#LASIGE
⏱️ Robôs de Telepresença: inclusão e autonomia!

O projeto ShiftHRI, apresentado por Tiago Guerreiro (LASIGE), usa robôs de telepresença para permitir que pessoas acamadas ou com mobilidade reduzida visitem museus, espaços ao ar livre e familiares à distância.

🔗 Ouça: t.ly/sisJY
November 14, 2026 at 10:00 AM
4/4 We finished the trip with a visit to the Tech & People Lab at the University of Lisbon. A lovely way to round off the week!

techandpeople.github.io
Tech & People Lab - Home
Tech & People Lab at LASIGE, FCUL
techandpeople.github.io
November 2, 2026 at 6:16 PM
New preprint! 🚀

How well do the internal representations of VLMs organize visual information for #unsupervised #imageclustering?

We explore this over 252 configurations, with some interesting results!

arxiv.org/abs/2610.33265

#VLM #visionlanguagemodels #INESCINOV #ULusófona #FCUL #LASIGE
Image Clustering with Vision-Language Model Embeddings
Pretrained vision-language models provide image representations whose suitability for clustering may vary with feature extraction, image domain, and partitioning algorithm. We compare nine representat...
arxiv.org
October 27, 2026 at 5:13 PM
Olá Lisbon! I'm here for the FLOC mega-fest, and starting things off with a talk on neuro-symbolic AI on July 22 at the Faculty of Sciences of the University of Lisbon.

Thanks to Catia for the invitation, looking forward to it!

lasige.pt/talk/lasige-... --
Olá Lisbon! I'm here for the FLOC mega-fest, and starting things off with a talk on neuro-symbolic AI on July 22 at the Faculty of Sciences of the University of Lisbon. Thanks to Catia for the… | Vaishak Belle
Olá Lisbon! I'm here for the FLOC mega-fest, and starting things off with a talk on neuro-symbolic AI on July 22 at the Faculty of Sciences of the University of Lisbon. Thanks to Catia for the invitation,...
www.linkedin.com
July 21, 2026 at 5:06 PM
📢 #BSCSeminar: Neurosymbolic #AI for explainable scientific discovery

🗣 @catiapesquita.bsky.social, University of Lisbon, LASIGE
📆2 October

➡ www.bsc.es/4ZQ

#EquityinBSC #WomeninBSC @sommalliance.bsky.social
September 29, 2025 at 8:44 AM
#Tutorial T7: Data-Centric AI: Addressing Missing Data Imputation in Image and Tabular Contexts
By 👥: Joana Cristo Santos, LASIGE; Ricardo Cardoso Pereira, CISUC; Pedro Henriques Abreu, CISUC
🔗https://2026.ijcai.org/accepted-tutorials/
#IJCAI2026 #ECAI2026
July 22, 2026 at 2:05 PM
Bernardo Almeida (LASIGE, Faculty of Sciences, University of Lisbon, Portugal), Andreia Mordido (LASIGE, Faculty of Sciences, University of Lisbon, Portugal), Vasco T. Vasconcelos (LASIGE, ...
Local Type Inference for Context-Free Session Types
https://arxiv.org/abs/2505.20855
May 28, 2025 at 4:37 AM
Ulbmilin birget bures gielddaválggain! Dál Anára Ruonáin leat jo 8 evttohasa, muhto lasige čáhket listui 💚 Giitu Lappi Ruonáid doaimmajođiheaddji Ella galledeamis Anáris ja giitu buohkaide hui buorre ságastallamis boahttevaš válgatemáin! #gielddaválggat #anár
January 25, 2025 at 9:09 AM
Today, Talks @ LASIGE !

When you want an ethical mechanism , but the only way to make it really work is to make it aggressive and intrusive…!
April 29, 2026 at 6:58 AM
Thank you @manlius.bsky.social for having me in Padova and for everybody attending and all the exciting questions!
Thank you LASIGE for having me again, it was a blast being back and seeing so many familiar faces! The questions were also sharp and super timely.
Super grateful 🙌🏼
September 24, 2025 at 6:16 AM
For those in Portugal, I’ll be giving a talk next Thursday at LASIGE, Informática em Ciências , Faculdade de Ciências da Universidade de Lisboa

Looking forward to seeing colleagues and previous students!

lasige.pt/talk/lasige-...
Talks @ LASIGE: Andreia Sofia Teixeira - LASIGE
Title: Towards Predictive Social Network Science: Polarisation & Equilibrium in Signed Networks Speakers: Andreia Sofia Teixeira (Network Science Institute, NUL, LASIGE) Date: September 18, 2025, 14h0...
lasige.pt
September 13, 2025 at 9:21 AM
Tiago Guerreiro, professor na Faculdade de Ciências da Universidade de Lisboa e diretor do LASIGE, escreve no Expresso sobre como a discussão em torno da Inteligência Artificial vai muito além da tecnologia.
February 10, 2026 at 12:56 PM
💡 “A realidade virtual vai muito além da visão”.

