World Models in the Loop: Towards Application-Driven World Model Evaluation

More workshops at European Conference on Computer Vision 2026

• 3D Human Understanding (Third Edition) — Advances 3D understanding of human bodies, faces, and hands for applications in AR/VR, animation, and...
• 3D in the Era of World Models — Explores how world models and neural 3D representations are converging to enable unified 3D scene...
• 11th Workshop and Competition on Affective and Behavior Analysis in-the-wild — Long-running workshop and competition on recognizing human emotions, affect, and social behaviors from in-the-wild visual...
• Agent in World: Living Worlds with Interactive Agents — Explores embodied agents that perceive, reason, and interact within dynamic living world models. Focuses on...
• AI4M3D: Artificial Intelligence for Medical 3D Vision — Focuses on AI methods for analyzing and reconstructing 3D medical data from CT, MRI, and...
• AI4MFDD: Artificial Intelligence for Multimedia Forensics and Disinformation Detection — Focuses on AI methods for detecting manipulated, synthetic, and misleading multimedia content including deepfakes, image...
• The 4th AI for Visual Arts Workshop and Challenges (AI4VA) — Focuses on AI methods for analyzing, understanding, and generating visual art across historical periods and...
• Towards Sim2Real Transfer and Unified Reasoning: 10th AI City Challenge — 10th edition of the AI City Challenge combining sim-to-real transfer research with unified reasoning for...
• AI for Climate and Conservation (AICC) — Applies AI and computer vision to climate change research and biodiversity conservation. Covers species identification,...
• 14th International Workshop on Assistive Computer Vision and Robotics — Long-running workshop applying computer vision and robotics to assistive technologies for people with disabilities. Covers...
• Third Workshop on Audio-Visual Generation and Learning (AVGenL) — Covers multimodal generation and learning models that jointly process and produce synchronized audio and visual...
• 2nd Workshop on Benchmarking Evidence-Aligned Multimodal Reasoning (BEAM 2) — Develops rigorous evaluation benchmarks for multimodal reasoning systems that require evidence-based inference from visual and...
• BioImage Computing — Focuses on AI and computer vision methods for biological and biomedical microscopy image analysis. Covers...
• Biomedical Image and Signal Computing for Unbiasedness, Interpretability, and Trustworthiness — Addresses bias, interpretability, and trustworthiness challenges in AI applied to biomedical imaging and signal data....
• How to Build Effective World Models for Embodied AI — Practical workshop on designing and training world models that effectively support embodied agent planning and...
• 2nd Workshop on Curated Data for Efficient Learning (CDEL) — Explores data curation strategies that enable more efficient learning with less data in computer vision....
• CONTEXTUS: Understanding Multi-Actor Scene Interaction in Context — Focuses on understanding complex interactions between multiple actors - humans, animals, objects - within scene...
• Computer Vision for Humanitarian Action — Bridges computer vision research and humanitarian practice, covering Earth observation, conflict monitoring, and responsible AI...
• 3rd Workshop on Computer Vision for Ecology — Applies computer vision to ecological monitoring, species identification, and biodiversity assessment. Covers camera trap analysis,...
• CVNH: Computer Vision for Natural Heritage — Applies computer vision to documenting, monitoring, and preserving natural heritage sites, biodiversity, and ecosystems. Covers...
• Data Curation and Augmentation in Medical Imaging — Addresses creating high-quality training datasets for medical imaging AI through systematic curation, annotation, and augmentation...
• Observing and Acting as Dexterous Hands — Explores visual observation and motor control for dexterous robotic hand manipulation at human level. Covers...
• DriveX: Foundation Models for Autonomous Driving — Advances foundation models for autonomous driving, exploring how large-scale pretraining on diverse driving data can...
• Efficient Visual Generation (EVG) — Addresses computational efficiency in visual generation models, developing faster and cheaper methods for image and...
• Embodied Agent and Dialog — Workshop at the intersection of embodied AI and natural language dialog systems, focusing on agents...
• Workshop on Embodied Multimodal Reasoning in Physical Environments — Explores multimodal reasoning capabilities of embodied agents operating in physical environments, including visual question answering,...
• Emerging Behaviors in Embodied AI for Achieving Robust Autonomy — Investigates how embodied AI agents develop complex behaviors and skills through interaction with environments. Focuses...
• E.T.: Empirical Theory in Representation Learning — Explores theoretical foundations and empirical understanding of representation learning in deep neural networks. Bridges theoretical...
• Event-Based Multimodal Vision: Imaging, Perception, and Understanding — Advances event cameras and neuromorphic sensing combined with conventional vision for robust perception in dynamic...
• 3rd Workshop on Explainable CV (eXCV): Challenges and Opportunities in the Era of Foundation Models — Addresses explainability challenges in modern foundation model-based computer vision systems. Covers attribution methods, concept-based explanations,...
