Doctoral Theses: Recent submissions

Now showing items 169-171 of 23400

    • Steering Vision at Scale: From the Model Weights to Training Data 

      Materzyńska, Joanna (Massachusetts Institute of Technology, 2025-09)
      We study the interpretability and controllability of multimodal and generative models, with a particular focus on text–image representation models and text-to-image diffusion systems. We begin by addressing limitations in ...

    • How Data Drives ML Models Performance 

      Khaddaj, Alaa (Massachusetts Institute of Technology, 2025-09)
      Data has been been playing an increasingly more important role in the machine learning (ML) pipeline. This thesis deepens the understanding of the effect of the data on model performance and reliability. First, we study ...

    • Understanding and Overcoming Optimization Barriers in Non-convex and Non-smooth Machine Learning 

      Gatmiry, Khashayar (Massachusetts Institute of Technology, 2025-09)
      At their core, our machine learning systems are trained by solving an optimization problem, where the goal is to minimize a predefined objective function by adjusting model parameters based on the data. Despite the wealth ...