Solaris: Building a Multiplayer Video World Model in Minecraft
Georgy Savva Oscar Michel Daohan Lu Suppakit Waiwitlikhit Timothy Meehan Dhairya Mishra Srivats Poddar Jack Lu Saining Xie
作者信息
Abstract
Existing action-conditioned video generation models (video world models) are limited to single-agent perspectives, failing to capture the multi-agent interactions of real-world environments. We introduce Solaris, a multiplayer video world model that simulates consistent multi-view observations. To enable this, we develop a multiplayer data system designed for robust, continuous, and automated data collection on video games such as Minecraft. Unlike prior platforms built for single-player settings, our system supports coordinated multi-agent interaction and synchronized videos + actions capture. Using this system, we collect 12.64 million multiplayer frames and propose an evaluation framework for multiplayer movement, memory, grounding, building, and view consistency. We train Solaris using a staged pipeline that progressively transitions from single-player to multiplayer modeling, combining bidirectional, causal, and Self Forcing training. In the final stage, we introduce Checkpointed Self Forcing, a memory-efficient Self Forcing variant that enables a longer-horizon teacher. Results show our architecture and training design outperform existing baselines. Through open-sourcing our system and models, we hope to lay the groundwork for a new generation of multi-agent world models.引用本文复制引用
Georgy Savva,Oscar Michel,Daohan Lu,Suppakit Waiwitlikhit,Timothy Meehan,Dhairya Mishra,Srivats Poddar,Jack Lu,Saining Xie.Solaris: Building a Multiplayer Video World Model in Minecraft[EB/OL].(2026-02-26)[2026-02-28].https://arxiv.org/abs/2602.22208.学科分类
计算技术、计算机技术
|国家预印本平台
评论