外观
论文HF Daily Papers · arXiv 2610.279148 天前
ConfigWM：任务条件感知世界模型规划成功率提升22.3%
本文由 AI 根据公开内容整理，可能有误，请以原文为准：World Models with Configurable Perception（HF Daily Papers · arXiv 2610.27914）
核心内容
针对真实世界观测噪声大且含大量任务无关信息导致现有世界模型编码器易受干扰的问题，研究提出ConfigWM框架。该方法利用任务语言描述作为配置信号，引导视觉嵌入映射至任务特定状态空间，选择性保留相关信息并抑制无关变化。实验显示，在干扰递增环境中，ConfigWM规划成功率平均比最强竞品高22.3%，且在物理量探测与抗扰检索指标上显著领先。
技术层面，ConfigWM核心在于任务条件状态提取机制，将语言指令转化为调节视觉表征的调制信号，使状态空间动态适配当前任务需求，随后在该空间内学习动作条件动力学用于规划。量化评测表明，其物理量探测Pearson相关系数提升0.365，从干扰场景到干净场景的检索准确率提升75.5%，证明模型能有效解耦任务相关特征与环境噪声，支撑具身智能体在复杂非结构化环境下的可靠建模与决策。
关键看点
- 任务条件感知：以语言描述为配置信号 steer 视觉嵌入映射，构建任务特定状态空间以抑制无关噪声
- 规划性能突破：在多级干扰环境中保持稳定性，平均规划成功率较最强竞争方法提升22.3%
- 状态表征验证：物理量探测Pearson r增加0.365，干扰至干净检索准确率提升75.5%，证实特征解耦有效性
- 动力学建模：在任务特定状态空间中学习动作条件动力学，支持噪声环境下的鲁棒规划与决策
工程与产业观察
ConfigWM证明了语言引导的可配置感知是解决具身智能体在开放世界抗噪难题的有效路径。通过将语义意图注入状态编码过程，实现了表征层面的任务自适应，为机器人在非结构化、高干扰环境中的Sim-to-Real迁移及长程规划提供了新的算法范式与工程参考。
英文摘要 (Abstract)
Real-world observations are noisy and often contain excessive task-irrelevant information. Effective world modeling and planning need to abstract observations into world state representations while filtering out irrelevant information. However, encoders in existing world models are typically non-adaptive, leading to state representations that are easily distracted by task-irrelevant information. As a result, the model may not selectively filter observations to cater to different task demands. To address this problem, we introduce ConfigWM, which realizes configurable perception through task-conditioned state extraction. Given a language description of the task at hand, ConfigWM uses it as a configuration signal to steer how visual embeddings are mapped into a task-specific state space, selectively preserving information relevant to the current task while suppressing task-irrelevant variations. Action-conditioned dynamics are then learned in this task-specific state space for planning. We evaluate ConfigWM in environments with increasing levels of distraction. While existing methods exhibit substantial declines in planning success rate as the environments become increasingly noisy, ConfigWM remains comparatively stable and outperforms the strongest competing method by 22.3% on average across diverse environments. Consistent gains in physical-quantity probing (+0.365 Pearson r) and distracted-to-clean retrieval (+75.5%) further indicate that ConfigWM learns states that preserve task-relevant information while remaining robust to distractors, supporting reliable world modeling and planning in noisy worlds. Project Page: https://configwm.github.io
Hugging Face Daily Papers 热度：2 upvotes 作者：Yijun Shen, Delong Chen, Xianming Hu, Kai Zhang, Pascale Fung
来源
本页事实对应的公开页面，以原文为准。