---
title: "PlayGen2: Learning Real-Time Playable Worlds with Explicit 3D State"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.07867v1"
permalink: "https://feed.astralor.com/items/itm_42f9b3bf25d8afa36c1f9e0a"
published: "2026-11-05T11:45:25.000Z"
score: 62
channel: "tech"
tags: ["推理效率","多模态","PlayGen2","Learning Real-Time Playable","Worlds","Explicit","State Building","Using"]
---

# PlayGen2: Learning Real-Time Playable Worlds with Explicit 3D State

## 速览

Building a playable world requires more than generating plausible video: it demands responsive control, persistent spatial structure, and coherent interactions with dynamic entities. Using generated frames as the sole r…

## 关键点

- Building a playable world requires more than generating plausible video: it demands responsive control, persistent spatial structure, and coherent interactions with dynamic entities.
- Using generated frames as the sole recurrent world representation ties these requirements to view-dependent appearance synthesis, making it difficult to maintain long-term spatial and temporal consistency in generation …
- We present PlayGen2, a real-time interactive world model that separates learned 3D state evolution from neural rendering.

## 全文

Building a playable world requires more than generating plausible video: it demands responsive control, persistent spatial structure, and coherent interactions with dynamic entities. Using generated frames as the sole recurrent world representation ties these requirements to view-dependent appearance synthesis, making it difficult to maintain long-term spatial and temporal consistency in generation and interaction. We present PlayGen2, a real-time interactive world model that separates learned 3D state evolution from neural rendering. PlayGen2 maintains a persistent world memory comprising static geometry represented by a volumetric occupancy grid and identity-indexed 3D states for the player and other entities. Within a fixed-size local region, its world-state model jointly learns action-conditioned entity dynamics, geometry completion, and entity discovery, committing updates to a persistent world memory. A separate neural renderer synthesizes first-person observations from depth and semantic projections of the world state, without feeding generated images back into state prediction. Using Doom as a testbed, we demonstrate that the model successfully learns world dynamics including geometry-aware player motion and player--NPC interactions. The framework is computationally efficient, enabling the complete simulation and rendering pipeline to achieve approximately 160ms backend latency on a MacBook Pro with an M4 Pro chip. Beyond single-player interaction, we demonstrate zero-shot deployment on unseen Doom maps, multiplayer interaction through the composition of single-player models, and programmable gameplay through rule-based state interventions. These capabilities demonstrate the transferability and extensibility of the learned game-world model. Code and pretrained model weights are publicly available.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_42f9b3bf25d8afa36c1f9e0a