Waypoint-1.5：面向消费级硬件的实时视频世界模型
Waypoint-1.5: A Real-Time Video World Model for Consumer Hardware
浏览论文内容
中文总结 AI 辅助
Waypoint 1.5是面向消费级硬件的实时扩散世界模型，基于10万小时游戏数据预训练，支持键盘鼠标输入生成可玩游戏视频，并通过延迟和吞吐量评估交互性。
中文摘要 AI 辅助
我们提出了Waypoint 1.5，一个用于在消费级硬件上进行交互式视频生成的实时扩散世界模型。与通用视频扩散模型不同，交互式世界模型（iWMs）必须在严格的延迟和吞吐量约束下响应用户的密集控制。Waypoint 1.5在来自数百个游戏的10万小时多样化、控制对齐的视频游戏数据上进行了预训练，并生成以完整键盘和鼠标输入为条件的可玩游戏视频。该模型包含两个分辨率变体，可在广泛的消费级硬件上运行。为了刻画这一独特设置，我们区分了渲染FPS、潜在FPS和控制率。我们描述了Waypoint 1.5背后的数据管道、架构、训练方法和运行时系统。我们通过延迟和吞吐量来评估交互性。最后，我们讨论了iWMs特有的安全与伦理考量。
英文摘要
We present Waypoint 1.5, a real-time diffusion world model for interactive video generation on consumer-grade hardware. Unlike general video diffusion models, interactive world models (iWMs) must respond to dense user controls under strict latency and throughput constraints. Waypoint 1.5 is pre-trained on 100,000 hours of diverse, control-aligned video game data across hundreds of games, and generates playable video conditioned on full keyboard and mouse input. The model includes two resolution variants that run across a wide spectrum of consumer hardware. To characterize this unique setting, we distinguish rendered FPS, latent FPS, and control rate. We describe the data pipeline, architecture, training methodology, and runtime system behind Waypoint 1.5. We evaluate interactivity through latency and throughput. Finally, we discuss the safety and ethics considerations unique to iWMs.
发表机构
- Overworld
- HuggingFace
机构由 AI 辅助整理，请以论文原文为准。
