Publications

* denotes equal contribution.

2025

  1. MechInterp Workshop @ NeurIPS 2025, Spotlight
    Preview image
    RelP: Faithful and Efficient Circuit Discovery via Relevance Patching
    F. Rezaei Jafari , O. Eberle , A. Khakzar , N. Nanda
    Mechanistic Interpretability Workshop @ NeurIPS 2025

    Circuit/Subgraph-Level Model Analysis; LLMs; Mechanistic Interpretability; Sparse Feature Circuits

    PDF Website
  2. Information Fusion
    Preview image
    Towards Symbolic XAI – Explanation Through Human Understandable Logical Relationships Between Features
    T.* Schnake , F.* Rezaei Jafari , J Lederer , P. Xiong , S. Nakajima , S. Gugler , G. Montavon , K-R. Müller
    Information Fusion 2025

    Compositional Reasoning in LLMs & Vision Transformers; Subgraph-Level Model Analysis; Bridging Mechanistic Interpretability with Symbolic Reasoning; Logical Explanations for Transformers & GNNs

    PDF Website

2024

  1. NeurIPS
    Preview image
    MambaLRP: Explaining Selective State Space Sequence Models
    F. Rezaei Jafari , G. Montavon , K-R. Müller , O. Eberle
    Conference on Neural Information Processing Systems (NeurIPS) 2024

    State-Space Models; Mamba LLMs; Vision Mamba; Interpretability; Identifying Model Biases; Analyzing Long-Range Dependencies; Introducing a Novel Evaluation Metric for Needle-in-a-Haystack

    PDF Website

2022

  1. ECCV, Oral
    Preview image
    Adaptive Token Sampling For Efficient Vision Transformers
    M.* Fayyaz , S.* Abbasi Kouhpayegani , F.* Rezaei Jafari , S. Sengupta , E. Sommerlade , H. Vaezi Joze , H. Pirsiavash , J. Gall
    European Conference on Computer Vision (ECCV) 2022

    Test-Time Computation Scaling; Efficient Image/Video Transformers; Parameter-Free Adaptive Token Sampling; Emergent Capabilities in Vision Transformers

    PDF Website