Graduate Theses: Recent submissions

Now showing items 40-42 of 36437

    • Cognify: An On-Device, AI-powered Learning Assistant 

      Huang, Siyong (Massachusetts Institute of Technology, 2025-09)
      Large Language Models (LLMs) have proven highly effective for a wide range of natural language processing tasks, but their size and compute requirements often restrict their use to powerful cloud-based infrastructures. In ...

    • Performance Analysis of the Apple AMX Matrix Accelerator 

      Zhou, Jonathan (Massachusetts Institute of Technology, 2025-09)
      Apple Silicon integrates a dedicated Apple Matrix Coprocessor (AMX) that executes outer-product style computations with high throughput, but its public programming model remains largely hidden behind the Accelerate framework. ...

    • Optimizing Large Language Models from a Data SystemsPerspective 

      Chen, Peter Baile (Massachusetts Institute of Technology, 2025-09)
      Strong retrieval and reasoning capabilities are essential for large language models (LLMs) to effectively handle a broad spectrum of downstream tasks, such as open-domain question answering and solving math or science ...