Grounding Computer Use Agents on Human Demonstrations
International Conference on Learning Representations (ICLR), 2026
Publications
Google Scholar141 publications
2026
Conference Article
StarFlow: Generating Structured Workflow Outputs from Sketch Images
Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2026
Apriel-1.5-OpenReasoner: RL Post-Training for General-Purpose and Efficient Reasoning
arXiv preprint arXiv:2604.02007, 2026
VectorGym: A Multitask Benchmark for SVG Code Generation, Sketching, and Editing
arXiv preprint arXiv:2603.29852, 2026
WildSVG: Towards Reliable SVG Generation Under Real-Word Conditions
arXiv preprint arXiv:2602.21416, 2026
2025
AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding
Advances in Neural Information Processing Systems (NeurIPS), 2025
BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning
Conference on Language Modeling (COLM), 2025
BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks
International Conference on Learning Representations (ICLR), 2025
Rendering-Aware Reinforcement Learning for Vector Graphics Generation
Advances in Neural Information Processing Systems (NeurIPS), 2025
StarVector: Generating Scalable Vector Graphics Code from Images and Text
Computer Vision and Pattern Recognition (CVPR), 2025
UI-Vision: A Desktop-Centric GUI Benchmark for Visual Perception and Interaction
International Conference on Machine Learning (ICML), 2025
WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025
AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery
Workshop at Association for Computational Linguistics (ACL), 2025
AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding
ICLR Workshops 2025, 2025
Preprint Article
Patent2024
CADet: Fully Self-Supervised Out-of-Distribution Detection with Contrastive Learning
Advances in Neural Information Processing Systems (NeurIPS), 2024
GEO-Bench: Toward Foundation Models for Earth Monitoring
Advances in Neural Information Processing Systems (NeurIPS), 2024
Group Robust Classification without Any Group Information
Advances in Neural Information Processing Systems (NeurIPS), 2024
InsightBench: Evaluating Business Analytics Agents through Multi-Step Insight Generation
International Conference on Learning Representations (ICLR), 2024
RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content
Advances in Neural Information Processing Systems (NeurIPS), 2024
WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?
International Conference on Machine Learning (ICML), 2024
XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference
Advances in Neural Information Processing Systems (NeurIPS), 2024
Towards Good Validation Metrics for Generative Models in Offline Model-Based Optimisation
Transactions on Machine Learning Research (TMLR), 2024
A Multimodal Class-Incremental Learning Benchmark for Classification Tasks
Workshop at Advances in Neural Information Processing Systems (NeurIPS), 2024
Patent2023
Constraining Representations Yields Models That Know What They Don't Know
International Conference on Learning Representations (ICLR), 2023
Expecting the Unexpected: Towards Broad Out-of-Distribution Detection
Advances in Neural Information Processing Systems (NeurIPS), 2023
FigGen: Text to Scientific Figure Generation
International Conference on Learning Representations (ICLR), 2023
Flaky Performances When Pretraining on Relational Databases
Conference on Artificial Intelligence (AAAI), 2023
Improving Generalization in Task-Oriented Dialogues with Workflows and Action Plans
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023
OCR-VQGAN: Taming Text-within-Image Generation
Winter Conference on Applications of Computer Vision (WACV), 2023
TK-KNN: A Balanced Distance-Based Pseudo Labeling Approach for Semi-Supervised Intent Classification
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023
Knowledge Hypergraph Embedding Meets Relational Algebra
Journal of Machine Learning Research (JMLR), 2023
Capture the Flag: Uncovering Data Insights with Large Language Models
Workshop at Advances in Neural Information Processing Systems (NeurIPS), 2023
IntentGPT: Few-Shot Intent Discovery with Large Language Models
Workshop at International Conference on Learning Representations (ICLR), 2023
