This workshop provides a venue for original scientific work presenting novel model editing techniques. We also encourage submissions on model compression methods, which aim to minimize the storage and computational costs of operating trained models with little impact on their performance. Additionally, papers that explore methods for adapting foundation models for efficient fine-tuning or editing are relevant.

Workshop topics: We solicit papers on topics including, but not limited to:

• Unlearning

• Model Stitching and Editing

• Model Merging and "MoErging" (Mixture of Experts Merging)

• Model compression

• Efficient domain adaptation 

• Multi-domain/cross-domain U&ME

• Online/lifelong learning, unlearning, and model editing

• Responsible U&ME (e.g., robustness, ethics and fairness, resource efficiency, privacy, and regulatory compliance)  

• Applications in computer vision 

Though we prioritize papers on generative models, but we also welcome submissions that present methods designed for other types of models, such as discriminative classifiers.

11 May 2025 - Website created!

21 May 2025 - Updated the details of the Genμ Challenge

1 June 2025 - Challenge Begins! [Details] [Kaggle]

20 June 2025 - We are now also accepting non-archival papers!

1 July 2025 - The paper submission deadline has been extended to 3 July 2025.

12 July 2025 - Notifications of acceptance sent out!

1 October 2025 - Published the list of accepted papers and extended abstracts

3 October 2025 - Program and Invited Speakers are now online!

15 October 2025 - Program updated!

This research is supported by Srijan: COE on Generative AI supported by the IndiaAI mission, MEITY, and Meta. Masi was partially supported by PNRR MUR PE0000013-FAIR under the MUR National Recovery and Resilience Plan funded by the European Union - NextGenerationEU and MUR PRIN 2022 project 20227YET9B ``AdVVent''.