ELLIS / ELIAS / ELLIOT / ELSA HCML Workshop 2026

Annual workshop of the ELLIS Human-centric Machine Learning Program — focused on trustworthy AI, robustness, fairness, transparency, and interpretability of large-scale AI systems.

📅 27–28 May 2026
📍 Alicante, Spain
🌐 Hybrid Attendance
Scientific Event

General Information

FormatHybrid — in-person attendance in Alicante + online via Microsoft Teams
Duration2 days (working dinner on May 27; main workshop on May 28)
LanguageEnglish
TimezoneCEST (UTC+2)
Open to ELLIS ELIAS ELLIOT ELSA
Focus areasRobustness, safety & security, fairness, transparency, accountability, interpretability of LLMs, VLMs, and multimodal systems
LocationSala Rafael Altamira, Sede Universitaria Ciudad de Alicante, Spain
FeeNone
Working Dinner
27 May 2026
19:00 – 21:00
Main Workshop
28 May 2026
09:00 – 18:15
Online
Teams Link
TBC after registration
About

Description

This is the annual workshop of the ELLIS Human-centric Machine Learning Program, bringing together researchers from across the ELLIS, ELIAS, ELLIOT, and ELSA networks. Hosted in Alicante, Spain, the workshop focuses on trustworthy AI — one of the most pressing challenges in modern machine learning.

Topics span the full spectrum of trustworthy AI: robustness, safety and security, fairness, transparency, accountability, and interpretability of large-scale AI systems including LLMs, VLMs, and multimodal architectures.

The workshop is co-organized by Adrian Weller, Plamen Angelov, and Nuria Oliver. Its goals are to share an update on ELLIS, understand what each fellow is working on, and explore concrete ways to collaborate.

Both in-person attendance in Alicante and hybrid online participation via Microsoft Teams are supported.

Program

Schedule

All times in CEST (UTC+2). Agenda reflects the confirmed program structure.

Pre
Wednesday, 27 May 2026
Working Dinner & Panel
19:00 – 21:00
Dinner + Panel
AI in Higher Education
Cristina Cachero, University of Alicante
Moderator: Nuria Oliver
1
Thursday, 28 May 2026
Main Workshop — Trustworthy AI
09:00 – 09:20
Welcome
Welcome & Coffee
09:20 – 09:30
Introduction
Aims of the Workshop
ELLIS update · Fellows' work · Collaboration opportunities
Plamen Angelov, Nuria Oliver, Adrian Weller
09:30 – 10:30
Invited Talk
Dismantling Myths of Omnipotence: Foundation Models, Diversity and Epistemic Justice
Paula Helm, Goethe University — 40' talk + discussion
10:30 – 11:15
Session 1
AI Safety and Security
Nuria Oliver (ELLIS Alicante) — Jailbreaking reasoning models
Juan Antonio Pérez-Ortiz (Universitat d'Alacant) — Ethics of collecting linguistic data from indigenous people
Summary and Q&A
11:15 – 11:45
Break
Coffee Break
11:45 – 13:15
Session 2
Humans and AI
Bruno Lepri (Fondazione Bruno Kessler) — Generative AI collective behavior: an interactionist paradigm
Ciro Cattuto (ISI Foundation) — Agent frameworks for complex systems simulation
Umang Bhatt (University of Cambridge) — Building a Human API
Plamen Angelov (Lancaster University) — Knowledge preserving continual learning
Summary and Q&A
13:15 – 15:00
Lunch
Lunch — Mareando la Huerta
15:00 – 16:00
PhD & PostDoc Forum
Spotlight Talks — Early Career Researchers
5-minute talks per researcher
AI Safety
Ella Streefkerk (Goethe University Frankfurt)
Diego Miguel Lozano (ELLIS Alicante)
Adrián Arnaiz (ELLIS Alicante)
Bias & Fairness
Aditya Gulati (ELLIS Alicante)
Mengting Wei (University of Oulu)
Ioannis Sarridis (CERTH)
AI, Humans & Society
Julien Colin (ELLIS Alicante)
Kim Zierhan (ELLIS Alicante)
Ariella Shulman (University of Cambridge)
Elaf Almahmoud (University of Cambridge)
16:00 – 17:00
Invited Talk
Talk title TBC
Tom Lenaerts, Université libre de Bruxelles / Vrije Universiteit Brussel — 40' talk + discussion
18:00 – 18:15
Closing
Discussion & Closing
Invited Speakers

Confirmed Speakers

Invited Talk
Paula Helm
Goethe University — Dismantling Myths of Omnipotence: Foundation Models, Diversity and Epistemic Justice
Invited Talk
Tom Lenaerts
Université libre de Bruxelles / Vrije Universiteit Brussel — Talk title TBC
Session 2
Bruno Lepri
Fondazione Bruno Kessler — Generative AI collective behavior: an interactionist paradigm
Session 2
Ciro Cattuto
ISI Foundation — Agent frameworks for complex systems simulation
Session 2
Umang Bhatt
University of Cambridge — Building a Human API
Session 2
Plamen Angelov
Lancaster University — Knowledge preserving continual learning
Participation

Open Networks

The workshop is open to participants from the following European AI research networks. Researchers working on trustworthy, safe, robust, secure, and interpretable AI systems are especially encouraged to register.

  • ELLIS — European Laboratory for Learning and Intelligent Systems
  • ELIAS — European Lighthouse of AI for Sustainability
  • ELLIOT — ELLIS network participants
  • ELSA — European Lighthouse on Secure and Safe AI

The workshop is part of the ELLIS Programs initiative, inspired by the CIFAR Program model, and closely collaborates with the CIFAR LMB (Learning in Machines and Brains) Program.

Location

Venue

Workshop activities will be held at the Sala Rafael Altamira, Sede Universitaria Ciudad de Alicante, Spain. Online participants can attend via a Microsoft Teams link, to be confirmed after registration.

RoomSala Rafael Altamira
VenueSede Universitaria Ciudad de Alicante
CityAlicante, Spain
OnlineMicrosoft Teams — link TBC post-registration
FAQ

Frequently Asked Questions

Who can attend the workshop?
The workshop is open to participants from the ELLIS, ELIAS, ELLIOT, and ELSA networks — especially those working on trustworthy, safe, robust, secure, and interpretable AI systems. Register via the form to confirm attendance.
Is online attendance possible?
Yes. The workshop supports hybrid attendance. Online participants will receive a Microsoft Teams link after registering via the registration form.
Is there a registration fee?
No. The workshop is free to attend for eligible participants from ELLIS, ELIAS, ELLIOT, and ELSA networks.
What is the ELLIS Programs model?
ELLIS Programs are thematic research groups directed by outstanding European researchers and including leading researchers as Program Fellows. They focus on high-impact AI problem areas, are inspired by the CIFAR Program model, and closely collaborate with the CIFAR LMB Program. Each Program has a budget for 2–3 workshops per year.
Join Event

Register Today

Please complete the formal sign-up via the Microsoft registration form system to reserve your physical seat in Alicante or obtain the online streaming links.

1
Click the Register Now action link down below.
2
Fill out your profile details along with network affiliation status (ELLIS, ELIAS, ELLIOT, or ELSA).
3
Receive calendar configuration parameters and the Microsoft Teams broadcast channel links directly via email.
💡
Notice for Remote Attendees: Remote entry lines open 15 minutes before the initial schedule blocks launch each day.
Register Now via Microsoft Forms →

Upcoming Events