Now showing items 190-192 of 36487

    • Towards More Interpretable AI With Sparse Autoencoders 

      Engels, Joshua (Massachusetts Institute of Technology, 2025-05)
      While large language models demonstrate remarkable capabilities across diverse domains, the specific representations and algorithms they learn remain largely unknown. The quest to understand these mechanisms holds dual ...
    • Transmission Line Dynamics Modeling For Power Electronics-Enabled Control in the Electric Power Systems 

      Lawson, Riley E. (Massachusetts Institute of Technology, 2025-05)
      In the analysis and operation of electric power systems, understanding the rates at which dynamic phenomena evolve is critical. Classically, power systems operate on multiple time scales, with slower mechanical dynamics ...
    • Foundation Models for Protein Phenotype Prediction 

      Calef, Robert (Massachusetts Institute of Technology, 2025-05)
      Understanding the roles of human proteins remains a major challenge, with approximately 20% of human proteins lacking known functions and more than 40% missing context-specific functional insights. Even well-annotated ...