VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912161008189440 |
|---|---|
| author | Hou, Haowen Zeng, Peigen Ma, Fei Yu, Fei Richard |
| author_facet | Hou, Haowen Zeng, Peigen Ma, Fei Yu, Fei Richard |
| contents | Visual Language Models (VLMs) have rapidly progressed with the recent success of large language models. However, there have been few attempts to incorporate efficient linear Recurrent Neural Networks (RNNs) architectures into VLMs. In this study, we introduce VisualRWKV, the first application of a linear RNN model to multimodal learning tasks, leveraging the pre-trained RWKV language model. We propose a data-dependent recurrence and sandwich prompts to enhance our modeling capabilities, along with a 2D image scanning mechanism to enrich the processing of visual sequences. Extensive experiments demonstrate that VisualRWKV achieves competitive performance compared to Transformer-based models like LLaVA-1.5 on various benchmarks. Compared to LLaVA-1.5, VisualRWKV has a speed advantage of 3.98 times and can save 54% of GPU memory when reaching an inference length of 24K tokens. To facilitate further research and analysis, we have made the checkpoints and the associated code publicly accessible at the following GitHub repository: see https://github.com/howard-hou/VisualRWKV. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_13362 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models Hou, Haowen Zeng, Peigen Ma, Fei Yu, Fei Richard Computer Vision and Pattern Recognition Computation and Language Machine Learning Visual Language Models (VLMs) have rapidly progressed with the recent success of large language models. However, there have been few attempts to incorporate efficient linear Recurrent Neural Networks (RNNs) architectures into VLMs. In this study, we introduce VisualRWKV, the first application of a linear RNN model to multimodal learning tasks, leveraging the pre-trained RWKV language model. We propose a data-dependent recurrence and sandwich prompts to enhance our modeling capabilities, along with a 2D image scanning mechanism to enrich the processing of visual sequences. Extensive experiments demonstrate that VisualRWKV achieves competitive performance compared to Transformer-based models like LLaVA-1.5 on various benchmarks. Compared to LLaVA-1.5, VisualRWKV has a speed advantage of 3.98 times and can save 54% of GPU memory when reaching an inference length of 24K tokens. To facilitate further research and analysis, we have made the checkpoints and the associated code publicly accessible at the following GitHub repository: see https://github.com/howard-hou/VisualRWKV. |
| title | VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models |
| topic | Computer Vision and Pattern Recognition Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2406.13362 |