P13N: Personalization in Generative AI Workshop

CVPR 2026

June 4, 2026, 8:30 a.m. – 12:30 p.m.

Room Mile High 4CD, Denver Convention Center, Denver, CO, USA

Workshop Overview

The P13N: Personalization in Generative AI workshop aims to unite researchers, practitioners, and artists from academia and industry to explore the challenges and opportunities in personalized generative systems.

Generative AI has revolutionized creativity and problem-solving across domains, yet personalization remains one of the most challenging and underexplored frontiers. Building systems that understand and adapt to individual users’ preferences, identities, or contexts raises profound technical, ethical, and societal questions. Through invited talks, panel discussions, poster sessions, and hands-on challenges, P13N serves as a platform to foster new directions in model design, evaluation, and governance for personalized generative systems.

Call for Papers is Closed

We invite submissions on all aspects of personalization in generative AI. Both short papers (4 pages, non-archival) and long papers (8 pages, archival) 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 generative models
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
Dataset curation for benchmarking personalized generative models
Benchmark and evaluation metrics for personalization quality, style consistency, and identity preservation
New methods for personalized video generation
Ethical and privacy considerations (user consent, data ownership, transparency)
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

Submissions Closed

Important Dates

Description	Date	Countdown (AoE)
Submissions Open	March 1, 2026
Long-paper Deadline (archival)	March 23, 2026 23:59 AoE
Long-paper Notification	March 25, 2026 23:59 AoE
Long-paper Camera Ready	April 8, 2026 23:59 AoE
Short-paper Deadline (non-archival)	April 20, 2026 23:59 AoE
Short-paper Notification	April 25, 2026 23:59 AoE

Invited Speakers

Nataniel Ruiz is a Research Scientist at Google Deepmind and the lead author of DreamBooth, which was selected for a Best Paper Award at CVPR 2023. His main research interests revolve around generative models, and he has authored other works in the areas of controllability and personalization of diffusion models, including StyleDrop, ZipLoRA, and HyperDreamBooth.

Kfir Aberman is a founding member of Decart AI, leading the innovation in real-time, interactive generative video models. Previously, as Principal Research Scientist at Snap Research, he led the company’s Personalized Generative AI effort. His research, including breakthroughs like DreamBooth and Prompt-to-Prompt, has become foundational to how people and creators today interact with generative AI.

Pinar Yanardag is an Assistant Professor at Virginia Tech, where she leads research on generative AI, with a focus on personalization, controllability, and interpretability of generative models for images and video.

Or Patashnik is an assistant professor at Tel Aviv University and a Research Scientist at Snap. Her research lies at the intersection of computer graphics, computer vision, and machine learning, with a focus on generative models. She works on image and video generation, semantic editing, and personalization, driven by the goal of making visual content creation more controllable and expressive.

Schedule

Session	Time
Opening Remarks	8:25 – 8:30 AM
Oral Presentation #1 — Michael Opitz, "MakeupMirror: Improving Facial Attribute Preservation in Diffusion Models for Makeup Transfer"	8:30 – 8:40 AM
Oral Presentation #2 — Idan Schwartz, "Single Image Iterative Subject-driven Generation and Editing"	8:40 – 8:50 AM
Oral Presentation #3 — Yijie Zhu, "When Identities Collapse: A Stress-Test Benchmark for Multi-Subject Personalization"	8:50 – 9:00 AM
Keynote Talk #1 — Pinar Yanardag (25 min + 5 min Q&A)	9:00 – 9:30 AM
Keynote Talk #2 — Kfir Aberman (25 min + 5 min Q&A)	9:30 – 10:00 AM
Panel Discussion — Nupur Kumari (Moderator), Hadar Averbuch-Elor, Or Patashnik, Nataniel Ruiz, Kfir Aberman, Rana Hanocka	10:00 – 10:30 AM
Coffee Break & Poster Session (Posters 277–284)	10:30 – 11:30 AM
Keynote Talk #3 — Nataniel Ruiz (25 min + 5 min Q&A)	11:30 AM – 12:00 PM
Keynote Talk #4 — Or Patashnik (25 min + 5 min Q&A)	12:00 – 12:30 PM
Closing Remarks	12:30 – 12:35 PM

Accepted Papers

Long Papers (Proceedings)

Advancing Subject Consistent and Textual Alignment Personalized Image Generation via Precise Attribute Learning
Zijian He, Zheng Liu, Huiguo He, Weizhi Zhong, Yejun Tang, Huan Yang, Di ZHANG, Guanbin Li
PerFuSe: Personalized Full-Image Restoration via Modular Fusion
Nazish Naeem, Zeeshan Nadir, Seok-Jun Lee, Hamid Rahim Sheikh
MakeupMirror: Improving Facial Attribute Preservation in Diffusion Models for Makeup Transfer
Michael Opitz, Angel Martínez-González, Nefeli Andreou, Sabine Sternig, Matthieu Guillaumin, Epameinondas Antonakos
Single Image Iterative Subject-driven Generation and Editing
Yair Shpitzer, Aviv Weidenfeld, Gal Chechik, Idan Schwartz
Let Triggers Control: Frequency-Aware Dropout for Effective Token Control
Junyoung Koh, Hoyeon Moon, Dongha Kim, Seungmin Lee, SangHyun Park, Min Song
When Identities Collapse: A Stress-Test Benchmark for Multi-Subject Personalization
Zhihan Chen, Yuhuan Zhao, Yijie Zhu, Xinyu Yao
SubjectState: Persistent Subject States for Still-Image Personalized Video Generation
Adhiraj Chhoda
How Much Do Shared Adapters Leak? Measuring Privacy Risks in Personalized Diffusion Model Weights
Mujtaba Hasan
Timestep-Constrained One-Shot Video Motion Customization
Vatsal Baherwani, Yixuan Ren, Abhinav Shrivastava

Short Papers (Non-Proceedings)

DesignPref: Capturing Personal Preferences in Visual Design Generation
Yi-Hao Peng, Jeffrey P. Bigham, Jason Wu
A Dataset for Dynamic Human Preferences for Vision Language Models
Hannah Gao, Dylan Hadfield-Menell, Rachel Ma
Personalizing Text-to-Image Models to Individual Taste
Anne-Sofie Maerten, Juliane Verwiebe, Shyamgopal Karthik, Ameya Prabhu, Johan Wagemans, Matthias Bethge
SwiftPie: Lightning-fast Subject-driven Image Personalization via One step Diffusion
Huy Duong, Trong-Tung Nguyen, Cuong Pham, Anh Tuan Tran, Khoi Nguyen, Minh Hoai