Reading Group

The :brain: :cloud_with_lightning: Brainstorm XAI Reading Group is an international group of researchers who enjoy discussing and brainstorming about scientific papers. The group fosters a friendly, drama-free atmosphere and values diversity, equity, and inclusion. We encourage members to express their opinions freely and celebrate the diversity of perspectives and cultural backgrounds.

The primary goal of each meeting is not only to understand the papers but also to brainstorm their weak points, potential extensions, strengths, applications, and more. The group is open to anyone (students, researchers, or professors) who enjoys sharing ideas, brainstorm collaboratively, and critically analyze papers. To join, simply fill out this form: LINK. Once registered, you’ll be added to the mailing list and given access to calendar events.

Active since 2023, the group focuses on papers related to Explainable AI (XAI). We assume members have a basic understanding of XAI, and discussions span a wide range of domains, including vision, graphs, NLP, reinforcement learning, and classical AI.

Below, you can find updates on the scheduled presentations for the 2024/2025 season. Currently, we meet every other Tuesday at 6:30 PM CET / 9:30 AM Los Angeles Time.

  • 10 Dec 24
    • “GraphTrail: Translating GNN Predictions into Human-Interpretable Logical Rules”. Burouj Armgaan, Manthan Dalmia, Sourav Medya, and Sayan Ranu
  • 26 Nov 24
    • “Linear Explanations for Individual Neurons”. Tuomas Oikarinen, Tsui-Wei Weng
  • 12 Nov 24
    • “MambaLRP: Explaining Selective State Space Sequence Models”. Arnoush Rezaei Jafari, Gregoire Montavon, Klaus-Robert Muller, and Oliver Eberle
  • 29 Oct 24
    • “Explain via Any Concept: Concept Bottleneck Model with Open Vocabulary Concepts”. Andong Tan, Fengtao Zhou, and Hao Chen

Past presentations (2023/2024)

  • Concept Learning for Interpretable Multi-Agent Reinforcement Learning. Renos Zabounidis, Joseph Campbell, Simon Stepputtis, Dana Hughes, Katia Sycara
  • Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents. Quentin Delfosse, Sebastian Sztwiertnia, Mark Rothermel, Wolfgang Stammer, Kristian Kersting
  • IA-RED2: Interpretability-Aware Redundancy Reduction for Vision Transformers. Bowen Pan, Rameswar Panda, Yifan Jiang, Zhangyang Wang, Rogerio Feris, Aude Oliva
  • This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizations. Chiyu Ma, Brandon Zhao, Chaofan Chen, Cynthia Rudin
  • CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks. Tuomas Oikarinen, Tsui-Wei Weng
  • Everybody Needs a Little HELP: Explaining Graphs via Hierarchical Concepts. Jonas Jürß, Lucie Charlotte Magister, Pietro Barbiero, Pietro Liò, Nikola Simidjievski
  • Concept Bottleneck Generative Models. Aya Abdelsalam Ismail, Julius Adebayo, Hector Corrada Bravo, Stephen Ra, Kyunghyun Cho
  • Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents. Quentin Delfosse, Sebastian Sztwiertnia, Mark Rothermel, Wolfgang Stammer, Kristian Kersting
  • KAN: Kolmogorov-Arnold Networks. Ziming Liu, Yixuan Wang, Sachin Vaidya, Fabian Ruehle, James Halverson, Marin Soljačić, Thomas Y. Hou, Max Tegmark
  • Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet. Adly Templeton, Tom Conerly, Jonathan Marcus, Jack Lindsey, Trenton Bricken, Brian Chen, Adam Pearce, Craig Citro, Emmanuel Ameisen, Andy Jones, Hoagy Cunningham, Nicholas L Turner, Callum McDougall, Monte MacDiarmid, Alex Tamkin, Esin Durmus, Tristan Hume, Francesco Mosconi, C. Daniel Freeman, Theodore R. Sumers, Edward Rees, Joshua Batson, Adam Jermyn, Shan Carter, Chris Olah, Tom Henighan
  • Interpreting Language Models with Contrastive Explanations. Kayo Yin, Graham Neubig
  • Locating and Editing Factual Associations in GPT. Kevin Meng, David Bau, Alex Andonian, Yonatan Belinkov
  • From attribution maps to human-understandable explanations through Concept Relevance Propagation. *Reduan Achtibat, Maximilian Dreyer, Ilona Eisenbraun, Sebastian Bosse, Thomas Wiegand, Wojciech Samek & Sebastian Lapuschkin
  • What s in the Box? Exploring the Inner Life of Neural Networks with Robust Rules. Jonas Fischer, Anna Olah, Jilles Vreeken
  • Labeling Neural Representations with Inverse Recognition. Kirill Bykov, Laura Kopf, Shinichi Nakajima, Marius Kloft, Marina M.-C. Höhne