The international scientific meeting in the field of Robotics is co-sponsored by the Portuguese Society for Robotics, IEEE and IEEE Robotics and Automation Society (RAS), through its Portuguese Chapter.
ICARSC 2019 will take place at Porto – Gondomar, April 24-26, 2019. The conference is organized by the University of Porto – Faculty of Engineering, INESC-TEC, LIACC, CISTER, P.Porto and by the Portuguese Society for Robotics.
More information at https://web.fe.up.pt/~icarsc2019/
The talk entitled “The Cognitive and Human Factors of Formal Methods” will be given on 23 July at 11:00 am in room B025, moderated by Prof. Alexandra Mendes (DEI).
About the Talk:
“As formal methods improve in expressiveness and power, they create new opportunities for non-expert adoption. In principle, formal tools are now powerful enough to enable developers to scalably validate realistic systems artifacts without extensive formal training. However, realizing this potential for adoption requires attention to not only the technical but also the human side—which has received extraordinarily little attention from formal-methods research.
This talk presents some of our efforts to address this paucity. We apply ideas from cognitive science, human-factors research, and education theory to improve the usability of formal methods. Along the way, we find misconceptions suffered by users, how technically appealing designs that experts may value may fail to help, and how our tools may even mislead users.”
About the Speaker:
Shriram Krishnamurthi is a Professor of Computer Science at Brown University. With collaborators and students, he has created several influential systems like DrRacket, Margrave, Flapjax, LambdaJS, Flowlog, and Pyret. He has also written multiple widely-used books. He also co-directs the Bootstrap integrated computing outreach program. For his work he has received SIGPLAN’s Robin Milner Young Researcher Award, SIGPLAN’s Software Award (jointly), SIGSOFT’s Influential Educator Award, SIGPLAN’s Distinguished Educator Award (jointly), and Brown’s Wriston and Philip J. Bray teaching awards. He has authored over twenty papers recognized for honors by program committees. He has an honorary doctorate from the Università della Svizzera Italiana.
The talk entitled “On the State of Client-Side Web Vulnerabilities: DOM-XSS and JavaScript Libraries” will be given on 24 July at 2:30 pm in room B006, moderated by Prof. Alexandra Mendes (DEI).
About the Talk:
“Client-side web vulnerabilities continue to pose significant security risks. In this talk, I will present two research efforts that provide a broader view of the modern web attack surface. First, I will introduce SWIPE, a system for large-scale detection of DOM-based cross-site scripting (DOM-XSS). SWIPE combines interaction-based fuzzing with dynamic symbolic execution (DSE) to systematically explore event-driven behaviors and automatically synthesize URL parameters and fragments. This enables the discovery of vulnerabilities that traditional static or non-interactive techniques miss, significantly improving detection coverage. Second, I will present LIBINSPECTORJS, an end-to-end pipeline for identifying vulnerable JavaScript libraries and assessing their exploitability in practice. Our initial results show that vulnerable libraries are widespread, but not all instances lead to exploitable conditions.”
About the Speaker:
Limin Jia is a Research Professor of Electrical and Computer Engineering Department at Carnegie Mellon University and a member of CyLab, Carnegie Mellon’s computer security and privacy institute. She received her Ph.D. from Princeton in 2008. Her research is in the intersection of programming languages, formal methods, and computer security. She is particularly interested in applying formal methods to analyzing the security guarantees of software systems and to developing mechanisms to make software systems more secure.
Three master’s graduates from the Department of Informatics Engineering (DEI) at the Faculty of Engineering of the University of Porto (FEUP) have been distinguished in the 2nd edition of the Master’s Awards of the Ordem dos Engenheiros – Região Norte (OERN), an initiative that recognises the academic excellence of the top Engineering master’s students from public higher education institutions in Northern Portugal.
The award ceremony took place on 2 July, bringing together students, academic representatives, partner companies and OERN board members. In this edition, 52 merit awards, each worth €1,000, were granted from a total of 88 applications covering several engineering disciplines.