Leveraging Human Preferences to Master Poetry
Workshop at Conference on Artificial Intelligence (AAAI), 2023
Multilingual Code Retrieval without Paired Data: New Datasets and Benchmarks
Workshop at International Conference on Learning Representations (ICLR), 2023
OC-NMN: Object-Centric Compositional Neural Module Network for Generative Visual Analogical Reasoning
Workshop at International Conference on Machine Learning (ICML), 2023
The Unsolved Challenges of LLMs as Generalist Web Agents: A Case Study
Workshop at Advances in Neural Information Processing Systems (NeurIPS), 2023
Automatic Data Augmentation Learning using Bilevel Optimization for Histopathological Images
arXiv preprint arXiv:2307.11808, 2023
Language Decision Transformers with Exponential Tilt for Interactive Text Environments
arXiv preprint arXiv:2302.05507, 2023
Patent2022
Multi-Label Iterated Learning for Image Classification with Label Ambiguity
Computer Vision and Pattern Recognition (CVPR), 2022
Sequoia: A Software Framework to Unify Continual Learning Research
Conference on Lifelong Learning Agents (CoLLAs), 2022
Conference Article
A Survey of Self-Supervised and Few-Shot Object Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022
CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions
Artificial Intelligence Journal (AIJ), 2022
Exploring Validation Metrics for Offline Model-Based Optimisation with Diffusion Models
Transactions on Machine Learning Research (TMLR), 2022
Workflow Discovery from Dialogues in the Low Data Regime
Transactions on Machine Learning Research (TMLR), 2022
A Probabilistic Perspective on Reinforcement Learning via Supervised Learning
Workshop at International Conference on Learning Representations (ICLR), 2022
Constraining Low-Level Representations to Define Effective Confidence Scores
Workshop at Advances in Neural Information Processing Systems (NeurIPS), 2022
Contrastive Self-Supervision Defines General-Purpose Similarity Functions
Workshop at Advances in Neural Information Processing Systems (NeurIPS), 2022
Data Augmentation for Intent Classification with Off-the-Shelf Large Language Models
Workshop at Association for Computational Linguistics (ACL), 2022
Flaky Performances When Pretraining on Relational Databases
Workshop at International Conference on Machine Learning (ICML), 2022
Implicit Offline Reinforcement Learning via Supervised Learning
Workshop at Advances in Neural Information Processing Systems (NeurIPS), 2022
OCIM: Object-Centric Compositional Imagination for Visual Abstract Reasoning
Workshop at International Conference on Learning Representations (ICLR), 2022
Overcoming Challenges in Leveraging GANs for Few-Shot Data Augmentation
Workshop at Conference on Lifelong Learning Agents (CoLLAs), 2022
3rd Continual Learning Workshop Challenge on Egocentric Category and Instance Level Object Understanding
arXiv preprint arXiv:2212.06833, 2022
2021
A Weakly Supervised Consistency-Based Learning Method for COVID-19 Segmentation in CT Images
Winter Conference on Applications of Computer Vision (WACV), 2021
Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations
International Conference on Computer Vision (ICCV), 2021
Learning Data Augmentation with Online Bilevel Optimization for Image Classification
Winter Conference on Applications of Computer Vision (WACV), 2021
Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data
International Conference on Computer Vision (ICCV), 2021
3D Perception with Slanted Stixels on GPU
IEEE Transactions on Parallel and Distributed Systems (TPDS), 2021
A Deep Learning Localization Method for Measuring Abdominal Muscle Dimensions in Ultrasound Images
IEEE Journal of Biomedical and Health Informatics (JBHI), 2021
Weakly Supervised Underwater Fish Segmentation using Affinity LCFCN
Nature Scientific Reports, 2021
SSR: Semi-Supervised Soft Rasterizer for Single-View 2D to 3D Reconstruction
Workshop at International Conference on Computer Vision (ICCV), 2021
Toward Foundation Models for Earth Monitoring: Proposal for a Climate Change Benchmark
Workshop at Advances in Neural Information Processing Systems (NeurIPS), 2021
Decoupling Anomaly Discrimination and Representation Learning: Self-Supervised Learning for Anomaly Detection on Attributed Graph
