S3: A Simple Strong Sample-effective Multimodal Dialog System
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_ | 1866913405636444160 |
|---|---|
| author | Rykov, Elisei Malkershin, Egor Panchenko, Alexander |
| author_facet | Rykov, Elisei Malkershin, Egor Panchenko, Alexander |
| contents | In this work, we present a conceptually simple yet powerful baseline for the multimodal dialog task, an S3 model, that achieves near state-of-the-art results on two compelling leaderboards: MMMU and AI Journey Contest 2023. The system is based on a pre-trained large language model, pre-trained modality encoders for image and audio, and a trainable modality projector. The proposed effective data mixture for training such an architecture demonstrates that a multimodal model based on a strong language model and trained on a small amount of multimodal data can perform efficiently in the task of multimodal dialog. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_18305 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | S3: A Simple Strong Sample-effective Multimodal Dialog System Rykov, Elisei Malkershin, Egor Panchenko, Alexander Computation and Language Artificial Intelligence In this work, we present a conceptually simple yet powerful baseline for the multimodal dialog task, an S3 model, that achieves near state-of-the-art results on two compelling leaderboards: MMMU and AI Journey Contest 2023. The system is based on a pre-trained large language model, pre-trained modality encoders for image and audio, and a trainable modality projector. The proposed effective data mixture for training such an architecture demonstrates that a multimodal model based on a strong language model and trained on a small amount of multimodal data can perform efficiently in the task of multimodal dialog. |
| title | S3: A Simple Strong Sample-effective Multimodal Dialog System |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2406.18305 |