Among the award recipients were Sofia Vieira Pinto and Pedro Madureira, from the Master in Informatics and Computing Engineering (M.EIC), and João Viterbo Vieira, from the Master in Data Science and Engineering (MECD), in recognition of the work developed in their master’s dissertations:
Specification-Driven Test Generation for Fault Localisation in Dafny – Sofia Vieira Pinto
Although formal verification provides mathematical proof that software is free from errors, fixing faults detected during the development of formally verified software remains a complex task that discourages many programmers. This project aims to support the debugging process by exploring fault localisation methodologies for the Dafny programming language. The work resulted in the development of DSpec2Test, a novel tool that automatically generates test cases from formal specifications describing the expected behaviour of a system. In addition, a plugin was created to map the exact execution path of each test within the source code. Based on this information, the research compares traditional fault localisation algorithms with an Artificial Intelligence model to determine which approach is more effective in identifying faulty lines of code. By simplifying fault localisation, this project seeks to reduce debugging effort and move towards a future where reliable software development becomes the norm rather than the exception. This work is part of the VeriFixer project (https://doi.org/10.54499/2023.15557.PEX). The dissertation was supervised by Prof. Alexandra Mendes (DEI).
Towards Open-Vocabulary 3D Object Detection for Autonomous Driving – Pedro Madureira
Developed in collaboration with Bosch Portugal, this dissertation proposes a new approach to improving the safety of autonomous vehicles by replacing traditional visual detection systems, which can only recognise predefined obstacles, with an open-vocabulary model for 3D object detection. Using LiDAR sensor data combined with natural language-based Artificial Intelligence, the proposed system is capable of identifying and locating previously unseen objects on the road through simple textual descriptions, without requiring additional training. Designed to handle the challenges and noise of complex outdoor environments, this technology has the potential to reduce development costs while providing a far more flexible, intelligent and reliable perception system for autonomous driving. The work was supervised by Prof. Luís Filipe Teixeira (DEI).
Human Guidance in Self-Evolving Multi-Agent AI Systems – João Viterbo Vieira
This dissertation explores a new generation of Artificial Intelligence systems composed of multiple agents capable of evolving and autonomously adapting their behaviour over time. The research investigates how human-in-the-loop approaches and steering techniques, through prompts, contextual information and reinforcement learning, can be used to guide such systems safely and effectively. Through a practical case study, the dissertation compares the performance and behaviour of AI agents under different levels of human intervention, contributing to the development of more robust, transparent and human-aligned Artificial Intelligence systems. The dissertation was supervised by Prof. António Pedro Aguiar (DEEC).
Recognising Academic Excellence
Created to recognise academic achievement, encourage advanced education and strengthen ties between higher education institutions and industry, the OERN Master’s Awards annually distinguish students who have completed their degrees with outstanding academic performance.
During the opening session, OERN President Bento Aires highlighted the importance of directing these awards towards master’s students, underlining the relevance of advanced qualifications for the engineering profession.
DEI congratulates the three award-winning graduates and their supervisors on this important distinction, which reflects the quality of the education and research developed within their master’s programmes.
More information and photographs from the ceremony are available in the OERN news article: https://www.oern.pt/noticias/oern-distingue-52-estudantes-na-2-a-edicao-dos-premios-de-mestrado/
Applications are now open for the 5th Edition of the Prof. Raul Vidal / Deloitte Award, with the application period running until 31 August 2026.
Students enrolled in the Master in Informatics and Computing Engineering and the Master in Software Engineering may submit their applications until the aforementioned date.
This award aims to annually distinguish a recent graduate from these study programmes who has demonstrated excellence through their academic achievements, the quality and innovation of work carried out in the field of Software Engineering, and participation in social and community-oriented initiatives, which constitute a distinctive criterion of this award.
The Award was established by Deloitte, with the support of the Faculty of Engineering of the University of Porto (FEUP), through the Department of Informatics Engineering (DEI), with the purpose of honouring Professor Emeritus Raul Vidal. This distinction recognises the Professor’s remarkable contribution to the development of education and research in the field of Computer Science, as well as his fundamental role in enhancing FEUP’s national and international reputation and in educating highly qualified professionals for the labour market.
