PulseAugur
中
实时 17:17:24
English(EN) Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control

Zing-0.5:新型 5B 世界模型支持实时交互式探索

研究人员推出了 Zing-0.5,一个拥有 50 亿参数的自回归世界模型,专为交互式探索而设计。该模型集成了键盘和文本控制,可在生成的环境中进行实时导航和事件操控。Zing-0.5 采用统一的动作和文本条件设置、用于增量生成的事件尺度监督以及低成本的实时交互,以极低的成本实现了 24 FPS。它在 WBench 导航任务上表现出色,并发布了模型权重和部署代码,以促进可玩生成世界的进一步发展。 AI

影响 开启了新的 AI 驱动内容创作和探索形式,可能对游戏和模拟行业产生影响。

排序理由 该集群描述了一篇介绍新型 AI 模型 Zing-0.5 及其技术贡献的研究论文。

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

Zing-0.5:新型 5B 世界模型支持实时交互式探索

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群描述了一篇介绍新型 AI 模型 Zing-0.5 及其技术贡献的研究论文。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
42 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Mingyang Chen, Shengdong Chen, Xiaoxiao Fu, Bosheng Gong, Haoyuan Guo, Bowen Li, Jiawen Li, Kejun Li, Tianpeng Li, Yin Liu, Haoze Sun, Zeyang Tian, Meng Wang, Xinmiao Wu, Jiangqiao Yan, Zining Zhao ·

    Zing-0.5:迈向可玩世界,实现实时联合动作和文本控制

    arXiv:2609.17909v1 Announce Type: cross Abstract: We introduce Zing-0.5, a 5B autoregressive world model designed for playability: users can explore generated worlds, influence unfolding events, and respond to the resulting feedback through joint keyboard and online text control.…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    Zing-0.5:迈向具有实时联合动作和文本控制的可玩世界

    We introduce Zing-0.5, a 5B autoregressive world model designed for playability: users can explore generated worlds, influence unfolding events, and respond to the resulting feedback through joint keyboard and online text control. Our approach brings together three technical cont…