arXiv AI

CSWAM: Better Causal Semantic Representations for Out-of-Distribution Generalization in World Action Models

The paper introduces CSWAM, a Causal Semantic World Action Model that enhances FastWAM by integrating a causal semantic expert based on V-JEPA 2.1. This expert provides temporally grounded, appearance‑agnostic representations of semantic state changes and motion, leveraging sparse observation history and causal attention to improve action‑only inference. Experiments on simulation and real‑robot tasks show that CSWAM significantly boosts out‑of‑distribution generalization, raising success rates from 10.16% to 45.18% on RoboTwin 2.0 and from 27.5% to 70.0% across real‑robot tasks.

arXiv Computer Vision
Aug 27

Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization

Zero-WAM introduces a causal video-action model that enables robots to perform unseen manipulation tasks by following in-context human video guidance. The authors create HumanGen, a dataset of 74.2K human-robot ICL pairs across 8.6K tasks, and propose an in-context future chunk prediction objective to prevent shortcut learning. In simulation, Zero-WAM attains a 47.0% success rate on seven unseen tasks, outperforming the best video-action baseline by 29.5 percentage points, and demonstrates real‑world generalization to complex, long‑horizon, and fine‑grained tasks.

By Jiaming Zhou, Qihang Zhang, Gangwei Xu, Cunxin Fan, Yujie Zhao, Ruilin Wang, Yiming Luo, Shuai Yang, Xing Zhu, Yujun Shen, Junwei Liang, Yinghao Xu
arXiv AI
Aug 25

Act with Intent: Distilling Behavior Intent for Vision-Language-Action Models

The paper introduces Intention Distillation (INDI), a method that injects behavior-level intent into Vision‑Language‑Action (VLA) model decoders by leveraging a frozen teacher vision‑language model to interpret demonstrations. During training, the teacher processes the current observation, instruction, coarse action summary, and execution video, producing a multimodal intent representation that the VLA decoder uses alongside trajectory and execution features to predict actions. Experiments on SimplerEnv‑Bridge, RoboCasa Kitchen, and real‑world tasks show that INDI consistently improves success rates, especially on longer‑horizon tasks, demonstrating that explicit modeling of semantic intent benefits action decoders.

By Sangoh Lee, Sangwoo Mo, Wook-Shin Han