All information regarding the application process, eligibility conditions and the award regulations can be found at: https://dei.fe.up.pt/pt/premio-prof-doutor-raul-vidal/
A faculty member and four students from the Department of Informatics Engineering (DEI) took part in the development of AMALIA, the latest and largest large language model specifically designed for the Portuguese language and culture, which was publicly unveiled on 1 July.
The DEI team comprised Sérgio Nunes, Associate Professor and researcher at INESC TEC; Luís Relvas and José Isidro, students in the Master’s in Informatics and Computing Engineering (M.EIC); Rodrigo Batista, a student in the Master’s in Artificial Intelligence (M.IA); and José Evans, a student in the Master’s in Data Engineering and Data Science (MECD). Their participation formed part of the University of Porto’s contribution to the Media domain, which brought together members from FCUP, FEUP, and FLUP, in collaboration with INESC TEC and the University of Beira Interior.
AMALIA is a language model built from the ground up for the Portuguese linguistic and cultural context. Developed over 18 months with an investment of €5.5 million, AMALIA differs from general-purpose assistants such as ChatGPT in that it was conceived as an open-source foundation model (available on Hugging Face and GitHub), intended to power specific applications built on proprietary datasets rather than to be used directly by the general public. As the model is publicly available and accompanied by a model card containing information on its characteristics and training data, the wider community will be able to benefit from and contribute to its future improvement.
The project supports Portugal’s vision and ambitions for Artificial Intelligence (AI) by directly addressing the following objectives:
Promotion of the Portuguese language,
Enabling national companies, the public administration and other organisations to express themselves correctly in European Portuguese.
To preserve Portugal’s cultural heritage,
by recording and preserving proverbs, idioms, cultural references and knowledge about national figures and monuments.
Sovereignty over citizens’ data,
Enabling the latest advances in AI to be applied to areas such as public administration, whilst ensuring that confidential data does not leave the country.
Promoção da investigação e inovação em IA,
Estimulando a criação de um ecossistema de I&D colaborativo com vários centros de investigação e contribuindo para avançar o conhecimento nacional na fronteira da IA.
Promoting research and innovation in AI,
encouraging the creation of a collaborative R&D ecosystem involving various research centres and helping to advance national knowledge at the cutting edge of AI.
AMALIA is expected to support a range of public administration applications. The gov.pt portal will be among its first use cases. Additional applications are planned in the fields of education, culture, museums, media, and science. While it would be technically feasible to develop a general-purpose chatbot based on the model, creating a competitor to commercially available conversational AI assistants is not one of the objectives of the AMALIA project.
Many questions may arise, but the good news is that they can all be answered on this page.
The talk entitled “Trustworthy AI Under Constraints: From Small Language Models to Adaptive Antibiotic Treatment” will be given on 14 July at 4:00 pm in room B001, moderated by Prof. Gil Gonçalves (DEI).
About the Talk:
“This talk presents two current research directions in trustworthy and efficient AI systems for sensitive domains. The first part focuses on small language models as a practical alternative to large language models in settings where cost, energy use, privacy, local deployment, and governance are important. I will present our recent work on privacy risks in chatbots built on small language models, showing that standard template-based evaluations can underestimate personally identifiable information leakage. Our results motivate a broader view of reliability, where prompts, role formatting, decoding choices, and deployment settings are treated as part of the AI system itself.
The second part introduces OptiRegi, a project that uses reinforcement learning to study optimized dynamic antibiotic dosing regimens. The goal is to explore how treatment decisions can adapt over time while balancing bacterial killing, toxicity, resistance development, and changing infection dynamics. Together, these two projects highlight a common theme: building AI systems that remain trustworthy under real-world constraints, from privacy and deployment challenges in small language models to safe and adaptive treatment optimization.”
About the Speaker:
Dr. Vi Ngoc-Nha Tran is an Associate Professor of Computer Science at UiT The Arctic University of Norway and a member of the steering group of NORA.startup, the innovation network of the Norwegian Artificial Intelligence Research Consortium. She holds a Ph.D. in Computer Science from UiT, was a visiting scholar at Rutgers University, USA, and received an Erasmus Mundus scholarship for a European M.Sc. in Software Engineering. Her research spans machine learning, health technology, high-performance computing, and energy-efficient computing. She currently leads two projects as principal investigator: a UiT-funded project on trustworthy small language models for regulated domains, and OptiRegi, a Research Council of Norway-funded project on optimized dynamic antibiotic dosing using reinforcement learning.
