Graduate Theses: Recent submissions

Now showing items 466-468 of 36544

    • The Phase Transition for Recovering a Random Hypergraph from its Edge Data 

      Yao, Andrew (Massachusetts Institute of Technology, 2025-05)
      The weighted projection of a hypergraph is the weighted undirected graph with the same vertex set and edge weight equal to the number of hyperedges that contain the edge; the projection is the unweighted graph with the ...

    • Empowering Mobile-Only App Generation — Offline AI Code Generation with App Inventor 

      Yuan, Joyce (Massachusetts Institute of Technology, 2025-05)
      As digital tools become more accessible, creating software is becoming a powerful way for anyone to make real-world impact. Computational action—the idea that learners can build computing artifacts with authentic relevance ...

    • AutoDiff: A Scalable Framework for Automated Model Comparison 

      Woo, Andrew Kyoungwan (Massachusetts Institute of Technology, 2025-05)
      Post-training adaptations such as supervised fine-tuning, quantization, and reinforcement learning can cause large language models (LLMs) with identical architectures to exhibit divergent behaviors. However, the mechanisms ...