arXiv preprint arXiv:2304.05176, 2021
2020
Instance Segmentation with Point Supervision
International Conference on Pattern Recognition (ICPR), 2020
LOOC: Localize Overlapping Objects with Count Supervision
International Conference on Image Processing (ICIP), 2020
Online Fast Adaptation and Knowledge Accumulation: A New Approach to Continual Learning
Advances in Neural Information Processing Systems (NeurIPS), 2020
Online Fast Adaptation and Knowledge Accumulation: A New Approach to Continual Learning
Advances in Neural Information Processing Systems (NeurIPS), 2020
Proposal-Based Instance Segmentation with Point Supervision
International Conference on Image Processing (ICIP), 2020
Synbols: Probing Learning Algorithms with Synthetic Datasets
Advances in Neural Information Processing Systems (NeurIPS), 2020
A Realistic Fish-Habitat Dataset to Evaluate Algorithms for Underwater Visual Analysis
Nature Scientific Reports, 2020
Affinity LCFCN: Learning to Segment Fish with Weak Supervision
Nature Scientific Reports, 2020
Generating Virtual Images for Promoting Visual Artificial Intelligence
Neurocomputing, 2020
Pix2Shape: Towards Unsupervised Learning of 3D Scenes from Images Using a View-Based Representation
International Journal of Computer Vision (IJCV), 2020
Counting Cows: Tracking Illegal Cattle Ranching from High-Resolution Satellite Imagery
Workshop at Advances in Neural Information Processing Systems (NeurIPS), 2020
A Weakly Supervised Region-Based Active Learning Method for COVID-19 Segmentation in CT Images
arXiv preprint arXiv:2007.07012, 2020
Patent2019
Context-Aware Visual Compatibility Prediction
Computer Vision and Pattern Recognition (CVPR), 2019
Knowledge Hypergraphs: Prediction Beyond Binary Relations
International Joint Conferences on Artificial Intelligence (IJCAI), 2019
Where Are the Masks: Instance Segmentation with Image-Level Supervision
British Machine Vision Conference (BMVC), 2019
Slanted Stixels: A Way to Represent Steep Streets
International Journal of Computer Vision (IJCV), 2019
Adversarial Learning of General Transformations for Data Augmentation
Workshop at International Conference on Learning Representations (ICLR), 2019
Class-Based Styling: Real-Time Localized Style Transfer with Semantic Segmentation
Workshop at International Conference on Computer Vision (ICCV), 2019
Fourier-CPPNs for Image Synthesis
Workshop at International Conference on Computer Vision (ICCV), 2019
2018
Environmental Perception for Intelligent Vehicles
Intelligent Vehicles Symposium (IV), 2018
Learning to Remove Rain in Traffic Surveillance by using Synthetic Data
International Conference on Computer Vision Theory and Applications (VISIGRAPP), 2018
Where Are the Blobs: Counting by Localization with Point Supervision
European Conference on Computer Vision (ECCV), 2018
Data for Training Models, Domain Adaptation
Intelligent Vehicles: Enabling Technologies and Future Developments, Elsevier, 2018
2017
GPU-Accelerated Real-Time Stixel Computation
Winter Conference on Applications of Computer Vision (WACV), 2017
Slanted Stixels: Representing San Francisco's steepest streets
British Machine Vision Conference (BMVC), 2017
A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images
Journal of Healthcare Engineering (JHE), 2017
Journal Article
Journal Article
Semantic Segmentation of Urban Scenes via Domain Adaptation of SYNTHIA
Domain Adaptation in Computer Vision Applications, Springer, 2017
Simulation Tools
Intelligent Vehicles: Enabling Technologies and Future Developments, Elsevier, 2017
Journal Article
Vision-Based Advanced Driver Assistance Systems
Computer Vision in Vehicle Technology: Land, Sea and Air, Wiley, 2017
The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
Workshop at Computer Vision and Pattern Recognition (CVPR), 2017
2016
Comparison of Two Non-Linear Model-Based Control Strategies for Autonomous Vehicles
Mediterranean Conference on Control and Automation (MED), 2016
Embedded Real-Time Stereo Estimation via Semi-Global Matching on the GPU
International Conference on Computational Science (ICCS), 2016
PixelVAE: A Latent Variable Model for Natural Images
