Skip to content

@sjtu-xai-lab Lab for Interpretability and Theory-Driven Deep Learning

Change the repository type filter

All

    Repositories list

    12 repositories

    • interaction-sparsity

      Public
      PyTorch implementation of the paper "Where We Have Arrived in Proving the Emergence of Sparse Interaction Primitives in AI Models" (ICLR 2024)
      Python
      •0•0•0•0•Updated Nov 11, 2024Nov 11, 2024

    • InteractionSparsity

      Public
      JavaScript
      •0•0•0•0•Updated Oct 23, 2024Oct 23, 2024

    • ReasoningMemorization

      Public
      Academic page for Paper: Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs
      JavaScript
      •1•0•0•0•Updated Oct 9, 2024Oct 9, 2024

    • UnifyAttribution

      Public
      JavaScript
      •0•0•0•0•Updated Oct 8, 2024Oct 8, 2024

    • sjtu-xai-lab.github.io

      Public
      Quanshi Zhang's website. Sjtu interpretable ml lab website.
      website
      HTML
      •1•3•0•0•Updated Oct 4, 2024Oct 4, 2024

    • InteractionDynamics

      Public
      Academic page for the empirical and theoretical findings of the two-phase dynamics of interactions
      JavaScript
      •0•0•0•0•Updated Oct 4, 2024Oct 4, 2024

    • interaction-concept

      Public
      PyTorch implementation of the paper "Does a Neural Network Really Encode Symbolic Concept?" (ICML 2023)
      Jupyter Notebook
      •0•9•0•0•Updated Aug 19, 2024Aug 19, 2024

    • generalizable-interaction

      Public
      PyTorch implementation of the paper "Defining and extracting generalizable interaction primitives from DNNs" (ICLR 2024)
      Jupyter Notebook
      •1•4•0•0•Updated Jun 13, 2024Jun 13, 2024

    • BNN-concepts

      Public
      PyTorch implementation of the paper "Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Concepts" (ICML 2023)
      Python
      •0•1•0•0•Updated Dec 27, 2023Dec 27, 2023

    • aog

      Public
      PyTorch Implementation of the paper "Defining and Quantifying the Emergence of Sparse Concepts in DNNs" (CVPR 2023)
      Jupyter Notebook
      •0•8•1•0•Updated Dec 24, 2023Dec 24, 2023

    • Learn

      Public
      PyTorch implementation of the paper "Towards the Difficulty for a Deep Neural Network to Learn Concepts of Different Complexities" in (NeurIPS 2023)
      Python
      •0•1•0•0•Updated Dec 13, 2023Dec 13, 2023

    • transformation-complexity

      Public
      PyTorch implementation of "Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs"
      Jupyter Notebook
      •0•1•0•0•Updated Jun 15, 2022Jun 15, 2022