paper-with-me

Papers

In-Context World Modeling for Robotic Control

2026-06-24 · Siyin Wang, Junhao Shi, Senyu Fei, Zhaoyang Fu, Li Ji, Jingjing Gong, Xipeng Qiu arxiv

Modern Vision-Language-Action (VLA) models often fail to generalize to novel setups, such as altered camera viewpoints or robot morphologies, because they are typically conditioned only on current observations and language instructions. By ignoring the underlying system configuration as a variable, these models implicitly assume a fixed execution context encountered during training, necessitating data-intensive fine-tuning for any new environment. In this work, we introduce In-Context World Modeling (ICWM), a framework that treats system identification as an in-context adaptation problem. ICWM enables robot policies to autonomously infer essential system variables from a short history of self-generated, task-agnostic interactions. Unlike traditional In-Context Learning that uses demonstrations to specify what task to perform, ICWM leverages the context window to understand how the system operates. By processing these interactions before task execution, the model implicitly captures the world dynamics of the current system, enabling adaptation to novel configurations without parameter updates. Extensive experiments in simulation and on real-world robot platforms demonstrate that ICWM significantly outperforms standard VLA baselines on novel camera viewpoints.

📄 PDF Abstract BibTeX arXiv:2606.26025

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

U-DiT Policy: U-shaped Diffusion Transformers for Robotic Manipulation

2025-09-29 · Linzhi Wu, Aoran Mei, Xiyue Wang, Guo-Niu Zhu 외 arxiv

Diffusion-based methods have been acknowledged as a powerful paradigm for end-to-end visuomotor control in robotics. Most existing approaches adopt a Diffusion Policy in U-Net architecture (DP-U), which, while effective,…

Spatial Policy: Guiding Visuomotor Robotic Manipulation with Spatial-Aware Modeling and Reasoning

2025-08-21 · Yijun Liu, Yuwei Liu, Yuan Meng, Jieheng Zhang 외 arxiv

Vision-centric hierarchical embodied models have demonstrated strong potential. However, existing methods lack spatial awareness capabilities, limiting their effectiveness in bridging visual plans to actionable control i…

Spatial ReasoningVideo Generation

WSA$_1$: a 3D-Centric World-Spatial-Action Model for Generalizable Robot Control

2026-07-04 · Jiahao Jiang, Jianing Zhang, Zhenhan Yin, Ruidong Chen 외 arxiv

Recent advances in embodied AI have established robot foundation models (RFMs) as the dominant approach for generalist robotic systems to date. By leveraging imitation learning on extensive robot demonstrations, RFMs hav…

Robust Robotic Control from Pixels using Contrastive Recurrent State-Space Models

2021-12-02 · Nitish Srivastava, Walter Talbott, Martin Bertran Lopez, Shuangfei Zhai 외

Modeling the world can benefit robot learning by providing a rich training signal for shaping an agent's latent state space. However, learning world models in unconstrained environments over high-dimensional observation …

State Space Models

Contextual Intelligence The Next Leap for Reinforcement Learning

2026-02-17 · André Biedenkapp arxiv

Reinforcement learning (RL) has produced spectacular results in games, robotics, and continuous control. Yet, despite these successes, learned policies often fail to generalize beyond their training distribution, limitin…

Reinforcement LearningContinuous Control