The Department of Informatics Engineering (DEI) at the Faculty of Engineering of the University of Porto (FEUP) will hold, on July 14, the 2026 edition of DEI Open Day, an annual event that brings together companies, institutions and the academic community to showcase the department’s teaching, research and innovation activities. This year’s meeting will focus on the theme “Transformation with Artificial Intelligence: Challenges and Paths for the Future“. Throughout the day, the organizers aim to launch a broad debate on the challenges posed by AI adoption in public and private organizations, seeking to identify paths toward sustainable digital transformation and the role that Informatics Engineering can play in that process.
Opening and international keynote
The program starts at 09:00 with the reception of participants, followed at 9:30 by the opening session, featuring remarks from Rui Calçada, Director of FEUP, and João Paiva Cardoso, Director of DEI. The opening talk will be delivered by Cátia S. Silva, Associate Professor at the University of Florida, under the title “From Models to AI Systems: AI Engineering for Digital Transformation“. The researcher will discuss the shift from a model-development-centered AI to an approach oriented toward AI systems engineering, addressing how recent advances in foundation models are expanding the skills required of AI engineers — from systems integration to data engineering, computing infrastructure, and human-system interaction. Cátia Silva coordinates master’s programs in AI Systems and Applied Data Science at the U.S. university and has received several awards for her teaching work, including the UF Undergraduate Teacher of the Year and the UF Rising Star Award, both in 2025.
Panel brings together industry, justice, and public administration
Between 10:30 and 12:00, a discussion papel dedicated to the event’s central theme will take place, moderated by Ana Paula Rocha, Vice-President of FEUP’s Pedagogical Council. Representatives from different sectors will gibe their contribute:
Diogo Pernes, Lead Research Scientist at OutSystems;
Nuno Fonseca, Board Member of IGFEJ – Instituto de Gestão Financeira e Equipamentos da Justiça (Portugal’s Institute for Financial Management and Justice Infrastructure);
Nuno Paiva, Head of Data Science, B2C & SME at NOS;
Rodrigo Passos, City Councillor at the Porto City Council;
Sofia Gomes, Director of Data Engineering at Feedzai.
The diversity of profiles, spanning corporate digital transformation, justice system modernization, innovation in public administration, and the implementation of data and AI solutions in a global context, is expected to fuel a discussion on the challenges and opportunities of AI adoption in both the public and private sectors.
Afternoon dedicated to ways of collaborating with DEI
After the event’s official photograph (12:15) and lunch, the afternoon is reserved for individual sessions on possible ways to collaborate with DEI, namely master’s dissertations across the department’s various master’s programs, the Integrative Project of the Bachelor’s in Informatics and Computing Engineering (L.EIC), the Project Management Laboratory (LGP), FEUP Prime and DoRPE, and opportunities related to the department’s student groups.
Through this initiative, DEI aims not only to present the current state of its scientific and pedagogical activity, but also to open the door to new partnerships with companies and institutions interested in collaborating on projects across various areas of informatics engineering.
DEI Talk by Vi Ngoc-Nha Tran – UiT- The Arctic University of Norway
Also as part of the Open Day, we will be hosting a lecture by Vi Ngoc-Nha Tran, Associate Professor at UiT – The Arctic University of Norway, on the topic: “Trustworthy AI Under Constraints: From Small Language Models to Adaptive Antibiotic Treatment”.
Full details of the lecture can be found here.
Abel Dantas, Invited Assistant Professor at the Department of Informatics Engineering (DEI) and a PhD candidate in the Doctoral Programme in Informatics Engineering (ProDEI), has been appointed by the European Commission’s AI Office to join the AI Act Advisory Forum, a group of experts that advises the European Commission and the European AI Board on the implementation of the European Union’s new Artificial Intelligence Regulation, the AI Act.
