Interpretability has become a standard part of the data scientist’s toolkit. Explainability libraries are easy to install, but there is a gap between what they promise in papers and what they deliver on real models under real-time pressure. Explanations sometimes mislead, contradict, or reveal bugs you wish you had not found.

This session brings together practitioners and researchers to share what interpretability looks like in practice: e.g., a model debugged through an explanation revealing a hidden shortcut; a deployment where stakeholders disagreed on what makes a good explanation; a method that worked on benchmarks but broke in production. We want the successes and the failures, the tips that are not in any tutorial, and the open problems no one has solved.

Invited and lightning talks from industry and academia, a panel discussion, and roundtables will spark discussion and networking.

—————

Be part of shaping the discussions – call for Lightning talks

Have you used interpretability methods in practice? We invite 5-minute lightning talks from researchers and practitioners sharing experiences with interpretability.

We welcome success stories, failures, lessons learned, deployment challenges, unexpected findings, and open problems.

Submit: A short abstract (100-200 words) to lenhy@dtu.dk by October 4.

—————-

Programme

Welcome (5 minutes)

2 invited talks + Q&A (40 min)

Lightning talks, part 1 (20 min)

Structured discussions/round tables (25 minutes)

Lunch break

1 invited talk + Q&A (20 minutes)

Panel discussion with all the speakers (20 minutes) 

Lightning talks, part 2 (20 minutes)

Structured discussions/round tables (25 minutes)

Wrap-up (5 minutes)

Invited talks

Real world interpretability in hearing health care
Niels Henrik Pontoppidan, Principal Scientist, Eriksholm Research Centre

Hierarchical Reasoning Models, Deconstructed
Lukas Galke Poech, Associate Professor, University of Southern Denmark

Visual information flow in vision-language models
Isra Salazar, PhD student, KU

Level

Intermediate: For attendees who have basic understanding or some experience with the subject but are not yet advanced.

Organizers

• Lenka Tětková, postdoc, DTU (lead organizer)
• Stella Frank, postdoc, DTU
• Teresa Dorszewski, postdoc, KU
• Lorenz Linhardt, PhD student, TU Berlin