Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control
- 类型：arxiv
- 标识：2609.17909
- 链接：https://arxiv.org/abs/2609.17909
- 主分类：multimodal
- 形态：method
- 被引：3
- 被引来源：Semantic Scholar
- S2被引：3
- OpenAlex被引：0
- 影响力被引：0
- TLDR：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 contributions: (1) Unified action and text conditioning, combining magnitude-aware keyboard inputs with temporally aligned text instructions and jointly annotated videos to learn navigation and event control within the same sequence; (2) Event-scale supervision for incremental generation, using a segment-level teacher trai
- OpenAlex ID：W7213512311
- OpenAlex DOI：10.48550/arxiv.2609.17909
- DOI：10.48550/arxiv.2609.17909
- DOI来源：OpenAlex
- 开放获取：green
- 开放获取链接：https://arxiv.org/pdf/2609.17909
- OpenAlex更新：2026-09-20
- 待LLM分类：否
- 标题中文：Zing-0.5: 迈向具备实时联合动作与文本控制的可玩世界
- TLDR中文：我们提出 Zing-0.5，一个 5B 自回归世界模型，专注于可玩性：用户可以探索生成的世界、影响事件演进，并通过键盘与在线文本的联合控制对反馈做出响应。我们的方法汇聚了三项技术贡献：(1) 统一的动作与文本条件建模，将感知幅度的键盘输入与时序对齐的文本指令、以及联合标注的视频结合，在同一序列中学习导航与事件控制；(2) 面向增量生成的事件尺度监督，使用分段级教师...
- 来源文件：
- /inbox/tom/_candidates/2026-09-17-agent-rag-longcontext-candidates.json
- [S2 enrich]
- [OpenAlex backfill]