GAIPS Lab

15/04/2026

✨ The first INESC-ID GAIPS Trimonthly Digest from 2026 is out!

Don't miss the chance to discover GAIPS updates from January to March 2026!
🔗 Read it in full in here: https://canva.link/8g5h4eqy50tdqso

24/03/2026

🤖 GAIPS is at HRI 2026 in Edinburgh, Scotland! 🏴󠁧󠁢󠁳󠁣󠁴󠁿

Swipe to discover our work ➡️

📄 Full papers by Joana Brito (with Ana Paiva and Joana Campos), and Rui Prada

And that's not all — Sandra Andrade also represented GAIPS at the Workshop on Designing Transparent and Understandable Robots (D-TUR), presenting the ERROR-MM Project: Exploring Robotlike Robot Behaviours in Users' Mental Models. 🛠️

Check our Link In Bio for these papers 🔗

05/02/2026

🎉 New paper accepted! 🎉

GAIPS member Regina Duarte just published exciting new research on how AI and Explainable AI (XAI) shape real clinical decision-making 🏥🤖

Instead of focusing on isolated diagnostic tasks, this study looks at the full clinical workflow — from exams to diagnosis and treatment — revealing important trade-offs between accuracy and efficiency.

Great work by Mónica Abreu, Prof. Joana Campos, and our amazing clinical partners at Hospital da Luz!

📄 Read the paper here: https://dl.acm.org/doi/abs/10.1145/3788685

30/01/2026

Here’s Pedro at yet another international conference! 🙌 ✨
GAIPS member Pedro P. Santos presented his work, “Centralized training with hybrid ex*****on in multi-agent reinforcement learning via predictive observation imputation”, at the 40th Annual AAAI Conference on Artificial Intelligence, AAAI 2026, in Singapore.

Check out his paper: https://doi.org/10.1016/j.artint.2025.104404

07/12/2025

This week we are inviting you to join in on our bi-weekly group meeting for a special talk by Prof. Miguel Couceiro. The talk will place next Wednesday, December 10th, at 11:00 AM in room 1.38 IST - Taguspark.

Miguel Couceiro is a Full Professor in Computer Science (CS) and in Mathematics (Math) at the Instituto Superior Técnico (IST), U. Lisbon. With 200+ publications and major contributions to fair & explainable AI and automated reasoning, he leads and collaborates on several European and ANR projects.

This talk revisits the foundations of analogical reasoning in AI and introduces a new unified framework for analogical inference in continuous domains. It extends analogy-based learning to both classification and regression, providing theoretical guarantees and practical, closed-form prediction rules. Featuring results from an upcoming AAAI 2026 paper.

Join us ✨

05/12/2025

New Publication Alert! 📖
We’re excited to share GAIPS members Henrique Fonseca and António Fernandes' new paper titled “Can Media Act as a Soft Regulator of Safe AI Development? A Game Theoretical Analysis.” This work emerged from the 2025 AI Governance Modelling Workshop, hosted by Teesside University (UK), and was officially published and presented at ALIFE 2025.

🔗 Read the full paper here: https://direct.mit.edu/isal/proceedings/isal2025/37/90/134023

25/11/2025

Another GAIPS adventure unlocked! 🎮✨

This time, GAIPS member Miguel Belbute transformed a 3rd-grade classroom into a mini game dev studio — teaching curious young minds the basics of game design and development! 👾💡

This session was part of “Engenharia para Todos”, a project by Câmara Municipal de Oeiras and Instituto Superior Técnico in collaboration with INESC-ID, promoting scientific and technological literacy in Oeiras 💛🔧🌍

Future creators, coders, and game designers—level up! 🚀🎉

02/11/2025

Last month, GAIPS member Diogo Carvalho presented this paper at EPIA 2025!

You can read the work here: https://rdcu.be/eNUs

New publication! 📖

Visiting student Victor Pugliese collaborated with GAIPS members Diogo Carvalho, Fábio Faria and Francisco Melo on a paper titled “Optimizing 2D Packing Strategies for Autoclave Loading Using Deep Reinforcement Learning”, which will be presented this week at The EPIA 2025 international conference on Artificial Intelligence. Read this work here: https://link.springer.com/chapter/10.1007/978-3-032-05179-0_4

10/10/2025

Thrilled to announce that GAIPS has contributed to the OECD’s AI and Future of Skills (AIFS) project! 🚀

Our team at GAIPS helped develop the Social Interaction scale, part of a broader framework comparing human and AI skills across nine domains. This scale captures AI agents’ and robots’ ability to perceive and respond to social cues—a challenging task, as true social intelligence emerges through embodied interaction over time.

Proud to see this work culminate in an OECD report and grateful for the chance to collaborate with such an amazing team! 🌟

03/10/2025

Here’s some photos of GAIPS member Pedro Pinto Santos presenting his work on the 42nd International Conference on Machine Learning (ICML 2025) in Vancouver and the 18th European Workshop on Reinforcement Learning (EWRL 2025) in Tübingen, Germany. His poster was selected as a "spotlight poster" (top 2.6% of the papers), and can be found here: https://icml.cc/virtual/2025/poster/45751

30/09/2025

New publication! 📖

Visiting student Victor Pugliese collaborated with GAIPS members Diogo Carvalho, Fábio Faria and Francisco Melo on a paper titled “Optimizing 2D Packing Strategies for Autoclave Loading Using Deep Reinforcement Learning”, which will be presented this week at The EPIA 2025 international conference on Artificial Intelligence. Read this work here: https://link.springer.com/chapter/10.1007/978-3-032-05179-0_4

23/09/2025

We welcome our newest senior researcher at GAIPS, Dr Anna Ciaunica! 🙌 She will be attending ALife 2025 and Tech for Impact Summit 2025, and she will be making an appearance at Tufts University and on the 6th International Workshop on Active Inference.
Make sure not to miss Anna’s insightful talks on these upcoming events! 📆