ðŸŠī Berwin Gan

            • Luminal - Search-Based Deep Learning Compilers
              • REOrdering Patches Improves Vision Models
              • FlexAttention
              • How Attention Sinks Keep Language Models Stable
              • Muon - An optimizer for hidden layers in neural networks
            • Distillation Robustifies Unlearning
            • H-Net
            • Hierarchical Reasoning Model
            • Language Models in Plato's Cave
            • Learning Compositional Models of the World
            • STP: Self-Play LLM Theorem Provers with Iterative Conjecturing and Proving
      • Aggregate Voting Rank ðŸ—ģïļ
      • Covering Discs and Orthants 📐
      • Lambda Calculus ðŸ§Ū
    Home

    âŊ

    Notes 🗒ïļ

    âŊ

    Machine Learning ðŸĪ–

    âŊ

    Research

    Folder: Notes-🗒ïļ/Machine-Learning-ðŸĪ–/Research

    9 items under this folder.

    • Aug 16, 2025

      H-Net

      • Aug 16, 2025

        Mechanistic-Interpretability

        • folder
      • Jul 29, 2025

        Hierarchical Reasoning Model

        • hierarchy
      • Jun 28, 2025

        STP: Self-Play LLM Theorem Provers with Iterative Conjecturing and Proving

        • self-play
        • agents
      • Jun 18, 2025

        Optimizer

        • folder
      • Jun 17, 2025

        Language Models in Plato's Cave

        • llm
        • video
        • vision
      • Jun 15, 2025

        Holding

        • folder
      • Jun 14, 2025

        Distillation Robustifies Unlearning

        • unlearning
        • distillation
      • Jun 10, 2025

        Learning Compositional Models of the World

        • planning
        • composition

      Created with Quartz v4.4.0 ÂĐ 2025

      • GitHub
      • Discord Community