P13N: Personalization in Generative AI Workshop
ICCV 2025
October 20, (full-day) in Honolulu, USA
Workshop Overview
Welcome to the Personalization in Generative AI Workshop (P13N). This full-day workshop brings together leading researchers and industry experts to explore cutting-edge personalization techniques in generative AI.
The event will feature paper presentations, panel discussions, and a competition focusing on personalized generative models across images, video, 3D, and AR/VR. Topics include advanced optimization methods for personalizing diffusion models (e.g., DreamBooth, textual inversion), multi-subject composition, cross-modal personalization, AR/VR personalization, dataset curation and benchmarking, as well as ethical and privacy considerations.
Call for Papers is Open!
We invite submissions on all aspects of personalization in generative AI. Both short papers (4 pages, out of proceedings) and long papers (8 pages, in-proceedings) are welcome and should be double-blind. References do not count toward the page limits. Including supplementary material is allowed after the references.
Topics:
- Advanced optimization methods for personalizing diffusion models (e.g., DreamBooth, textual inversion)
- Multi-subject composition: handling multiple entities in a single scene
- Cross-modal personalization: bridging text, images, video, and 3D
- AR/VR personalization for handling immersive experiences where user-specific styles or preferences adapt in real time within augmented or virtual environments
- Dataset curation for benchmarking personalized generative models
- Benchmark and evaluation metrics, developing standardized protocols to measure personalization quality, style consistency, and identity preservation
- New methods for personalized video generation
- Ethical and privacy considerations in personalization (addressing user consent, data ownership, and transparency in personalized content generation)
- Personalized storytelling and narrative visualization
- Style adaptation for digital art and illustration
- Emerging applications in gaming, e-commerce, and digital marketing
- Adapting LLM-based personalization approaches to vision tasks
- Personalization on edge devices for deploying personalized models on resource-constrained hardware
Important Dates
| Description | Date | Countdown (AoE) |
| Long-paper Deadline (in proceedings) | July 07, 2025 23:59 AoE | |
| Long-paper Notification | July 11, 2025 23:59 AoE | |
| Long-paper Camera Ready | August 13, 2025 23:59 AoE | |
| Short-paper Deadline (out of proceedings) | August 18, 2025 23:59 AoE | |
| Short-paper Notification | August 29, 2025 23:59 AoE | |
| Workshop Date | Full-day, Oct 20 |
Personalization Challenge
We will host two key challenges that address critical problems in the personalization of generative models: multi-concept image personalization and video personalization.
Multi-concept personalization challenge: Current approaches often struggle with concept interference, identity loss, or compositional failures when combining multiple concepts. This challenge will focus on methods that accurately integrate multiple personalized concepts (e.g., a custom character, specific objects, or artistic styles) while maintaining semantic consistency.
Video personalization: This challenge will focus on achieving temporally coherent personalization while maintaining subject fidelity across generated frames. This includes addressing challenges such as identity drift, motion distortion, and loss of subject details over time.
The challenge datasets and details will be announced soon, stay tuned for updates! With sponsorship from Fal.ai, we will distribute cash prizes up to $5K, stay tuned!
