Posters

Josep Lopez (UOC) - Automated Detection of Visual Attribute Reliance with a Self-Reflective Agent (NeurIPS 2025) 

Josep Lopez (UOC) - OpenMAIA: a Multimodal Automated Interpretability Agent based on open-source models (NeurIPS workshops 2025)

Marius Miron (Earth Species Project ) - AI-assisted bioacoustics: from specialized models to multi-task cross-taxa LLMs (ICLR 2025) 

Pol Puigdemont (EPFL) - Ascent Fails to Forget (NeurIPS 2025) 

Guillem Capellera (IRI-UPC & Kognia Sports Intelligence) - Unified Uncertainty-Aware Diffusion for Multi-Agent Trajectory Modeling (CVPR 2025) 

Xavier Suau (Apple) - LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss (NeurIPS 2025) 

Alexandra Gomez-Villa (CVC - UAB) - Free-Lunch Appearance Control for Text-to-Image Models (NeurIPS 2025) 

Diego Porres (CVC) - Towards Kinetic Manipulation of the Latent Space (NeurIPS 2024 Creative AI Track) 

Míriam Barrabés (Stanford University) - Feature Shift Localization Network (ICML 2025) 

David Serrano-Lozano (CVC) - Revisiting Image Fusion Multi-Illuminant White-Balance Correction (ICCV 2025) 

Imanol G. Estepa (UB) - Conjuring Positive Pairs for Efficient Unification of Representation Learning and Image Synthesis (WACV 2026) 

Xavier Juanola (UPF) - Learning from Silence and Noise for Visual Sound Source Localization Models (The British Machine Vision Conference (BMVC 2025)) 

David Bonet (Stanford University) - Compressive Meta-Learning (KDD 2025) 

Ecesu Ürker (UPF) - NeLLCom-Lex: A Neural-agent Framework to Study the Interplay between Lexical Systems and Language Use (Findings of EMNLP 2025) 

Mykola Trokhymovych (UPF) - Graph-Linguistic Fusion: Using Language Models for Wikidata Vandalism Detection (ACL (Industry Track)) 

Mykola Trokhymovych (UPF) - Characterizing Knowledge Manipulation in a Russian Wikipedia Fork (ICWSM) 

Oriol Pareras (BSC) - Speech-to-Text Translation with Speech LLMs at BSC (Interspeech 2025) 

Gerard I. Gállego (BSC - UPC) - Single-stage TTS with Masked Audio Token Modeling and Semantic Knowledge Distillation (ICASSP 2025) 

Dr. Nabiz Rahpoe (BSC) - Deep Learn Emulator for Ocean Biogeochemical Model (CVPRW 2025)

Williams Contreras-Higuera (UOC) - Understanding the Dynamics of Facial Expressions with Wavelet Functions and Attention+LSTM (ACM Multimedia Workshop 2025) 

Ahmad AlMughrabi (UB) - FoodMem: Near real-time and precise food video segmentation (Pattern Recognition Letters) 

Ahmad AlMughrabi (UB) - VolTex: Food Volume Estimation using Text-Guided Segmentation and Neural Surface Reconstruction (CVPRW 2025) 

Ahmad AlMughrabi (UB) - OneVol: Single-Image Food Volume Estimation via Diffusion-Based 3D Reconstruction (CVPRW 2025) 

Laura De Grazia (UB) - MuSeD: A Multimodal Spanish Dataset for Sexism Detection in Social Media Videos (COLM 2025) 

Daniel Ponte (UB) - LLM-generated Semantic Co-occurrences for Multi-label Food Recognition (CAIP) 

Anna Oliveras Tous (Eurecat) - LAND: Lung and Nodule Diffusion for 3D Chest CT Synthesis with Anatomical Guidance (MedEurips)

Artemis Llabrés (CVC-UAB) - ComicsPAP: understanding comic strips by picking the correct panel (ICDAR 2025) 

Carlos Heredia (IAMM Research - DAMM S.A.) - Modeling AdaGrad, RMSProp, and Adam with Integro-Differential Equations (Journal of Machine Learning)

Alex Vicente (Center for Genomic Regulation) - From task-aware to task-agnostic parameter isolation for incremental learning (Neural Processing Letters) 

Sebastian Idesis - Angela Lopez Cardona (Telefónica Scientific Research - UPC) - OASST-ETC Dataset: Alignment Signals from Eye-tracking Analysis of LLM Responses (Proceedings of the ACM on Human-Computer (ETRA) Interaction) 

Artur Díaz Juan (UPF) - SoccerHigh: A Benchmark Dataset for Automatic Soccer Video Summarization (ACM Multimedia Workshops 2025) 

Gabriel Carneiro (University of Trás-Os-Montes and Alto Douro) - RRMAE: Redundancy-Reduced Masked Autoencoders for Fine-Grained Representation Learning (PhD project)

