Adaptive Subspace Projection for Generative Personalization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913101774848000 |
|---|---|
| author | Nguyen, Van-Anh Bui, Anh Tuan Abraham, Tamas Kim, Junae Kaur, Amardeep Omari, Rollin Vu, Thuy-Trang Phung, Dinh |
| author_facet | Nguyen, Van-Anh Bui, Anh Tuan Abraham, Tamas Kim, Junae Kaur, Amardeep Omari, Rollin Vu, Thuy-Trang Phung, Dinh |
| contents | Generative personalization often suffers from the semantic collapsing problem (SCP), where a learned personalized concept overpowers the rest of the text prompt, causing the model to ignore important contextual details. To address this, we first analyze the underlying cause, revealing that the semantic drift responsible for SCP is not random but is concentrated within a specific low-dimensional subspace. We also discover that the personalization process perturbs the embedding of the original base concept, making it an unstable reference point. Based on these insights, we introduce Test-time Embedding Adjustment with Adaptive Subspace Projection (AdaptSP), a training-free method that uses the stable, pre-trained embedding as an anchor. AdaptSP isolates the semantic drift and projects it onto the identified subspace, performing a precise adjustment that mitigates SCP while maintaining the subject identity. Our experiments show that this targeted approach significantly improves prompt fidelity and contextual alignment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_07257 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Adaptive Subspace Projection for Generative Personalization Nguyen, Van-Anh Bui, Anh Tuan Abraham, Tamas Kim, Junae Kaur, Amardeep Omari, Rollin Vu, Thuy-Trang Phung, Dinh Computer Vision and Pattern Recognition Generative personalization often suffers from the semantic collapsing problem (SCP), where a learned personalized concept overpowers the rest of the text prompt, causing the model to ignore important contextual details. To address this, we first analyze the underlying cause, revealing that the semantic drift responsible for SCP is not random but is concentrated within a specific low-dimensional subspace. We also discover that the personalization process perturbs the embedding of the original base concept, making it an unstable reference point. Based on these insights, we introduce Test-time Embedding Adjustment with Adaptive Subspace Projection (AdaptSP), a training-free method that uses the stable, pre-trained embedding as an anchor. AdaptSP isolates the semantic drift and projects it onto the identified subspace, performing a precise adjustment that mitigates SCP while maintaining the subject identity. Our experiments show that this targeted approach significantly improves prompt fidelity and contextual alignment. |
| title | Adaptive Subspace Projection for Generative Personalization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.07257 |