• 3rd Workshop on Fairness and Ethics in AI: Facing the ChalLEnge through Model Debiasing (FAILED) — Addresses algorithmic bias, fairness, and ethical concerns in computer vision and AI systems through debiasing...
• Force-Grounded, Cross-View Articulated Manipulation — Explores robotic manipulation grounded in physical force sensing and cross-view visual understanding. Covers tactile feedback...
• 2nd Workshop on Foundation Data for Industrial Tech Transfer — Bridges the gap between foundation model research and industrial computer vision applications through high-quality curated...
• Functionality, Articulation, and Interaction for Modeling and Generating 3D Objects — Focuses on understanding and generating 3D objects with functional properties, articulated parts, and interaction affordances....
• GAIA 2026: Geospatial AI and Foundation Models — Covers foundation models and AI methods applied to geospatial data including satellite imagery, aerial photography,...
• Third Workshop on Foundation and Generative Models in Biometrics — Applies foundation models and generative AI to biometric recognition tasks including face, fingerprint, iris, and...
• 2nd Workshop on Generative AI for Audio-Visual Content Creation — Explores generative models for producing and editing synchronized audio-visual media, including video generation, music visualization,...
• Interactive Social Avatars with the 4th GENEA Gesture Generation Challenge — 4th edition of the GENEA challenge advancing gesture generation for social avatars and virtual humans....
• Workshop on Geometric Intelligence: From Vision to Scientific Discovery — Explores how geometric deep learning and 3D computer vision can accelerate scientific discovery across domains...
• Human-Scene Interaction (HSI): Towards Scene-Aware Motion, Communication, and Embodied Agents — Explores interactions between humans and their environments, including how humans move through and interact with...
• Workshop on Human-AI Co-Creation — Explores the collaborative space between humans and AI systems for creative tasks including art, design,...
• Human-inspired Computer Vision — Explores how principles from human visual perception and cognition can inspire more robust and efficient...
• Human-Centered Multimodal Intelligence in the Wild: Foundation Models and Beyond — Explores foundation models for human-centered visual understanding in unconstrained real-world conditions. Covers person detection, tracking,...
• Hyperbolic Deep Learning for Computer Vision: 3rd Beyond Euclidean Workshop — Explores deep learning architectures operating in hyperbolic and non-Euclidean geometry for computer vision. Addresses hierarchical...
• Instance-Level Recognition and Generation — Addresses fine-grained instance-level recognition and generation tasks including person re-identification, instance segmentation, and controlled generation...
• LifeGenIP: Life-Cycle Intellectual Property Governance of Visual Generative Models — Addresses intellectual property, copyright, and provenance issues throughout the lifecycle of visual generative AI models....
• 4th LIMIT Workshop — Addresses learning and inference challenges in computer vision under imperfect or limited supervision conditions. Covers...
• Low-Level Vision Frontiers — Brings together researchers exploring low-level vision at the intersection of generative models, reward learning, and...
• 2nd Workshop on Marine Vision — Applies computer vision to underwater and marine environments for marine biology, oceanography, and underwater robotics....
• Medical Foundation Models and Benchmarks — Focuses on developing and evaluating large-scale foundation models pretrained on medical imaging data. Covers benchmark...
• Workshop on Medical Video Understanding (MedVidU) — Focuses on AI methods for analyzing medical video data from endoscopy, laparoscopy, ultrasound, and surgical...
• 3rd Workshop on More Exploration, Less Exploitation (MELEX) — Addresses the exploration-exploitation tradeoff in visual learning systems, encouraging novel dataset collection, benchmark creation, and...
• 2nd Workshop on MUCG: Multimodal Large Language Models for Unified Comprehension and Generation — Advances multimodal large language models capable of unified image and text comprehension and generation. Covers...
• Multimodal Digital Agents Workshop — Focuses on building autonomous digital agents powered by multimodal foundation models that can perceive and...
• Multimodal Reasoning and Slow Thinking in the Large Model Era: Towards System 2 and Beyond — Explores how large multimodal models can develop deliberate reasoning capabilities for complex visual and language...
• MUSTCV: Computer Vision for Multimedia Spatial Intelligence through Time — Explores computer vision methods for understanding and generating spatial environments across time, with applications in...
• 3rd Neural SLAM Workshop (NeuSLAM) — Explores neural and learning-based approaches to simultaneous localization and mapping. Covers differentiable SLAM, neural implicit...
• Workshop on Neuromorphic Vision (NeVi) — Explores event-based and neuromorphic cameras for visual perception, offering advantages in low latency, high dynamic...
• On-device Embodied World Models — Explores compact, efficient world models designed to run on edge devices and embedded systems for...
• OpenSUN3D: Workshop and Challenge on Open-World 3D Scene Understanding and Representations — Advances open-vocabulary and open-world 3D scene understanding with neural representations. Covers zero-shot 3D object recognition,...
• Human Motion in Real-World and Clinical Setting: Benchmark and Challenge on Parkinsonian Gait — Clinical workshop combining human motion analysis with a benchmark challenge for detecting and characterizing Parkinsonian...
