arXiv Open Access 2026

Advancing Open-source World Models

Robbyant Team Zelin Gao Qiuyu Wang Yanhong Zeng Jiapeng Zhu +19 lainnya
Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

Penulis (24)

Robbyant Team

Z

Zelin Gao

Q

Qiuyu Wang

Y

Yanhong Zeng

J

Jiapeng Zhu

K

Ka Leong Cheng

Y

Yixuan Li

H

Hanlin Wang

Y

Yinghao Xu

S

Shuailei Ma

Y

Yihang Chen

J

Jie Liu

Y

Yansong Cheng

Y

Yao Yao

J

Jiayi Zhu

Y

Yihao Meng

K

Kecheng Zheng

Q

Qingyan Bai

J

Jingye Chen

Z

Zehong Shen

Y

Yue Yu

X

Xing Zhu

Y

Yujun Shen

H

Hao Ouyang

Format Sitasi

Team, R., Gao, Z., Wang, Q., Zeng, Y., Zhu, J., Cheng, K.L. et al. (2026). Advancing Open-source World Models. https://arxiv.org/abs/2601.20540

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2026
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