Exploiting symmetry in structured data is a powerful way to improve the generalization ability, data efficiency, and robustness of AI systems, which leads to the research direction of equivariant deep learning. Showing its effectiveness, it has been widely adopted in a large variety of subareas of computer vision, from 2D image analysis to 3D perception, as well as further applications such as medical imaging and robotics.

Our topics include but are not limited to:

• Theoretical foundations of equivariant deep learning with symmetry and group theory.
• Equivariance by design: Neural network architectures and mathematical guarantees.
• Equivariance from data: Learning equivariant and invariant features.
• Applications in 2D and 3D computer vision and robotics.
• Applications in broader science: computational biology, medicine, natural science, etc.
• Equivariance in the large-model era and potential future directions.