OpenSUN3D: Workshop and Challenge on Open-World 3D Scene Understanding and Representations
ViLMa – 2nd Workshop on Visual Localization and Mapping; From Optimization to 3D Foundation Models
Agent in World: Living Worlds with Interactive Agents
Interactive Social Avatars with the 4th GENEA Gesture Generation Challenge
Multimodal Digital Agents Workshop
Biomedical Image and Signal Computing for Unbiasedness, Interpretability, and Trustworthiness
2nd Workshop on Marine Vision
Instance-Level Recognition and Generation
Workshop on Human-AI Co-Creation
2nd Workshop on MUCG: Multimodal Large Language Models for Unified Comprehension and Generation
4th LIMIT Workshop
3rd Workshop on Explainable CV (eXCV): Challenges and Opportunities in the Era of Foundation Models
3rd workshop on Fairness and Ethics in AI: facing the ChalLEnge through Model Debiasing (FAILED)
ECCV 2026 Workshop on Viual Persuasion (VisPer)
Uncertainty Quantification for Computer Vision UNCV
Workshop on Artificial Intelligence for Multimedia Forensics and Disinformation Detection: AI4MFDD
TerraBytes II: Towards global datasets and models for Earth Observation
3rd Workshop on Computer Vision for Ecology
Event-Based Multimodal Vision: Imaging, Perception, and Understanding
Our workshop focuses on research at the intersection of event-based sensing and multimodal vision, spanning the full pipeline from sensing systems and low-level imaging to perception and high-level understanding.
CVNH - Computer Vision for Natural Heritage
Post-Training Diffusion Models: Enhancing Capabilities, Control, and Alignment
Pre-trained generative models are built using massive, typically unlabeled corpora, enabling them to capture broad, generic knowledge across diverse domains. However, at inference time, we often aim to adjust and customize these models — to exert control, enhance specific capabilities, and align their behavior with user intent and preferences. Post-training techniques have therefore emerged as both a practical necessity and an accessible means of adapting these powerful, yet static, models. This tutorial surveys the state-of-the-art in post-training methods for diffusion models, analyzing their strengths, limitations, and areas of application. We conclude with a critical discussion on the boundaries of post-training — asking whether fundamental semantic malfunctions can truly be resolved without revisiting the pretraining process.