Massachusetts Institute of Technology (2010-2017)

Ph.D., Brain and Cognitive Sciences

California Institute of Technology (2006-2010)

B.S. with Honors, Engineering and Applied Science (Computation and Neural Systems) and History and Philosophy of Science

May 2018 – Present

Research Scientist, Google Research, Brain Team

July 2017 – July 2018

Google Brain Resident

Mar. 2011 – June 2017

Graduate Research Assistant, Department of Brain and Cognitive Sciences, MIT (Supervisor: Earl K. Miller)

Sept. 2009 – Jan. 2011

Research Assistant, Division of Biology, Caltech (Supervisor: Doris Tsao)

June 2007 – Sept. 2009

Undergraduate Research Assistant, Division of Biology, Caltech (Supervisor: Christof Koch)

June 2005 – Feb. 2017

Senior Developer, Zotero, Roy Rosenzweig Center for History and New Media, George Mason University

(For an up-to-date list including unpublished preprints, see my Google Scholar page.)

Ilharco, G.*, Wortsman, M.*, Gadre, S. Y.*, Song, S., Hajishirzi, H., Kornblith, S., Farhadi, A., & Schmidt, L. (2022). Patching open-vocabulary models by interpolating weights. Neural Information Processing Systems. (* = equal contribution)

Nguyen, T., Raghu, M., & Kornblith, S. (2022). On the origins of the block structure phenomenon in neural network representations. Transactions on Machine Learning Research.

Brempong, E. A., Kornblith, S., Chen, T., Parmar, N., Minderer, M., & Norouzi, M. (2022). Decoder denoising pretraining for semantic segmentation. Transactions on Machine Learning Research.

Wortsman, M., Ilharco, G., Gadre, S. Y., Roelofs, R., Gontijo-Lopes, R., Morcos, A. S., Namkoong, H., Farhadi, A., Carmon, Y.*, Kornblith, S.* & Schmidt, L.* (2022). Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. International Conference on Machine Learning. (* = equal contribution)

Wortsman, M.*, Ilharco, G.*, Kim, J.W., Li, M., Kornblith, S., Roelofs, R., Lopes, R. G., Hajishirzi, H., Farhadi, A., Namkoong, H., & Schmidt, L. (2022). Robust fine-tuning of zero-shot models. Computer Vision and Pattern Recognition (Oral). (* = equal contribution)

Hyunh, T., Kornblith, S., Walter, M. R, Maire, M., & Khademi, M. (2022). Boosting contrastive self-supervised learning with false negative cancellation. Winter Conference on Applications of Computer Vision.

Kornblith, S., Chen, T., Lee, H., & Norouzi, M. (2021). Why do better loss functions lead to less transferable features? Neural Information Processing Systems.

Williams, A. H., Kunz, E., Kornblith, S., & Linderman, S. (2021). Generalized shape metrics on neural representations. Neural Information Processing Systems.

Raghu, A., Lorraine, J. P., Kornblith, S., McDermott, M. B. A., Duvenaud, D. (2021). Meta-learning to improve pre-training. Neural Information Processing Systems.

Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C., & Dosovitskiy, A. (2021). Do Vision Transformers see like convolutional neural networks? Neural Information Processing Systems.

Azizi, S., Mustafa, B., Ryan, F., Beaver, Z., Freyberg, J., Deaton, J., ..., Kornblith, S., Chen, T., Natarajan, V., & Norouzi, M. (2021). Big self-supervised models advance medical image classification. International Conference on Computer Vision.

Cranko, Z., Shi, Z., Zhang, X., Nock, R., & Kornblith, S. (2021). Generalised Lipschitz regularisation equals distributional robustness. International Conference on Machine Learning.

Angles, B., Kornblith, S., Izadi, S., Tagliasacchi, A., & Yi, K. M. (2021). MIST: Multiple Instance Spatial Transformer network. Computer Vision and Pattern Recognition.

Brincat, S. L., Donoghue, J. A., Mahnke, M. K., Kornblith, S., Lundqvist, M., & Miller, E. K. (2021). Interhemispheric transfer of working memories. Neuron.

Nguyen, T., Raghu, M., & Kornblith, S. (2021). Do wide and deep networks learn the same things? Uncovering how neural network representations vary with width and depth. International Conference on Learning Representations.

Raghu, A., Raghu, M., Kornblith, S., Duvenaud, D., & Hinton, G. (2021). Teaching with commentaries. International Conference on Learning Representations.

Hermann, K., Chen, T., Norouzi, M., & Kornblith, S. (2020). Understanding self-supervised learning using controlled datasets with known structure. NeurIPS 2020 Workshop: Self-Supervised Learning - Theory and Practice.

Hermann, K., Chen, T., & Kornblith, S. (2020). The origins and prevalence of texture bias in convolutional neural networks. Neural Information Processing Systems. (Oral presentation. An earlier version of this work won the best poster award at the NeurIPS 2019 SVRHM workshop.)

