Trustworthy, Robust, Uncertainty-Aware, and Explainable Visual Intelligence and Beyond (TRUE-V)

📍 Venue: CVPR 2026 Workshop · 📅 Date: June 3rd (tentative) · 🌍 Location: Denver, CO, USA

Introduction

Contemporary vision models and vision–language models are increasingly deployed in high-stakes domains, yet remain opaque, fragile, and difficult to align across tasks and modalities. This workshop aim to foster dialogue on the urgent need for transparent, reliable, and safe computer vision systems, especially in critical domains such as healthcare, transportation, and legal decision making. It brings together research on interpretability, robustness, uncertainty, and alignment under a unified design paradigm, encouraging cross-disciplinary exchange on shared technical and societal challenges. By promoting responsible design and deployment, the workshop seeks to advance forward-looking solutions for visual intelligence that enhance accountability and public trust.

Topics

We invite researchers and practitioners to submit high quality papers to our workshop TRUE-V in CVPR 2026. This workshop aims to bring together the community working on trustworthy, robust, uncertainty-aware and explainable computer vision systems to discuss recent advances, emerging challenges, and future directions in this rapidly evolving area.

We welcome submissions that address theoretical, methodological, and application oriented aspects related to advancing Trustworthy Visual Intelligence, including (but not limited to):

Interpretable and explainable computer vision
Robustness and reliability under distribution shift
Concept bottleneck and modular architectures
Uncertainty estimation and trust calibration
Alignment, safety, and ethical considerations in vision models
Evaluation benchmarks and human-in-the-loop analysis
Vision-language models and multimodal reasoning
Trustworthy deployment in high-stakes domains (e.g., healthcare, robotics, legal decision making, etc)

Submission Guidelines

Submissions should be up to 8 pages in length (excluding references) using CVPR paper template
Submissions will be peer-reviewed and selected based on technical quality, and relevance to the workshop
This workshop is not archival. We welcome submissions for both new papers and recent papers that are published in an archival venue within a year (after Feb 20, 2025).
Submission site: Openreview

More Instructions on submissions will be provided shortly.