Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.14569 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915625746563072 |
|---|---|
| author | Hazimeh, Adam Favero, Alessandro Frossard, Pascal |
| author_facet | Hazimeh, Adam Favero, Alessandro Frossard, Pascal |
| contents | Task arithmetic has recently emerged as a promising method for editing pre-trained \textit{open-vocabulary} models, offering a cost-effective alternative to standard multi-task fine-tuning. However, despite the abundance of \textit{closed-vocabulary} models that are not pre-trained with language supervision, applying task arithmetic to these models remains unexplored. In this paper, we deploy and study task addition in closed-vocabulary image classification models. We consider different pre-training schemes and find that \textit{weight disentanglement} -- the property enabling task arithmetic -- is a general consequence of pre-training, as it appears in different pre-trained closed-vocabulary models. In fact, we find that pre-trained closed-vocabulary vision transformers can also be edited with task arithmetic, achieving high task addition performance and enabling the efficient deployment of multi-task models. Finally, we demonstrate that simple linear probing is a competitive baseline to task addition. Overall, our findings expand the applicability of task arithmetic to a broader class of pre-trained models and open the way for more efficient use of pre-trained models in diverse settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_14569 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Task Addition and Weight Disentanglement in Closed-Vocabulary Models Hazimeh, Adam Favero, Alessandro Frossard, Pascal Machine Learning Task arithmetic has recently emerged as a promising method for editing pre-trained \textit{open-vocabulary} models, offering a cost-effective alternative to standard multi-task fine-tuning. However, despite the abundance of \textit{closed-vocabulary} models that are not pre-trained with language supervision, applying task arithmetic to these models remains unexplored. In this paper, we deploy and study task addition in closed-vocabulary image classification models. We consider different pre-training schemes and find that \textit{weight disentanglement} -- the property enabling task arithmetic -- is a general consequence of pre-training, as it appears in different pre-trained closed-vocabulary models. In fact, we find that pre-trained closed-vocabulary vision transformers can also be edited with task arithmetic, achieving high task addition performance and enabling the efficient deployment of multi-task models. Finally, we demonstrate that simple linear probing is a competitive baseline to task addition. Overall, our findings expand the applicability of task arithmetic to a broader class of pre-trained models and open the way for more efficient use of pre-trained models in diverse settings. |
| title | Task Addition and Weight Disentanglement in Closed-Vocabulary Models |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2511.14569 |