The MIT Libraries is completing a major upgrade to DSpace@MIT. Starting May 5 2026, DSpace will remain functional, viewable, searchable, and downloadable, however, you will not be able to edit existing collections or add new material. We are aiming to have full functionality restored by May 18, 2026 but intermittent service interruptions may occur. Please email dspace-lib@mit.edu with any questions. Thank you for your patience as we implement this important upgrade.

Publications: Recent submissions

Now showing items 88-90 of 160

    • 3D Object-Oriented Learning: An End-to-end Transformation-Disentangled 3D Representation 

      Liao, Qianli; Poggio, Tomaso (2017-12-31)
      We provide more detailed explanation of the ideas behind a recent paper on “Object-Oriented Deep Learning” [1] and extend it to handle 3D inputs/outputs. Similar to [1], every layer of the system takes in a list of ...

    • Exact Equivariance, Disentanglement and Invariance of Transformations 

      Liao, Qianli; Poggio, Tomaso (2017-12-31)
      Invariance, equivariance and disentanglement of transformations are important topics in the field of representation learning. Previous models like Variational Autoencoder [1] and Generative Adversarial Networks [2] attempted ...

    • Object-Oriented Deep Learning 

      Liao, Qianli; Poggio, Tomaso (Center for Brains, Minds and Machines (CBMM), 2017-10-31)
      We investigate an unconventional direction of research that aims at converting neural networks, a class of distributed, connectionist, sub-symbolic models into a symbolic level with the ultimate goal of achieving AI ...