International Conference on Learning Representations (ICLR), 2016
The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes
Computer Vision and Pattern Recognition (CVPR), 2016
GPU-Based Pedestrian Detection for Autonomous Driving
Procedia Computer Science, Elsevier, 2016
Hierarchical Adaptive Structural SVM for Domain Adaptation
International Journal of Computer Vision (IJCV), 2016
On-Board Object Detection: Multicue, Multimodal, and Multiview Random Forest of Local Experts
IEEE Transactions on Systems, Man, and Cybernetics (TSMC), 2016
Journal Article
Node-Adapt, Path-Adapt and Tree-Adapt: Model-Transfer Domain Adaptation for Random Forest
arXiv preprint arXiv:1611.02886, 2016
From Virtual to Real World Visual Perception using Domain Adaptation -- The DPM as Example
Domain Adaptation in Computer Vision Applications, Springer, 2016
2015
3D-Guided Multiscale Sliding Window for Pedestrian Detection
Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA), 2015
Multiview Random Forest of Local Experts Combining RGB and LIDAR Data for Pedestrian Detection
Intelligent Vehicles Symposium (IV), 2015
Spatiotemporal Stacked Sequential Learning for Pedestrian Detection
Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA), 2015
Vision-Based Offline-Online Perception Paradigm for Autonomous Driving
Winter Conference on Applications of Computer Vision (WACV), 2015
2014
Cost-Sensitive Structured SVM for Multi-Category Domain Adaptation
International Conference on Pattern Recognition (ICPR), 2014
Incremental Domain Adaptation of Deformable Part-Based Models
British Machine Vision Conference (BMVC), 2014
Domain Adaptation of Deformable Part-Based Models
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2014
Learning a Part-Based Pedestrian Detector in Virtual World
IEEE Transactions on Intelligent Transportation Systems (T-ITS), 2014
Virtual and Real World Adaptation for Pedestrian Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2014
2013
Interactive Training of Human Detectors
International Conference on Multimodal Interaction (ICMI), 2013
Learning a Multiview Part-Based Model in Virtual World for Pedestrian Detection
Intelligent Vehicles Symposium (IV), 2013
Random Forests of Local Experts for Pedestrian Detection
International Conference on Computer Vision (ICCV), 2013
Occlusion Handling via Random Subspace Classifiers for Human Detection
IEEE Transactions on Systems, Man, and Cybernetics, Part B (TSMC-B), 2013
Adapting a Pedestrian Detector by Boosting LDA Exemplar Classifiers
Workshop at Computer Vision and Pattern Recognition (CVPR), 2013
Adapting Pedestrian Detection from Synthetic to Far Infrared Images
Workshop at International Conference on Computer Vision (ICCV), 2013
Multi-Task Bilinear Classifiers for Visual Domain Adaptation
Workshop at Advances in Neural Information Processing Systems (NeurIPS), 2013
Weakly Supervised Automatic Annotation of Pedestrian Bounding Boxes
Workshop at Computer Vision and Pattern Recognition (CVPR), 2013
Book / Chapter
Domain Adaptation of Virtual and Real Worlds for Pedestrian Detection
PhD Thesis, Universitat Autònoma de Barcelona, 2013
2012
Improving HOG with Image Segmentation: Application to Human Detection
International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS), 2012
Unsupervised Domain Adaptation of Virtual and Real Worlds for Pedestrian Detection
International Conference on Pattern Recognition (ICPR), 2012
Pedestrian Detection: Exploring Virtual Worlds
Handbook of Pattern Recognition: Methods and Application, Springer, 2012
2011
Color Contribution to Part-Based Person Detection in Different Types of Scenarios
International Conference on Computer Analysis of Images and Patterns (CAIP), 2011
Opponent Colors for Human Detection
Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA), 2011
Virtual Worlds and Active Learning for Human Detection
International Conference on Multimodal Interaction (ICMI), 2011
Cool World: Domain Adaptation of Virtual and Real Worlds for Human Detection using Active Learning
Workshop at Advances in Neural Information Processing Systems (NeurIPS), 2011
2010
Learning Appearance in Virtual Scenarios for Pedestrian Detection
Computer Vision and Pattern Recognition (CVPR), 2010
Book / Chapter