Maria del Mar Coch-Alcina (URL) - Comparative Evaluation of Single-View 3D Human Body Reconstruction Methods for Turner Syndrome Diagnosis (PhD topic)

Gemma Boleda (UPF / ICREA) - LLMs as a synthesis between discrete and continuous approaches to language (Findings of the ACL)

Oscar Mañas (Mila, Université de Montréal, Meta FAIR) - Controlling Multimodal LLMs via Reward-guided Decoding (ICCV 2025)

Lucas Ventura (École Des Ponts ParisTech | Inria) - Efficient Chaptering in Hour-Long Videos with LLMs (CVPR 2025)

Javier Vazquez-Corral (CVC-UAB) - The art of deception: Color visual illusions and diffusion models (CVPR 2025) 

Pol Caselles Rico (Crisalix SA) - GLVD: Guided Learned Vertex Descent (NeurIPS 2025) 

Joan Serrà (Sony AI) - Supervised contrastive learning from weakly-labeled audio segments for musical version matching (ICML 2025) 

Zhijin Chen (IRI - CSIC/UPC) - CLOT: Closed Look Optimal Transport for Unsupervised Action Segmentation (ICCV 2025)

Yiannis (Ioannis) Tsiamas (UPC) - Improving Language and Modality Transfer in Translation by Character-level Modeling (ACL 2025) 

Marco Del Tredici (Axiomatic_AI) - From Tools to Teammates: Evaluating LLMs in Multi-Session Coding Interactions (ACL 2025) 

Nora Graichen (UPF) - Not a nuisance but a useful heuristic: Outlier dimensions favor frequent tokens in language models (EMNLP 2025 Workshop) 

Sikha O K (UPF) - Uncertainty-aware segmentation quality prediction via deep learning Bayesian Modeling: Comprehensive evaluation and interpretation on skin cancer and liver segmentation (Computerized Medical Imaging and Graphics Journal) 

Ayan Banerjee (CVC) - CraftSVG: Multi-Object Text-to-SVG Synthesis via Layout Guided Diffusion (WACV 2026) 

Changhui Hu (UB) - Dual Polarity Prompts with Stochastic Entropy Perturbation for Label Noise (BMVC 2025) 

Javier Ródenas (UB) - Slot Attention-based Feature Filtering for Few-Shot Learning (CVPR Workshops) 

Javier Ródenas (UB) - Stochastic-based Patch Filtering for Few-Shot Learning (CVPR Workshops) 

Javier Ródenas (UB) - Quartet of Experts: Multi-Aspect Semantic Guidance for Few-Shot Learning 

Marc Serra Ortega (CVC) - CoSMo: A Multimodal Transformer for Page Stream Segmentation in Comic Books (ICCV 2025 Workshop) 

Ioannis Arapakis (Telefónica Scientific Research) - Large Language Model driven Policy Exploration for Recommender Systems (WSDM 2025) 

Meritxell Riera i Marín (Sycai Medical - UPF) - Multi-Rater Calibration Error Estimation (MICCAI 2025 Workshop) 

Ismael Benito-Altamirano (UOC) - When and How to Cut Classical Concerts? A Multimodal Automated Video Editing Approach (ACM Multimedia 2025 Workshop) 

Marc Balle Sanchez (UPF) - HyperSORT: Self-Organising Robust Training with hyper-networks (MICCAI 2025) 

Amirpasha Mozaffari (BSC) - Historical Reconstruction and Future Projection of Land Surface Boundary Conditions (NeurIPS 2025 Workshop) 

Mario Sänger (AstraZeneca) - Knowledge-augmented pre-trained language models for biomedical relation extraction (BMC Bioinformatics) 

Jose Giraldo (BSC) - Evaluating Speech Enhancement Performance Across Demographics and Languages (Interspeech) 

Eric López (CVC) - Enhancing Document VQA Models via Retrieval-Augmented Generation (ICDAR 2025 Workshop) 

Rahul Methari (UPF) - 3D Reconstruction of the Left Atrial Geometry from 2D Echocardiographic Images Using Deep Learning (Functional Imaging and Modeling of the Heart (FIMH-2025)) 

Xavi Font Aragones (Tecnocampus Mataró-Maresme (UPF)) - Wavelet Vision Transformers and Quantum Pyramidal Networks for Biomedical Image Analysis (9th International Conference on Quantum Techniques in Machine Learning) 

Alex Ferrando de las Morenas (UAB) - Dynamically Scaled Activation Steering 

Umair Haroon (UB) - VolE: A Point-cloud Framework for Food 3D Reconstruction and Volume Estimation (Under Review) 

Paula Rivera Hidalgo de Torralba (BSC) - Psycholinguistic Probing of Language Models' Internal Layers (UPF e-Repositori) 

Sergio Rodriguez Llana (FRCB - IDIBAPS) - Leveraging General-purpose Models for Enhancing Automatic Head and Neck Tumor Segmentation (PhD topic)

Caterina Fuses (UB) - Deconvolving CAG Somatic Expansion Transcriptomic Signatures in Huntington's Disease (Not published) 

