Deep Dive Workshop
Interpretability in the lab and in the wild
Organized by:
Friday 9 October 10.05
Lead organizer: Lenka Tětková, DTU Compute
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.
The session will combine invited talks (3 in total, 15 minutes per talk + 5 minutes of interactive Q&A, speakers from both industry and academia), lightning talks (intended mostly for junior participants), and interactive elements: structured discussions/round tables and a panel discussion with the speakers.
Welcome (5 minutes)
2 invited talks (2 x 15 minutes, plus 10 minutes for questions)
Lightning talks, part 1 (20 min)
open call before D3A
Structured discussions/round tables (20 minutes)
small group discussions for sharing experience and networking
Coffee break in the middle (10 minutes)
connected to the discussions, so that people can either continue with the discussions, or take a break
1 invited talk (15 minutes, plus 5 minutes for questions)
Panel discussion with all the speakers (20 minutes)
moderated by an organizer and integrating questions from the structured discussion
Lightning talks, part 2 (20 minutes)
Structured discussions/round tables (20 minutes)
Participants will form new groups, and have an opportunity for discussions with the lightning talk speakers
Wrap-up (5 minutes)
Niels Henrik Pontoppidan – Principal Scientist – Eriksholm Research Centre:
Real world interpretability in hearing health care
Nina Weng – 3Shape, formerly DTU (PhD defended in 2026):
How interpretability helps model auditing in the GenAI era
Constanza Fierro (postdoc) & Isra Salazar (PhD student) – KU:
Visual information flow in vision-language models
Intermediate: For attendees who have basic understanding or some experience with the subject but are not yet advanced.