Research engineer part-time position

Reference: 20260721_DAG  About CVC:  The Computer Vision Center (CVC) is a non-profit research center established in 1995 by the Generalitat de Catalunya and the Universitat Autònoma de Barcelona (UAB). Its mission is to carry out cutting-edge research that has the highest international impact in the field of computer vision. It also promotes the transference of knowledge to industry and society.   Computer vision is … Read more

POSTDOC POSITION IN MULTIMODAL FOUNDATION MODELS FOR DOCUMENT UNDERSTANDING 

Call reference: 20260713_VL  Closing date: 19/07/2026  We are seeking a postdoc to join the Vision, Language and Reading group at the Computer Vision Center (CVC), in Barcelona, Spain.  The position is initially for 6 months and linked to the project “Multimodal LLMs for Document Undestanding” (MuDocU), funded by the Ministry of Science, Innovation and Universities. The project targets the development of open Multimodal Models for Document Understanding (DU) pushing research forward to deal with large-scale input and explainability, security and privacy of models. .  PROJECT PI & HOSTING GROUP  The direct responsible for this post will Dr Dimosthenis … Read more

Cruïlla Festival Becomes a Citizen Innovation Space to Explore Artificial Intelligence and Digital Identity

From 8 to 11 July, the Cruïlla Festival will become a unique space for exploring the role that artificial intelligence can play in music and the arts within an open science and innovation framework. Researchers, public administrations, and companies from the innovation ecosystem are joining forces in this initiative to test emerging technologies in a … Read more

International experts gather in Barcelona to discuss the latest advances in multimodal AI foundation models

Multimodal Foundation Models represent one of the most advanced research frontiers in artificial intelligence. These technologies can learn from vast amounts of heterogeneous data —including text, images, audio, video, and sensor data— enabling them to integrate and relate information from multiple sources to create systems that are more flexible, robust and closer to how humans … Read more

WORKSHOP | Multimodal Foundation Models: from Research to Innovation

On 1 July 2026, the European AI research community will gather in Barcelona for the Workshop on Multimodal Foundation Models: From Research to Innovation. This half-day workshop will explore the latest advances in multimodal artificial intelligence, with a focus on how cutting-edge research can be translated into real-world innovation. Bringing together leading researchers, industry representatives … Read more

Anunci d’una posició de Tècnic/a de Comunicació i Màrqueting per a la Xarxa RDI-IA del Centre de Visió per Computador

Data obertura: 26/06/2026  Ref: 20260626_XARXA  Tècnic/a de comunicació i màrqueting  La Xarxa d’RDI en Intel·ligència Artificial es va articular a finals de l’any 2022 gràcies al finançament de l’AGAUR (Generalitat de Catalunya) i representarà el sector de la Innovació en Intel·ligència Artificial (IA) a Catalunya, amb ànim de consolidar l’ecosistema català d’IA i posicionar el territori com … Read more

PREDOC POSITION IN MULTIMODAL FOUNDATION MODELS FOR DOCUMENT UNDERSTANDING

Call reference: 20260619_MDU  Closing date: 28/06/2026  We are seeking a predoc to join the Vision, Language and Reading group at the Computer Vision Center (CVC), in Barcelona, Spain.  * The category will be changed to postdoctoral researcher once the thesis has been defended. The position is initially for 1 year and linked to the project “Multimodal LLMs for Document Undestanding” (MuDocU), financed by the Spanish Ministry of Science.   Proyecto PID2023-146426NB-100 financiado por MICIU/AEI /10.13039/501100011033 … Read more

Material selection in 2D and beyond – methods, tricks and applications

Abstract: In this talk, we’ll explore image understanding from a material-centric perspective, namely through the lens of material appearance. Materials distinguish themselves by their response to light, which is governed and modelled through physical properties like roughness or gloss – however, understanding such properties is a non-trivial task for current models and network architectures. We’ll … Read more