Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2601.20540 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917227449548800 |
|---|---|
| author | Robbyant Team Gao, Zelin Wang, Qiuyu Zeng, Yanhong Zhu, Jiapeng Cheng, Ka Leong Li, Yixuan Wang, Hanlin Xu, Yinghao Ma, Shuailei Chen, Yihang Liu, Jie Cheng, Yansong Yao, Yao Zhu, Jiayi Meng, Yihao Zheng, Kecheng Bai, Qingyan Chen, Jingye Shen, Zehong Yu, Yue Zhu, Xing Shen, Yujun Ouyang, Hao |
| author_facet | Robbyant Team Gao, Zelin Wang, Qiuyu Zeng, Yanhong Zhu, Jiapeng Cheng, Ka Leong Li, Yixuan Wang, Hanlin Xu, Yinghao Ma, Shuailei Chen, Yihang Liu, Jie Cheng, Yansong Yao, Yao Zhu, Jiayi Meng, Yihao Zheng, Kecheng Bai, Qingyan Chen, Jingye Shen, Zehong Yu, Yue Zhu, Xing Shen, Yujun Ouyang, Hao |
| contents | We present LingBot-World, an open-sourced world simulator stemming from video generation. Positioned as a top-tier world model, LingBot-World offers the following features. (1) It maintains high fidelity and robust dynamics in a broad spectrum of environments, including realism, scientific contexts, cartoon styles, and beyond. (2) It enables a minute-level horizon while preserving contextual consistency over time, which is also known as "long-term memory". (3) It supports real-time interactivity, achieving a latency of under 1 second when producing 16 frames per second. We provide public access to the code and model in an effort to narrow the divide between open-source and closed-source technologies. We believe our release will empower the community with practical applications across areas like content creation, gaming, and robot learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20540 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Advancing Open-source World Models Robbyant Team Gao, Zelin Wang, Qiuyu Zeng, Yanhong Zhu, Jiapeng Cheng, Ka Leong Li, Yixuan Wang, Hanlin Xu, Yinghao Ma, Shuailei Chen, Yihang Liu, Jie Cheng, Yansong Yao, Yao Zhu, Jiayi Meng, Yihao Zheng, Kecheng Bai, Qingyan Chen, Jingye Shen, Zehong Yu, Yue Zhu, Xing Shen, Yujun Ouyang, Hao Computer Vision and Pattern Recognition We present LingBot-World, an open-sourced world simulator stemming from video generation. Positioned as a top-tier world model, LingBot-World offers the following features. (1) It maintains high fidelity and robust dynamics in a broad spectrum of environments, including realism, scientific contexts, cartoon styles, and beyond. (2) It enables a minute-level horizon while preserving contextual consistency over time, which is also known as "long-term memory". (3) It supports real-time interactivity, achieving a latency of under 1 second when producing 16 frames per second. We provide public access to the code and model in an effort to narrow the divide between open-source and closed-source technologies. We believe our release will empower the community with practical applications across areas like content creation, gaming, and robot learning. |
| title | Advancing Open-source World Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.20540 |