• The Path to Manufacturing: Evolving 3D Generation to Intelligent Computer-Aided Design — Bridges 3D generative AI with practical manufacturing and computer-aided design workflows. Explores how diffusion models...
• Perception Test: from Tabletop to City Scale — Advances visual perception evaluation and methods across different scales from fine-grained object understanding to city-scale...
• Privacy, Fairness, Accountability and Transparency in Computer Vision (PFATCV) — Addresses the intersection of privacy, algorithmic fairness, accountability, and transparency in computer vision systems. Covers...
• Physical AI: Understanding and Building the Physical World — Explores AI systems that understand and reason about physical principles, causality, and material properties in...
• 11th Workshop in Computer Vision in Plant Phenotyping and Agriculture — Long-running workshop applying computer vision to plant phenotyping, crop monitoring, and precision agriculture. Covers leaf...
• Recovering 6D Object Pose — Focuses on estimating the full 6D position and orientation of objects from visual observations. Covers...
• 3rd International Workshop on Privacy-Preserving Computer Vision — Focuses on developing computer vision systems that preserve individual privacy while maintaining utility. Covers face...
• Privacy-Preserving Visual Localization and Mapping — Addresses privacy concerns in visual localization and SLAM systems that process images of people and...
• 3rd Workshop on Quantum Computer Vision and Machine Learning (QCVML) — Investigates quantum computing approaches to computer vision and machine learning, exploring potential speedups and novel...
• Real-World Video Representation Learning — Addresses learning robust video representations from unconstrained real-world data at scale. Covers self-supervised and weakly...
• RetailVision7: Revolutionizing the World of Retail — Focuses on computer vision applications in retail environments including product recognition, planogram compliance, cashierless checkout,...
• Safe and Defensive Autonomous Driving — Focuses on safety-critical aspects of autonomous driving systems including adversarial robustness, failure detection, and defensive...
• Safe World Models for Trustworthy Embodied AI — Focuses on building world models for embodied AI that are accurate, safe, reliable, and aligned...
• Scalable 3D Scene Generation and 3D Geometric Scene Understanding — Addresses methods for generating realistic 3D scenes at scale and understanding geometric structure of 3D...
• Structure-from-Motion in the Age of Deep Learning (SfM-ADL) — Addresses how deep learning is transforming classical structure-from-motion and 3D reconstruction pipelines. Covers learned feature...
• SLoMO: Story-Level Movie Understanding and Audio Description — Focuses on understanding movies and visual narratives at the story level, including plot understanding, character...
• Human Motion-Informed World Models and Socially Intelligent Action — Develops world models that incorporate human motion understanding to enable socially intelligent autonomous behavior. Covers...
• TerraBytes II: Towards Global Datasets and Models for Earth Observation — Focuses on large-scale datasets and foundation models for Earth observation from satellite and aerial imagery....
• TwinWorld: Visual Intelligence for Built Environment Digital Twins — Develops visual AI methods for creating and maintaining digital twins of built environments including buildings,...
• Uncertainty Quantification for Computer Vision (UNCV) — Focuses on methods for quantifying and communicating uncertainty in computer vision models to improve reliability...
• UniWorld: Universal Representations for Perception, Reasoning, and World Modeling — Develops unified neural architectures and representations that simultaneously support visual perception, reasoning, and world modeling...
• 3rd Workshop and Challenge on Unlearning and Model Editing (U&ME) — Addresses machine unlearning and model editing techniques for removing or updating specific knowledge in trained...
• Large-scale Video Object Segmentation — Advances video object segmentation methods at large scale, addressing temporal consistency, long-video understanding, and diverse...
• ViLMa: 2nd Workshop on Visual Localization and Mapping: From Optimization to 3D Foundation Models — Advances visual localization and 3D mapping methods from classical optimization-based approaches to modern 3D foundation...
• Vision for Art and Culture (VISART) VIII — 8th edition of the long-running workshop applying computer vision to art history, cultural heritage, and...
• ECCV 2026 Workshop on Visual Persuasion (VisPer) — Investigates how visual content is used to persuade, influence, and shape beliefs and behaviors in...
• Workshop on Visual Perception and Reasoning in the Interactable World — Focuses on visual understanding of interactive and manipulable environments where objects have affordances and functional...
• Visual Object Tracking and Segmentation Challenge VOTS2026 Workshop — 2026 edition of the Visual Object Tracking and Segmentation challenge, benchmarking state-of-the-art methods for tracking...
• Wearable AI and Egocentric Vision — Advances egocentric vision and long-context multimodal understanding for next-generation wearable devices, featuring grand challenges using...
• Wild3D: 3D Modeling, Reconstruction, and Generation in the Wild — Addresses 3D understanding from unconstrained in-the-wild visual data including internet images and videos. Covers monocular...
• Women in Computer Vision — Community and research workshop celebrating and advancing the contributions of women in computer vision research....