João Guerreiro, professor de CIÊNCIAS e investigador no LASIGE, lidera, juntamente com outros seis cientistas deste centro, o desenvolvimento de um projeto dedicado a tornar a realidade virtual mais acessível usando um cenário complexo: o do boxe.
January 6, 2026 at 4:39 PM
Tiago Guerreiro, professor de CIÊNCIAS e vice-diretor do LASIGE, foi distinguido como ACM Distinguished Member 2025, um dos mais prestigiados reconhecimentos internacionais em computação.

🔗Leia mais: tinyurl.com/2u7x7xbu
December 26, 2025 at 6:46 PM
👉Já David Gonçalves, estudante de doutoramento, e João Guerreiro, professor de CIÊNCIAS, no LASIGE, participaram no dia 23 com duas talks dedicadas à acessibilidade dos jogos para pessoas cegas.
🔗Programa completo e inscrições: t.ly/_Hmsz
Game on! A ULisboa marca presença na Lisboa Games Week 2025
De 20 a 23 de novembro, na FIL, mostramos como ciência, arte e tecnologia se cruzam para criar novas experiências de gaming e de entretenimento.
t.ly
November 19, 2025 at 6:10 PM
👉André Rodrigues, investigador de CIÊNCIAS no LASIGE, participará na iniciativa como orador com a Talk “Estruturas de Jogos Cooperativos” onde abordará as estratégias de design que moldam a comunicação e as estruturas de jogos cooperativos.
November 19, 2025 at 6:10 PM
💡 Catia Pesquita, coordenadora do Mestrado em Ciência de Dados de Ciências ULisboa e especialista em Inteligência Artificial no LASIGE, partilhou com a Radio France Internationale (RFI) a sua visão sobre o Atlas, o navegador lançado pela criadora do ChatGPT.

📡 Leia aqui: t.ly/1g0kg
October 28, 2025 at 4:30 PM
Tiago Guerreiro, professor de CIÊNCIAS e investigador no LASIGE, distinguido com o Scientific Merit Award 2024, será orador convidado das flash-talks "Leading-Edge Research @ CIÊNCIAS” do Research & Innovation Day.

👉Talk: “Designing Technology for What People Value”.
🔗https://t.ly/fYoSw
October 17, 2025 at 5:06 PM
💡Corrida da Europa à IA não é velocidade, mas inteligência.
👉"Se a Europa quiser estar na linha da frente, não bastará correr mais rápido; será necessário correr de forma mais inteligente".
🔗Leia a opinião de Catia Pesquita, professora de CIÊNCIAS e investigadora no LASIGE ➡ t.ly/ZP7eq
September 15, 2025 at 2:31 PM
💡 CIÊNCIAS recebeu ontem Meredith Morris, diretora de Investigação em Interação Humano-IA da Google DeepMind, numa palestra organizada pelo LASIGE.
July 16, 2025 at 2:26 PM
GPT-4.1 sets a new benchmark: reliably generating Python code for tough experiments with little-known libraries, while revealing gaps in docs. 📄

#AI #Python #Research #GPT41 @ULusofona @UNINOVA @lasige #codegeneration #codequality #LLMs

www.mdpi.com/1999-5903/17...
www.mdpi.com
September 15, 2025 at 5:05 PM
A simple question about our robot’s cleanup turned into a deep dive… and the definition of a new discrete statistical distribution 🤓🗑️➡️📊

Not world-changing, but definitely a fun journey with great colleagues!

👌U. Lusófona CTS/UNINOVA, FCUL, LASIGE, FCT

www.sciencedirect.com/science/arti...
August 25, 2025 at 11:45 AM
New preprint: Can #LLMs run computational experiments?

✅ #GPT41 nailed it
⚖️ #Grok3 & #Mistral did well
❌ Smaller local models couldn't keep up

Tks: @ULusofona, @UNINOVA, FCUL, @lasige, @fct_pt, ILIND

arxiv.org/abs/2508.00033
GPT-4.1 Sets the Standard in Automated Experiment Design Using Novel Python Libraries
Large Language Models (LLMs) have advanced rapidly as tools for automating code generation in scientific research, yet their ability to interpret and use unfamiliar Python APIs for complex computation...
arxiv.org
August 4, 2025 at 10:56 AM
New paper out! It's an overview of deep learning methods for 2D semantic segmentation with benchmarks, datasets, metrics, and insights into future directions.
Acks ➡️ Lusófona University, FCT, CTS/UNINOVA, LASIGE/FCUL
#semanticsegmentation #deeplearning #2dsegmentation
www.mdpi.com/2673-4117/6/...
www.mdpi.com
July 18, 2025 at 2:27 PM
📝 New paper by our PhD student Afonso Oliveira in #DoCEIS25: "Detection and Characterization of PlumeDominated Wildfires" 🔥

Thanks for the support: U. Lusófona, Fundação para a Ciência e a Tecnologia, CTS/UNINOVA, LASIGE/FCUL!

#wildfires #plumefires #fireplumes

link.springer.com/chapter/10.1...
Detection and Characterization of Plume-Dominated Wildfires
Extreme wildfires are increasingly hazardous, particularly plume-dominated fires, which exhibit unpredictable behavior due to their self-sustaining convective columns. Despite their significance, thes...
link.springer.com
July 18, 2025 at 8:40 AM