The workshop solicits paper submissions of:

1. full papers meeting the full ECCV paper formatting instructions, as published by the ECCV Program Chairs for main conference papers, or

2. non-archival papers that do not go beyond 8 pages. In this case, the paper will not be published in the proceedings, but authors may be invited to present their work.   

 Accepted full papers will be published in the ECCV'26 Workshop Proceedings.  Papers are limited to 14 pages, including figures and tables, in the LNCS style of Springer. Additional pages containing only cited references are allowed. Please download the ECCV 2026 Author Kit for detailed formatting instructions. See ECCV instructions for authors for more info.

Target audience: We expect the workshop to attract attention from researchers and engineers from both academia and industry, representing a wide range of interests and backgrounds. These include ML researchers focused on core ML techniques related to model editing and unlearning, applied researchers interested in the practical aspects of deploying large generative models in production, and people interested in responsible AI (RAI), particularly in ensuring the safety and regulatory compliance of generative models.   

We make authors aware of OpenReview's moderation policy for newly created profiles:

• New profiles created without an institutional email will go through a moderation process that can take up to two weeks.

• New profiles created with an institutional email will be activated automatically.

• All participants in the ECCV 2026 review process must maintain complete and current OpenReview profiles. Please checkout complete guidelines here.