Farnoush Rezaei Jafari

prof_pic.jpg

I am a doctoral researcher in the Machine Learning / Intelligent Data analysis group at Technische Universität Berlin and BIFOLD (Berlin Institute for the Foundations of Learning and Data), working with Prof. Dr. Klaus-Robert Müller. My primary focus lies in enhancing the interpretability and efficiency of multi-modal LLMs, as well as vision and language models.

Before embarking on my Ph.D. journey, I accomplished my M.Sc. in Computer Science at TU Berlin in the year 2021. I did my Master’s thesis, titled “Analyzing the Importance of Temporal Information in 3D ConvNets for Human Action Recognition Through Explanations” under the supervision of Prof. Dr. Klaus-Robert Müller and Prof. Dr. Jürgen Gall.

news

Oct 22, 2025 🥳 Our paper, RelP accepted as a spotlight at Mechanistic Interpretability Workshop at NeurIPS 2025.
Mar 17, 2025 🎉 I have been accepted into the MATS 8.0 Training Program, led by Neel Nanda.
Jan 16, 2025 🎙️ Invited talk at Microsoft ASG about our NeurIPS 2024 paper, MambaLRP.
Jan 6, 2025 🥳 Our paper Towards Symbolic XAI has got accepted at Information Fusion.
Sep 27, 2024 🎉 Our paper, MambaLRP, has got accepted at NeurIPS 2024.
Aug 30, 2024 📢 Check out our new preprint Towards Symbolic XAI.
Jun 11, 2024 📢 Check out our new preprint on the interpretability of selective state space sequence models, called MambaLRP.
Jul 3, 2022 🥳 Our paper, ATS is accepted at ECCV 2022 as an oral presentation.
Jun 14, 2022 🎙️ Presented our paper, ATS at Franco-German Workshop at Inria.
Nov 17, 2021 🚀 I started my PhD journey.

Publications

  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

  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

  3. 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

  4. 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