December 7, 2023: MIT SuperUROP Presentations by Heidi Durresi and Kaivu Hariharan. October 6, 2023: NIH awards funding to BRAIN CONNECTS project involving CSAIL researchers September 5, 2023: SmartEM project posted on Forbes (Youtube video). May 31, 2023: Lu Mi and Michael Coulombe’s graduation (with Nir Shavit, Tony Wang, Linghao Kong) Group member Tony Wang’s research on adversarially exploiting superhuman Go AIs featured in the Financial Times! Lu Mi defended her thesis “Deep Learning Tools for Next-Generation Connectomics” on August 18, 2022. Check out her slides. Coming soon in Nature! “We are delighted to accept your manuscript entitled “Connectomes across development reveal principles of brainRead More →


High Throughput Connectomics The current design trend in large scale machine learning is to use distributed clusters of CPUs and GPUs with MapReduce-style programming. Some have been led to believe that this type of horizontal scaling can reduce or even eliminate the need for traditional algorithm development, careful parallelization, and performance engineering. This paper is a case study showing the contrary: that the benefits of algorithms, parallelization, and performance engineering, can sometimes be so vast that it is possible to solve “clusterscale” problems on a single commodity multicore machine. Connectomics is an emerging area of neurobiology that uses cutting edge machine learning and image processingRead More →

Graduate Students

Lu Mi

Jonathan Rosenfeld


Shraman Ray Chaudhuri
Will Noble


David Budden
Jonathan Stoller
Gergely Odor
Victor Jakubiuk
Quan Nguyen
Robert Radway


Wang, Tony T., Wang, Miles, Hariharan, Kaivalya, Shavit, Nir. Forbidden Facts: An Investigation of Competing Objectives in Llama 2. NeurIPS 2023 ATTRIB and SoLaR Workshops, December 2023. Meirovitch, Yaron, Park, Core Francisco, Mi, Lu, Potocek, Pavel, Sawmya, Shashata, Li, Yicong, Wu, Yuelong, Schalek, Richard, Pfister, Hanspeter, Schoenmakers, Remco, Peemen, Maurice, Lichtman, Jeff W., Samual, Aravinthan, Shavit, Nir. SmartEM: Machine-Learning Guided Electron Microscopy. bioRxiv: 2023.10.05.561103v1, October 2023. Li, Yicong, Meirovitch, Yaron, Kuan, Aaron T., Phelps, Jasper S., Pacureanu, Alexandra, Lee, Wei-Chung Allen, Shavit, Nir, Mi, Lu. X-Ray2EM: Uncertainty-Aware Cross-Modality Image Reconstruction from X-Ray to Electron Microscopy in Connectomics. IEEE – ISBI 2023: International Symposium on BiomedicalRead More →


No resources yet! But check back in soon.