Guillem Brasó (NVIDIA) - Native Segmentation Vision Transformers (NeurIPS 2025) 

Danna Xue (CVC - UAB) - HyperNVD: Accelerating Neural Video Decomposition via Hypernetworks (CVPR 2025) 

Ángela López Cardona (Telefonica Innovación Digital - UPC) - Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models (ICLR 2025) 

Angela López-Cardona, Mireia Masias (Telefonica Scientific Research) - Brain–Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantage (UniReps NeurIPS) 

Juan Rodriguez (Mila, "Stealth" Lab) - StarVector: Generating Scalable Vector Graphics Code using LLMs (CVPR 2025) 

Valentino Maiorca (Sapienza University of Rome) - Head Pursuit: Probing Attention Specialization in Multimodal Transformers (NeurIPS 2025)

Álvaro Parafita (BSC) - Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference (NeurIPS 2025)

Alexandru (Alex) Oarga (UB) - Generalizable Reasoning through Compositional Energy Minimization (NeurIPS 2025) 

Elias Abad Rocamora (EPFL) - Robustness in Both Domains: CLIP Needs a Robust Text Encoder (NeurIPS 2025) 

Josuan Eguiluz (BSC - Adevinta) - Position Paper: If Innovation in AI Systematically Violates Fundamental Rights, Is It Innovation at All? (NeurIPS 2025)

David Pujol Perich (UB) - Sparse-Dense Side-Tuner for efficient Video Temporal Grounding (ICCV 2025) 

Pol Pastells (UB) - SCRIBAL: A Digital Transcription Tool for Accessibility (Interspeech 2025) 

Eleonora Mancini (University of Bologna) - LMAC-TD: Producing Time Domain Explanations for Audio Classifiers (ICASSP 2025) 

Jesús M. Rodríguez-de-Vera (UB) - Precision at scale: Domain-specific datasets on-demand (Pattern Recognition) 

Matéo Mahaut (UPF) - Universals in heterogeneous communities of pre-trained visual deep networks (TMLR 2025) 

Vitor Jeronymo & Mario Sänger (AstraZeneca) - Self-calibration for Language Model Quantization and Pruning (NAACL 2025) 

Xinyue Ma (UB) - Semantic Prosody in Machine Translation: the English-Chinese Case of Passive Structures (Joint Conference on Lexical and Computational Semantics) 

Abir Messaoudi (BSC) - Optimizing ASR for Catalan-Spanish Code-Switching: A Comparative Analysis of Methodologies (Interspeech 2025) 

Marc Molina Van den Bosch (UPF - CERN) - The Interplay Between Explainability and Differential Privacy in Federated Healthcare (MICCAI) 

Álvaro Heredia-Lidón (URL) - BioFace3D: An end-to-end open-source software for automated extraction of potential 3D facial biomarkers from MRI scans (Computer Methods and Programs in Biomedicine) 

Gerard Comas-Quiles (UPC) - Towards Label-Free Brain Tumor Segmentation: Unsupervised Learning with Multimodal MRI (MICCAI Workshop) 

Raquel González López (BCN-MedTech, UPF) - Automatic Quality Assurance and Subcortical Brain Segmentation in Pediatric Ultra-Low-Field MRI: Exploring Ordinal Learning and Foundation Model Adaptation (MICCAI 2025 Workshop) 

Daniel Arteaga (Dolby Laboratories) - Room Impulse Response Generation Conditioned on Acoustic Parameters (EEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA 2025)) 

Gerard Asbert (CVC) - GAN-based Content-Conditioned Generation of Handwritten Musical Symbols (ICDAR workshop) 

Alex Batlle Casellas (Qualcomm AI Research (Barcelona Labs)) - Training LLM Models at Scale Using RDMA Over Converged Ethernet (RoCE) (IEEE/ACM Supercomputing SC 2025) 

Georgios Koutroumpas (Telefonica Research - UPC) - Beyond Clicks: Eye-Tracking Insights into User Responses to Different Recommendation Types (19th ACM Conference on Recommender Systems) 

Georgios Koutroumpas (Telefonica Research - UPC) - Beyond One-Size-Fits-All: A Study of Neural and Behavioural Variability Across Different Recommendation Categories (International Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR 2025)) 

Xavier Giró-i-Nieto (Amazon) - Cost Savings from Automatic Quality Assessment of Generated Images 

Aleix Torres-Camps (Qualcomm AI Research (Barcelona Labs)) - M3Kang: Evaluating Multilingual Multimodal Mathematical Reasoning in Vision-Language Models 

Filippo Stocco (Centre for Genomic Regulation) - Guiding Generative Protein Language Models with Reinforcement Learning (Under review Nature Methods) 

Berta Ros Blanco (UB) - Non-linear Representation Learning of Neuronal Population Dynamics 

Francesco Aldo Venturelli (UPF) - Quantum Generative Diffusion Models for Medical Imaging