Visual concept discovery aims to extract compact and structured representations of the visual world. It has played a crucial role in many core problems in computer vision research, including both discriminative and generative tasks. The goal of this workshop is to gather together researchers in computer vision, multi-modal learning, machine learning, and cognitive science to discuss the following topics:

• Representations for learning computational models of visual concepts;

• Objectives and sources of learning signals to facilitate visual concept learning, incorporating insights from various scientific fields including natural language processing, machine learning, and cognitive science;

• Applications of visual concept learning and reasoning, including but not limited to visual scene understanding, robotics, and controllable image generation;

• Interpretability of visual learning systems, delving deeper into how these systems learn, represent, and make use of learned concepts in various application domains.

TBA

We welcome short paper submissions on the topics above. Papers should follow the CVPR format and be up to 4 pages, excluding references and supplementary material. Any supplementary should be appended to the main PDF for submission. Reviews will be double-blind.

Accepted papers will not be published in proceedings. They will be made publicly available as non-archival reports, allowing future submission to archival venues. Accepted papers will be presented in poster sessions, and selected papers will be invited for spotlight presentations.

Submission deadline: 11:59 pm (Pacific Time), April 1st, 2026

Acceptance notification date: April 20th, 2026

Camera-ready deadline: May 11th, 2026

Submission site: OpenReview