VideoWorld: Exploring Knowledge Learning from Unlabeled Videos
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912259625713664 |
|---|---|
| author | Ren, Zhongwei Wei, Yunchao Guo, Xun Zhao, Yao Kang, Bingyi Feng, Jiashi Jin, Xiaojie |
| author_facet | Ren, Zhongwei Wei, Yunchao Guo, Xun Zhao, Yao Kang, Bingyi Feng, Jiashi Jin, Xiaojie |
| contents | This work explores whether a deep generative model can learn complex knowledge solely from visual input, in contrast to the prevalent focus on text-based models like large language models (LLMs). We develop VideoWorld, an auto-regressive video generation model trained on unlabeled video data, and test its knowledge acquisition abilities in video-based Go and robotic control tasks. Our experiments reveal two key findings: (1) video-only training provides sufficient information for learning knowledge, including rules, reasoning and planning capabilities, and (2) the representation of visual change is crucial for knowledge acquisition. To improve both the efficiency and efficacy of this process, we introduce the Latent Dynamics Model (LDM) as a key component of VideoWorld. Remarkably, VideoWorld reaches a 5-dan professional level in the Video-GoBench with just a 300-million-parameter model, without relying on search algorithms or reward mechanisms typical in reinforcement learning. In robotic tasks, VideoWorld effectively learns diverse control operations and generalizes across environments, approaching the performance of oracle models in CALVIN and RLBench. This study opens new avenues for knowledge acquisition from visual data, with all code, data, and models open-sourced for further research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_09781 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VideoWorld: Exploring Knowledge Learning from Unlabeled Videos Ren, Zhongwei Wei, Yunchao Guo, Xun Zhao, Yao Kang, Bingyi Feng, Jiashi Jin, Xiaojie Computer Vision and Pattern Recognition This work explores whether a deep generative model can learn complex knowledge solely from visual input, in contrast to the prevalent focus on text-based models like large language models (LLMs). We develop VideoWorld, an auto-regressive video generation model trained on unlabeled video data, and test its knowledge acquisition abilities in video-based Go and robotic control tasks. Our experiments reveal two key findings: (1) video-only training provides sufficient information for learning knowledge, including rules, reasoning and planning capabilities, and (2) the representation of visual change is crucial for knowledge acquisition. To improve both the efficiency and efficacy of this process, we introduce the Latent Dynamics Model (LDM) as a key component of VideoWorld. Remarkably, VideoWorld reaches a 5-dan professional level in the Video-GoBench with just a 300-million-parameter model, without relying on search algorithms or reward mechanisms typical in reinforcement learning. In robotic tasks, VideoWorld effectively learns diverse control operations and generalizes across environments, approaching the performance of oracle models in CALVIN and RLBench. This study opens new avenues for knowledge acquisition from visual data, with all code, data, and models open-sourced for further research. |
| title | VideoWorld: Exploring Knowledge Learning from Unlabeled Videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.09781 |