Reading Group Papers

Papers presented and scheduled for the Interpretable Deep Learning Reading Group.

Next Paper

  1. Title: Concept Bottleneck Large Language Models
    Presenter: Sun Chung-En
    Presentation Date: April 29, 2026
    Paper

Upcoming Reading Group Papers

  1. Title: Towards Reasonable Concept Bottleneck Models
    Presenter: Nektarios Kalampalikis
    Presentation Date: May 13, 2026
    Paper
  2. Title: Toward Informative, Training-free, and Task-agnostic Inherent Interpretability based on Pre-trained Language Models
    Presenter: Shin'ya Yamaguchi
    Presentation Date: May 20, 2026
    Paper
  3. Title: Selective Concept Bottleneck Models Without Predefined Concepts
    Presenter: Simon Schrodi
    Presentation Date: May 27, 2026
    Paper
  4. Title: Hierarchical Concept-based Interpretable Models
    Presenter: Oscar Hill
    Presentation Date: June 3, 2026
    Paper
  5. Title: PostDoc@MPI-INF
    Presenter: Wolfgang Stammer
    Presentation Date: June 10, 2026
    Paper

Previous Reading Group Papers

  1. Title: Concept Bottleneck Large Language Models
    Presenter: Chung-En Sun
    Presentation Date: April 15, 2026
    Paper
  2. Title: Interpretable and Steerable Concept Bottleneck Sparse Autoencoders
    Presenter: Akshay Kulkarni
    Presentation Date: April 8, 2026
    Paper
  3. Title: Object-Centric Concept Bottlenecks
    Presenter: David Steinmann
    Presentation Date: April 1, 2026
    Paper
  4. Title: Bayesian Concept Bottleneck Models with LLM Priors
    Presenter: Jean Feng
    Presentation Date: March 25, 2026
    Paper
  5. Title: There Was Never a Bottleneck in Concept Bottleneck Models
    Presenter: Antonio Almudévar
    Presentation Date: March 18, 2026
    Paper