The AI Act is the world’s first comprehensive legislation on artificial intelligence and represents a major milestone in establishing common rules for the development, use, and oversight of AI systems within the European Union. The Advisory Forum brings together experts from academia, industry, and civil society to support the practical implementation of the legislation by providing technical expertise and multidisciplinary perspectives.
The Forum’s first meeting took place on 19 June 2026. According to information shared by Abel Dantas, the appointment is made in a personal capacity, as an individual expert, in connection with his involvement in Cooptech, a technology cooperative of which he is a founder. The selection process took into account both the expert’s background and standing, as well as the profile of the associated organization.
In Abel’s case, this background also includes FEUP, where he teaches in the Bachelor’s Degree in Informatics and Computing Engineering (L.EIC) and conducts research in the field of distributed systems. His appointment therefore represents recognition of the scientific and professional relevance of his work, while also strengthening FEUP’s presence in European forums dedicated to the regulation and governance of artificial intelligence.
Participation in the AI Act Advisory Forum may also create opportunities for knowledge sharing and for highlighting the contributions of FEUP and the University of Porto to the European debate on the ethical, technical, and regulatory challenges associated with artificial intelligence.
Candidate:
Jorge Federico Forero Rodríguez
Date, Time and Location:
8 July 2026, at 14:30, Sala de Atos of the Faculdade de Engenharia da Universidade do Porto
President of the Jury:
João Carlos Pascoal Faria (PhD), Full Professor of the Department of Informatics Engineering of the Faculdade de Engenharia da Universidade do Porto.
Members:
Nuno António do Nascimento Correia (PhD), Associate Professor at University of Tallinn, Estonia;
Hugo Gonçalo Oliveira (PhD), Associate Professor of the Department of Informatics Engineering, Faculdade de Ciências e Tecnologia da Universidade de Coimbra;
Nuno Manuel Robalo Correia (PhD), Full Professor of the Department of Informatics, Faculdade de Ciência e Tecnologia da Universidade Nova de Lisboa;
Mónica Sofia Santos Mendes (PhD), Assistant Professor with Habilitation, Faculdade de Belas-Artes da Universidade de Lisboa (Supervisor);
Tiago Barbedo Assis (PhD), Assistant Professor of the Department of Design, Faculdade de Belas-Artes da Universidade do Porto;
António Fernando Vasconcelos Cunha Castro Coelho (PhD), Associate Professor with Habilitation of the Department of Informatics Engineering, Faculdade de Engenharia da Universidade do Porto.
The thesis was co supervised by Gilberto Bernardes de Almeida, Assistant Professor of the Department of Informatics Engineering of the Faculdade de Engenharia da Universidade do Porto.
Abstract:
The Ironic Machine[s] is a practice-based research project that explores the use of a bimodal speech emotion recognition system for the generation of affective virtual environments and creative
computational artifacts. Situated at the intersection of media art, affective computing, and natural language processing, the study investigates how rhetorical figures such as kind irony and sarcasm emerge through the divergence between semantic and acoustic emotional predictions, and how this interaction can inform the construction of Affective Virtual Environments. The primary contribution of this thesis is the formulation and empirical evaluation of a method for analyzing illocutionary irony using multimodal speech emotion recognition datasets. Building on sentiment analysis and speech emotion recognition techniques, the research introduces a statistical inference framework that integrates perceptual evaluation with hypothesis-driven analysis to identify prosodic features that significantly differentiate sincere and ironic speech. For posed American English samples, the results demonstrate that divergences between semantic and acoustic emotional predictions can be systematically quantified, supporting the hypothesis that prosodic irony can be understood as a measurable multimodal phenomenon. A secondary objective investigates whether these findings can be translated into a generative strategy for constructing Affective Virtual Environments. To this end, a three-level prompt engineering framework is proposed, mapping semantic and acoustic emotional predictions onto audiovisual features informed by statistical analyses of musical and visual datasets. Perceptual evaluation indicates that feature-based prompting shows a consistent advantage over high-level emotional labels, although the results do not reach conventional levels of statistical significance. The investigation is realized through a series of nine technological and artistic iterations, developed as autonomous yet interconnected works. These projects function as experimental platforms for exploring emotional ambiguity, disorientation, and the instability of meaning in computational environments within a techno-poetic narrative. Collectively, this work proposes both a methodological framework for the analysis of irony and a speculative approach to affective environment generation. It positions divergence between modalities as an operational principle in multimodal systems and demonstrates how practice-based research can serve as a rigorous mode of inquiry into the relationship between human emotion and machine-mediated representation.
