# Zing-0.5 发布 5B 实时联合动作与文本控制世界模型

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-09-15 08:00
- AIHOT 分数：58
- AIHOT 链接：https://aihot.news/items/cmu52md5m08q2roqbxq9oc2fq
- 原文链接：https://arxiv.org/abs/2609.17909

## AI 摘要

Zing-0.5 是一个 5B 自回归世界模型，支持键盘与文本联合控制，让用户在生成世界中导航并影响事件。技术要点包括统一动作与文本条件、事件级分布匹配蒸馏，以及四步生成加流式推理，在 832x480 分辨率下以 24 FPS 运行，估计服务器成本约每流分钟 0.009 美元；在 158 个 WBench Navigation 用例上取得总分 81.0 和一致性 88.5。

## 正文

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 trained on connected multi-prompt videos to supervise a block-level causal student through distribution-matching distillation; and (3) Low-cost real-time interaction, combining four-step generation with context-preserving streaming to support 832 x 480 inference at 24 FPS at an estimated server rental cost of approximately USD 0.009 per stream-minute.

Zing-0.5 achieves an overall score of 81.0 and a consistency score of 88.5 across 158 WBench Navigation cases. A joint-control demonstration shows a text-directed event change during continued navigation without restarting generation. We release the model weights, inference code, and Zing-SGLang serving implementation to support further work on playable generated worlds.