Skip to yearly menu bar Skip to main content


Workshop

Interpretable AI: Past, Present and Future

Suraj Srinivas ⋅ Michal Moshkovitz ⋅ Chhavi Yadav ⋅ Lesia Semenova ⋅ Nave Frost ⋅ Vinayak Abrol ⋅ Bitya Neuhof ⋅ Valentyn Boreiko ⋅ Dotan Di Castro ⋅ Himabindu Lakkaraju ⋅ Kamalika Chaudhuri
Project Page [ OpenReview] 

Abstract

Video

Chat is not available.

Schedule

Timezone: America/Los_Angeles
8:50 AM
Opening Remarks
10:00 AM
Poster Session
12:00 PM
Lunch
2:30 PM
Coffee Break
How Do Training Methods Influence the Utilization of Vision Models?
Paul Gavrikov ⋅ Shashank Agnihotri ⋅ Margret Keuper ⋅ Janis Keuper
[published paper track (COLT 2024)] A Theory of Interpretable Approximations
Marco Bressan ⋅ Nicolò Cesa-Bianchi ⋅ Emmanuel Esposito ⋅ Yishay Mansour ⋅ Shay Moran ⋅ Maximilian Thiessen
ProtoS-ViT: Visual foundation models for sparse self-explainable classifications
Hugues Turbe ⋅ Mina Bjelogrlic ⋅ Gianmarco Mengaldo ⋅ Christian Lovis
Competence-Based Analysis of Language Models
Adam Davies ⋅ Jize Jiang ⋅ Cheng Xiang Zhai
Residual Stream Analysis with Multi-Layer SAEs
Tim Lawson ⋅ Lucy Farnik ⋅ Conor Houghton ⋅ Laurence Aitchison
Latent Concept-based Explanation of NLP Models
Xuemin Yu ⋅ Fahim Dalvi ⋅ Nadir Durrani ⋅ Marzia Nouri ⋅ Hassan Sajjad
Exploiting Interpretable Capabilities with Concept-Enhanced Diffusion and Prototype Networks
Alba Carballo Castro ⋅ Sonia Laguna ⋅ Moritz Vandenhirtz ⋅ Julia Vogt
Subgroup Discovery with the Cox Model
Zachary Izzo ⋅ Iain Melvin
Explainable AI-based analysis of human pancreas sections detects traits of type 2 diabetes
Lukas Klein ⋅ Sebastian Ziegler ⋅ Felicia Gerst ⋅ Yanni Morgenroth ⋅ Karol Gotkowski ⋅ Eyke Schöniger ⋅ Nicole Kipke ⋅ Annika Seiler ⋅ Ellen Geibelt ⋅ Martin Heni ⋅ Silvia Wagner ⋅ Silvio Nadalin ⋅ Falko Fend ⋅ Daniela Aust ⋅ Andre Mihaljevic ⋅ Daniel Hartmann ⋅ Jurgen Weitz ⋅ Reiner Schwartzenberg ⋅ Marius Distler ⋅ Andreas Birkefeld ⋅ Susanne Ullrich ⋅ Paul Jaeger ⋅ Fabian Isensee ⋅ Michele Solimena ⋅ Robert Wagner
Explainable Concept Generation through Vision-Language Preference Learning
Aditya Taparia ⋅ Som Sagar ⋅ Ransalu Senanayake
Disentangling Mean Embeddings for Better Diagnostics of Image Generators
Sebastian Gruber ⋅ Pascal Tobias Ziegler ⋅ Florian Buettner
Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models
Konstantin Donhauser ⋅ Gemma Moran ⋅ Aditya Ravuri ⋅ Kian Kenyon-Dean ⋅ Kristina Ulicna ⋅ Cian Eastwood ⋅ Jason Hartford
Position: XAI needs formal notions of explanation correctness
Stefan Haufe ⋅ Rick Wilming ⋅ Benedict Clark ⋅ Rustam Zhumagambetov ⋅ Danny Panknin ⋅ Ahcene Boubekki
Error-controlled interaction discovery in deep neural networks
Winston Chen ⋅ Yifan Jiang ⋅ William Stafford Noble ⋅ Yang Lu
Evaluating Machine Learning Models with NERO: Non-Equivariance Revealed on Orbits
Zhuokai Zhao ⋅ Takumi Matsuzawa ⋅ William Irvine ⋅ Michael Maire ⋅ Gordon Kindlmann
This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizations
Chiyu Ma ⋅ Brandon Zhao ⋅ Chaofan Chen ⋅ Cynthia Rudin
Bivariate Decision Trees: Smaller, Interpretable, More Accurate
Rasul Kairgeldin ⋅ Miguel A. Carreira-Perpinan
ConceptDrift: Uncovering Biases through the Lens of Foundational Models
Cristian D Paduraru ⋅ Elena Burceanu ⋅ Antonio Barbalau ⋅ Andrei Nicolicioiu ⋅ Radu Filipescu
A is for Absorption: Studying Sparse Autoencoder Feature Splitting and Absorption in Spelling Tasks
James Wilken-Smith ⋅ Tomáš Dulka ⋅ David Chanin ⋅ Hardik Bhatnagar ⋅ Joseph Bloom
Deep quantum graph dreaming: deciphering neural network insights into quantum experiments
Tareq Jaouni ⋅ Sören Arlt ⋅ Carlos Ruiz-Gonzalez ⋅ Ebrahim Karimi ⋅ Xuemei Gu ⋅ Mario Krenn
CoS: Enhancing Personalization and Mitigating Bias with Context Steering
Sashrika Pandey ⋅ Jerry He ⋅ Mariah Schrum ⋅ Anca Dragan
A Concept-Based Explainability Framework for Large Multimodal Models
Jayneel Parekh ⋅ Pegah KHAYATAN ⋅ Mustafa Shukor ⋅ Alasdair Newson ⋅ Matthieu Cord
SignAttention: On the Interpretability of Transformer Models for Sign Language Translation
Pedro Alejandro Dal Bianco ⋅ Oscar Stanchi ⋅ Facundo Manuel Quiroga ⋅ Franco Ronchetti ⋅ Enzo Ferrante
Interactive Semantic Interventions for VLMs: A Human-in-the-Loop Approach to Interpretability
Lukas Klein ⋅ Kenza Amara ⋅ Carsten Lüth ⋅ Antonio Foncubierta-Rodriguez ⋅ Hendrik Strobelt ⋅ Mennatallah El-Assady ⋅ Paul Jaeger
Right on Time: Revising Time Series Models by Constraining their Explanations
Maurice Kraus ⋅ David Steinmann ⋅ Antonia Wüst ⋅ Andre Kokozinski ⋅ Kristian Kersting
Isometry pursuit
Samson Koelle ⋅ Marina Meila
A Mechanism for Storing Positional Information Without Positional Embeddings
Chunsheng Zuo ⋅ Pavel Guerzhoy ⋅ Michael Guerzhoy
What do we even know about interpretability?
Julian Skirzynski ⋅ Berk Ustun ⋅ Elena Glassman
GAMformer: Exploring In-Context Learning for Generalized Additive Models
Andreas Mueller ⋅ Julien Siems ⋅ Harsha Nori ⋅ Rich Caruana ⋅ Frank Hutter
The effect of whitening on explanation performance
Benedict Clark ⋅ Stoyan Karastoyanov ⋅ Rick Wilming ⋅ Stefan Haufe