Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control

Researchers released Zing-0.5, a 5B autoregressive world model that supports joint keyboard and online text control for real-time playable generated worlds, according to the arXiv paper 2609.17909v1. Zing-0.5 scores 81.0 overall and 88.5 on consistency across 158 WBench Navigation cases, and runs 832 x 480 inference at 24 FPS for an estimated server rental cost of about USD 0.009 per stream-minute using four-step generation with context-preserving streaming. The team released the model weights, inference code, and Zing-SGLang serving implementation.

arXiv:2609.17909v1 Announce Type: new 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. 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.