Robotics Systems and Science (RSS), pp. 129-136.
• Yamins D (2005). Towards a Theory of "Local to Global" in Distributed Muti-Agent Systems. I. Mathematical Theory. Intl. Conf on Autonomous Agents and Multi-Agent Systems (AAMAS), pp. 183-190.
• Yamins D (2005). Towards a Theory of "Local to Global" in Distributed Muti-Agent Systems. II. Data Structures. Intl. Conf on Autonomous Agents and Multi-Agent Systems (AAMAS), pp. 191-198.
• Yamins D,  Waydo S & Khaneja N (2004). Group Control and Kernels: The One-Dimesional Equigrouping Problem. Proceedings of the 43rd IEEE Conference on Decision and Control (CDC), pp. 2460-2466.

* = equal contribution

---

Representative Presentations