Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.16365 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912584961097728 |
|---|---|
| author | Li, Muyao Wang, Zihao He, Kaichen Ma, Xiaojian Liang, Yitao |
| author_facet | Li, Muyao Wang, Zihao He, Kaichen Ma, Xiaojian Liang, Yitao |
| contents | Recently, action-based decision-making in open-world environments has gained significant attention. Visual Language Action (VLA) models, pretrained on large-scale web datasets, have shown promise in decision-making tasks. However, previous work has primarily focused on action post-training, often neglecting enhancements to the foundational model itself. In response, we introduce a novel approach, Act from Visual Language Post-Training, which refines Visual Language Models (VLMs) through visual and linguistic guidance in a self-supervised manner. This enhancement improves the models' capabilities in world knowledge, visual recognition, and spatial grounding in open-world environments. Following the above post-training paradigms, we obtain the first VLA models in Minecraft that can follow human instructions on over 1k different atomic tasks, including crafting, smelting, cooking, mining, and killing. Our experiments demonstrate that post-training on non-trajectory tasks leads to a significant 40% improvement over the best agent baseline on a diverse set of atomic tasks. Furthermore, we demonstrate that our approach surpasses traditional imitation learning-based policies in Minecraft, achieving state-of-the-art performance. We have open-sourced the code, models, and datasets to foster further research. The project page can be found in https://craftjarvis.github.io/JarvisVLA. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_16365 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse Li, Muyao Wang, Zihao He, Kaichen Ma, Xiaojian Liang, Yitao Computer Vision and Pattern Recognition Artificial Intelligence Recently, action-based decision-making in open-world environments has gained significant attention. Visual Language Action (VLA) models, pretrained on large-scale web datasets, have shown promise in decision-making tasks. However, previous work has primarily focused on action post-training, often neglecting enhancements to the foundational model itself. In response, we introduce a novel approach, Act from Visual Language Post-Training, which refines Visual Language Models (VLMs) through visual and linguistic guidance in a self-supervised manner. This enhancement improves the models' capabilities in world knowledge, visual recognition, and spatial grounding in open-world environments. Following the above post-training paradigms, we obtain the first VLA models in Minecraft that can follow human instructions on over 1k different atomic tasks, including crafting, smelting, cooking, mining, and killing. Our experiments demonstrate that post-training on non-trajectory tasks leads to a significant 40% improvement over the best agent baseline on a diverse set of atomic tasks. Furthermore, we demonstrate that our approach surpasses traditional imitation learning-based policies in Minecraft, achieving state-of-the-art performance. We have open-sourced the code, models, and datasets to foster further research. The project page can be found in https://craftjarvis.github.io/JarvisVLA. |
| title | JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2503.16365 |