{"ID":2863861,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.25172","arxiv_id":"2509.25172","title":"Personalized Vision via Visual In-Context Learning","abstract":"Modern vision models, trained on large-scale annotated datasets, excel at predefined tasks but struggle with personalized vision -- tasks defined at test time by users with customized objects or novel objectives. Existing personalization approaches rely on costly fine-tuning or synthetic data pipelines, which are inflexible and restricted to fixed task formats. Visual in-context learning (ICL) offers a promising alternative, yet prior methods confine to narrow, in-domain tasks and fail to generalize to open-ended personalization. We introduce Personalized In-Context Operator (PICO), a simple four-panel framework that repurposes diffusion transformers as visual in-context learners. Given a single annotated exemplar, PICO infers the underlying transformation and applies it to new inputs without retraining. To enable this, we construct VisRel, a compact yet diverse tuning dataset, showing that task diversity, rather than scale, drives robust generalization. We further propose an attention-guided seed scorer that improves reliability via efficient inference scaling. Extensive experiments demonstrate that PICO (i) surpasses fine-tuning and synthetic-data baselines, (ii) flexibly adapts to novel user-defined tasks, and (iii) generalizes across both recognition and generation.","short_abstract":"Modern vision models, trained on large-scale annotated datasets, excel at predefined tasks but struggle with personalized vision -- tasks defined at test time by users with customized objects or novel objectives. Existing personalization approaches rely on costly fine-tuning or synthetic data pipelines, which are infle...","url_abs":"https://arxiv.org/abs/2509.25172","url_pdf":"https://arxiv.org/pdf/2509.25172v1","authors":"[\"Yuxin Jiang\",\"Yuchao Gu\",\"Yiren Song\",\"Ivor Tsang\",\"Mike Zheng Shou\"]","published":"2025-09-29T17:58:45Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[\"Diffusion Model\",\"Transformer\"]","has_code":false}