Keywords: Speech Emotion Recognition, Prosodic Irony, Affective Virtual Environments, Multimodal Analysis, Practice-based Research, Media Art.
Candidate:
Nádia de Sousa Varela de Carvalho
Date, Time and Location:
6 July 2026, at 14:30, Room Professor Vasco de Sá (L119) at DEMec, Faculdade de Engenharia da Universidade do Porto
President of the Jury:
António Fernando Vasconcelos Cunha Castro Coelho (PhD), Associate Professor with Habilitation, Department of Informatics Engineering, Faculdade de Engenharia da Universidade do Porto
Members:
Diemo Schwarz (PhD), Researcher of the Institute for Research and Coordination in Acoustics/Music (IRCAM), France;
Rui Luís Nogueira Penha (PhD), Coordinating Professor, Escola Superior de Música e Artes do Espetáculo do Instituto Politécnico do Porto;
Sofia Carmen Faria Maia Cavaco (PhD), Assistant Professor, Informatics Departament, Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa;
António Humberto Sá Pinto (PhD), Invited Assistant Professor, Departament of Informatics Engineering, Faculdade de Engenharia da Universidade do Porto and Affiliated Researcher at the Institute of Systems and Computer Engineering, Technology and Science (INESC TEC);
Gilberto Bernardes de Almeida (PhD), Assistant Professor, Department of Informatics Engineering, Faculdade de Engenharia da Universidade do Porto (Supervisor).
Abstract:
This thesis investigates the ontological and performative shift of the musical work. In this sense, we propose using intelligent computational mediation to reconfigure it from a static artefact into a mutable interface. Historically, the Western musical tradition has been framed by the work-concept (werktreue), which crystallizes the composition as an immutable object preserved by the rigidity of the score or the phonographic medium. However, contemporary digital and electroacoustic practices demand new paradigmas that account for the fluid boundaries between composition, performance, and technological agency. Acknowledging that, this research proposes a transition from the static score to the navigable topological manifold. Rather than utilizing fixed musical notation, these spaces treat the musical work as a dynamic environment. In this environment, identity is preserved through structural fluidity, leading to a paradigm change to a contextual navigation model. In a symbiotic dialogue of real-time structural discovery, the machine provides a restricted, high-dimensional map of the work’s universe, which the performer navigates using their gestural intuition.
The methodology follows a mixed approach between experimental and practice-based research. This methodology operates over a reflective-iterative cycle, integrating software development with musical performance. The study is divided into two main phases: symbolic (tonal) and sub-symbolic (timbre) representation and navigation. In the first phase, variational autoencoders (VAEs) are used to compress symbolic polyphony. A critical milestone was the empirical alignment found between unsupervised VAE latent spaces and theoretical Discrete Fourier Transform (DFT) phase spaces. This alignment confirms that black box latent space models naturally discover structural principles consistent with established music theory, such as the circle of fifths. The second phase employs Neural Audio Synthesis (RAVE) to map the timbre landscape of the tenor saxophone into high-dimensional latent spaces. To navigate these spaces, the research introduces a taxonomy of musical motions (parallel, oblique, and contrary). These motions propose to connect abstract data and musical intent, enabling gestural navigation that honours performer agency.
The practical applicability of this research is materialized in BroadcastJSB and Aethra. The former, a web-based topological instrument, uses a radio metaphor for real-time navigation within J.S. Bach’s chorales’ latent space. The latter consists of a co-creative interface for mixed music that synthesizes multidimensional complexity into a single axis of performative control. The primary contribution of this work lies in the formalization of the mutable work as a space of possibilities. We also demonstrate musical intelligibility within deep learning models and create open-access tools and data repositories for the computer music research and contemporary performance communities. In summary, the thesis argues that the future of musical practice lies in improving human intuition through intelligent mediation. By doing this, we position the mutable interface as a key place for collaboration and creative exploration in today’s digital world.