Chen, T., Kornblith, S., Swersky, K., Norouzi, M., & Hinton, G. E. (2020). Big self-supervised models are strong semi-supervised learners. Neural Information Processing Systems.

Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. (2020). A simple framework for contrastive learning of visual representations. International Conference on Machine Learning.

Elsayed, G. F., Ramachandran, P., Shlens, J., and Kornblith, S. (2020). Revisiting spatial invariance with low-rank local connectivity. International Conference on Machine Learning.

Elsayed, G. F., Kornblith, S., and Le, Q. V. (2019). Saccader: Improving accuracy of hard attention models for vision. Neural Information Processing Systems.

Müller, R., Kornblith, S., and Hinton, G. (2019). When does label smoothing help? Neural Information Processing Systems (Spotlight).

Kornblith, S., Norouzi, M., Lee, H., and Hinton, G. (2019). Similarity of neural network representations revisited. International Conference on Machine Learning. [code] (An abridged version of this paper won the best research paper award at the ICLR DebugML workshop.)

Kornblith, S., Shlens, J., and Le, Q. V. (2019). Do better ImageNet models transfer better? Computer Vision and Pattern Recognition (Oral).

Bastos, A. M., Loonis, R., Kornblith, S., Lundqvist, M., and Miller, E. K. (2018). Laminar recordings in frontal cortex suggest distinct layers for maintenance and control of working memory. Proceedings of the National Academy of Sciences, in press. doi: 10.1073/pnas.1710323115 

Kornblith, S. and Tsao, D. Y. (2017). How thoughts arise from sights: inferotemporal and prefrontal contributions to vision. Current Opinion in Neurobiology, 46, 208-218. doi:10.1016/j.conb.2017.08.016

Kornblith, S., Quiroga, R. Q., Koch, C., Fried, I., and Mormann, F. (2017). Persistent single neuron activity during working memory in the human medial temporal lobe. Current Biology, 27, 1026–1032. doi:10.1016/j.cub.2017.02.013 [code and data]

Mormann, F.*, Kornblith, S.*, Cerf, M., Ison, M. J., Kraskov, A., Tran, M., Knieling, S., Quiroga, R. Q., Koch, C., and Fried, I. (2017). Scene-selective coding by single neurons in the human parahippocampal cortex. Proceedings of the National Academy of Sciences, 114, 1153-1158. doi:10.1073/pnas.1608159113 (* = co-first author)

Kornblith, S., Buschman, T. J., and Miller, E. K. (2015). Stimulus load and oscillatory activity in higher cortex. Cerebral Cortex, 26, 3772-3784. doi:10.1093/cercor/bhv182

Mulliken, G. H., Bichot, N. P., Ghadooshahy, A., Sharma, J., Kornblith, S., Philcock, M., and Desimone, R. (2015). Custom-fit radiolucent cranial implants for neurophysiological recording and stimulation. Journal of Neuroscience Methods, 241, 146–154. doi:10.1016/j.jneumeth.2014.12.011

Kornblith, S., Cheng, X., Ohayon, S., and Tsao, D. (2013). A network for scene processing in the macaque temporal lobe. Neuron, 79, 766-781. doi:10.1016/j.neuron.2013.06.015

Mormann, F., Dubois, J., Kornblith, S., Milosavljevic, M., Cerf, M., Ison, M., Tsuchiya, N., Kraskov, A., Quiroga, R. Q., Adolphs, R., Fried, I., and Koch, C. (2011). A category-specific response to animals in the right human amygdala. Nature Neuroscience, 14, 1247-1249. doi:10.1038/nn.2899

Mormann, F., Kornblith, S., Quiroga, R. Q., Kraskov, A., Cerf, M., Fried, I., and Koch, C. (2008). Latency and selectivity of single neurons indicate hierarchical processing in the human medial temporal lobe. Journal of Neuroscience, 28, 8865-8872. doi:10.1523/jneurosci.1640-08.2008

• Action Editor, TMLR
• Area Chair, NeurIPS 2021, NeurIPS 2022
• Outstanding Reviewer, CVPR 2021, CVPR 2022
• Expert Reviewer, ICML 2021
• Top Reviewer, ICML 2020, NeurIPS 2020
• Reviewer for Nature Neuroscience, Nature Communications, PNAS, TPAMI
• Walle Nauta Award for Excellence in Graduate Teaching (2013)
• Swartz Travel Award, Single Neuron Studies of the Human Brain (2011)
• National Science Foundation Graduate Research Fellowship (2010)
• MIT Norman B. Leventhal Presidential Fellow (2010)
• Caltech Upper Class Merit Award (2009)
• Caltech Carnation Scholarship (2008)
• Presidential Scholar Candidate (2006)

See my GitHub page.

Contact me by email at simon@simonster.com.