arXiv 2610.28827 · cs.CV · 2026-10-20
WorldStream: Streaming Interactive 3D Worlds with Hierarchical Planning and Persistent State
Xiaoxiao Ma, Weiyang Jin, Yanwen Ma, Haoran Li, Zhixiang Wei, Songchun Zhang, Yaowei Li, Junhao Zhuang and 6 more
Affiliation unverified
In latest · #330 Added on 2026-10-26
One-line takeaway
WorldStream is an open-ended 3D world model that extends playable terrain indefinitely, acts on open-ended language, and restores visited places with edits, using a macro/micro hierarchical planner compiled into terrain and entities by deterministic code.
WorldStream 是开放式 3D 世界模型，能把可玩地形无限延伸、按开放语言指令改动世界，并在回访时恢复带编辑的场景；它用宏观加微观的分层规划器，再由确定性代码编译成地形、道路和实体。
Read on arXiv PDF Hugging Face discussion Code Project page
Topics & disciplines
More on Visual generation
- StreamEval: Evaluating Interactive Streaming Video Generation Models ▲649
- MaLiang-Harness: A Programmable Path to Image and Video Generation ▲367
- Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation ▲364
- DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models ▲325
- Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation ▲200
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-26.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.