arXiv：cs.AI· Thinker Team, Peng Gao, Jichao Jiao, Chen Liao, Daqin Luo, Yiming Ma, Baiyu Pan, Hailin Shi, Jiyuan Wang, Xiangming Xu, Xiongwei Zhao·· 6 小时前
Thinker-WM：面向具身智能的统一多模态世界模型
Thinker-WM: A Unified World Model with Shared Multimodal Representations for Embodied Intelligence
AI 导读
优必选 Thinker 团队提出统一多模态世界模型 Thinker-WM，通过共享的 Unified Dynamics Transformer 联合建模并生成 RGB、度量深度与机器人动作。模型训练数据约含 2 万小时第一视角视频、1 万小时真实机器人数据和 1 千小时仿真数据。Thinker-WM 在 EWMBench、WorldOlympiad 和 WorldArena 上排名第一。
正文
Authors:Thinker Team Ubtech: (Alphabetical order), Peng Gao, Jichao Jiao, Chen Liao, Daqin Luo, Yiming Ma, Baiyu Pan, Hailin Shi, Jiyuan Wang, Xiangming Xu, Xiongwei Zhao
Abstract:World models have emerged as a promising paradigm for embodied AI, yet existing systems often remain fragmented in the modalities they model and the functions they support. In particular, visual dynamics, geometric structure, and executable action are commonly coupled through separate interfaces or downstream modules rather than being jointly represented and evolved within a shared dynamics model. In this work, we present Thinker-WM, a unified multimodal world model that jointly models and generates RGB, metric depth, and robot action through a shared intermediate Unified Dynamics Transformer with modality-specific encoders and decoders. The model performs multimodal unification at the representation level: appearance, geometry, and action are transformed into a common dynamic representation and jointly evolved by shared parameters, while their distinct output structures are preserved. The same parameterization supports multiple functions, including joint video-action generation, world prediction, policy inference, action-conditioned generation, video-to-action generation, and inverse dynamics. To examine whether the shared representation captures action-related information, we introduce a lightweight motion probe that shows the frozen visual representation contains recoverable motion information. Thinker-WM is trained on a heterogeneous corpus comprising approximately 20K hours of egocentric video, 10K hours of real-robot data, and 1K hours of simulation data, including approximately 4K hours of real-robot data with aligned depth supervision. Extensive experiments demonstrate strong performance across embodied world-model evaluations. Thinker-WM ranks first on EWMBench, WorldOlympiad and WorldArena, while controlled studies further demonstrate the benefits of action conditioning, geometric interaction, and multi-function training within the shared representation.
| Comments: | Project page: this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO) |
| Cite as: | arXiv:2610.18447 [cs.AI] |
| (or arXiv:2610.18447v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18447 arXiv-issued DOI via DataCite |
Submission history
From: Baiyu Pan [view email]
[v1]
Tue, 13 Oct 2026 14:18:47 UTC (17,651 KB)
[v2]
Wed, 14 Oct 2026 05:41:05 UTC (17,631 KB)
来源：arXiv：cs.AI · arxiv.org