谢赛宁发布 Solaris：Minecraft 多人视频世界模型
world modeling is never about rendering pixels.
谢赛宁（Saining Xie）发布 Project Solaris，一个在 Minecraft 中构建多人视频世界模型的新项目。发布包含三部分：Solaris Engine 多人数据采集系统、Solaris Model（采用内存高效 self forcing 设计的多人 DiT，基于 1260 万帧协作 Minecraft 游戏画面训练）、以及用 VLM 作为评判者评估多人能力的 Solaris Eval。
查看原帖📢Current world models aren't really modeling the world; they're modeling one agent's view of it. Partial observations ≠ world state. Future world models will be independent of any one agent's perspective. You will be able to “drop in” any number of agents at any point in time, and a persistent world state will evolve with their interactions. Imagine a…
展开完整原文
📢Current world models aren't really modeling the world; they're modeling one agent's view of it. Partial observations ≠ world state. Future world models will be independent of any one agent's perspective. You will be able to “drop in” any number of agents at any point in time, and a persistent world state will evolve with their interactions. Imagine a neural MMORPG server. 🧵[1/10]
正文
当前显示原文，中文全文译文尚未就绪。
world modeling is never about rendering pixels.
rendering is local. world state is global. as soon as more than one agent exists, the only thing that truly matters is the shared representation beneath individual views. that shared representation is what scales into collective capability.
this is why I'm super excited to share project Solaris -- our new work focused on building a multiplayer video world model in minecraft.
This release includes three main pieces. 1⃣Solaris Engine, a fully featured multiplayer data collection system with built in visuals. the team put a huge amount of work into this since nothing like it really exists yet. https://t.co/dw9lTmr9Pk 2⃣Solaris Model, a multiplayer DiT with a new memory efficient self forcing design, trained on 12.6M frames of coordinated Minecraft gameplay. https://t.co/cVjlGKcNUf 3⃣Solaris Eval, which uses a VLM as a judge to evaluate different multiplayer capabilities.