Compositional Generative Modeling: A Single Model is Not All You Need
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911901325197312 |
|---|---|
| author | Du, Yilun Kaelbling, Leslie |
| author_facet | Du, Yilun Kaelbling, Leslie |
| contents | Large monolithic generative models trained on massive amounts of data have become an increasingly dominant approach in AI research. In this paper, we argue that we should instead construct large generative systems by composing smaller generative models together. We show how such a compositional generative approach enables us to learn distributions in a more data-efficient manner, enabling generalization to parts of the data distribution unseen at training time. We further show how this enables us to program and construct new generative models for tasks completely unseen at training. Finally, we show that in many cases, we can discover separate compositional components from data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_01103 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Compositional Generative Modeling: A Single Model is Not All You Need Du, Yilun Kaelbling, Leslie Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Robotics Large monolithic generative models trained on massive amounts of data have become an increasingly dominant approach in AI research. In this paper, we argue that we should instead construct large generative systems by composing smaller generative models together. We show how such a compositional generative approach enables us to learn distributions in a more data-efficient manner, enabling generalization to parts of the data distribution unseen at training time. We further show how this enables us to program and construct new generative models for tasks completely unseen at training. Finally, we show that in many cases, we can discover separate compositional components from data. |
| title | Compositional Generative Modeling: A Single Model is Not All You Need |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2402.01103 |