Papers
arXiv:2509.21790

LongScape: Advancing Long-Horizon Embodied World Models with Context-Aware MoE

Published on Sep 26
Authors:
,
,
,
,
,
,

Abstract

LongScape combines intra-chunk diffusion denoising with inter-chunk autoregressive generation to achieve stable long-horizon video generation for embodied manipulation tasks.

AI-generated summary

Video-based world models hold significant potential for generating high-quality embodied manipulation data. However, current video generation methods struggle to achieve stable long-horizon generation: classical diffusion-based approaches often suffer from temporal inconsistency and visual drift over multiple rollouts, while autoregressive methods tend to compromise on visual detail. To solve this, we introduce LongScape, a hybrid framework that adaptively combines intra-chunk diffusion denoising with inter-chunk autoregressive causal generation. Our core innovation is an action-guided, variable-length chunking mechanism that partitions video based on the semantic context of robotic actions. This ensures each chunk represents a complete, coherent action, enabling the model to flexibly generate diverse dynamics. We further introduce a Context-aware Mixture-of-Experts (CMoE) framework that adaptively activates specialized experts for each chunk during generation, guaranteeing high visual quality and seamless chunk transitions. Extensive experimental results demonstrate that our method achieves stable and consistent long-horizon generation over extended rollouts. Our code is available at: https://github.com/tsinghua-fib-lab/Longscape.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2509.21790 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2509.21790 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2509.21790 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.