FuguReport

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

Authors Jiaming Zhou, Qihang Zhang, Gangwei Xu, Cunxin Fan, Yujie Zhao, Ruilin Wang, Yiming Luo, Shuai Yang, Xing Zhu, Yujun Shen, Junwei Liang, Yinghao Xu
Affiliations Robbyant / The Hong Kong University of Science and Technology (Guangzhou) / The Hong Kong University of Science and Technology
Categories Method / Video Action Modeling / In-context causal modeling from videos, Application / Robotic Task Generalization / Open-ended task execution using video guidance, Evaluation / Task Performance Evaluation / Success rate on unseen RoboTwin tasks
License CC BY 4.0

Abstract Overview

This paper frames zero-shot cross-task robotic manipulation as an in-context learning problem, where an unseen task is specified at deployment time by a human demonstration video rather than only by language. The authors propose Zero-WAM, a causal video-action model that predicts future robot video chunks and aligned actions while conditioning on either language or human-video prompts. To make such training scalable, they introduce HumanGen, an automatically generated dataset of 74.2K human-robot in-context pairs spanning 8.6K tasks, together with task-balanced robotic pretraining data sampled at the task level. They also add an in-context future chunk prediction objective to reduce shortcut learning from seen-task robot histories and encourage use of the human-video prompt.

Novelty

The distinctive contribution is the use of human videos as in-context task specifications for zero-shot robotic task generalization within a single causal world-action model. The work also introduces an automatic pipeline for generating large-scale semantically matched human-robot pairs and an auxiliary future-chunk prediction objective designed specifically to make the model rely more on the in-context video.

Results

In RoboTwin 2.0 simulation, Zero-WAM achieves a 46.95% average success rate across seven unseen tasks, improving over LingBot-VA by 29.50 percentage points and over a Wan-based baseline by 35.97 points. In real-world evaluations on unseen task configurations, it reaches 53.3% success for object-to-container placement, 33.3% for three-object sequential manipulation, and 16.7% for two-table-leg insertion, outperforming the language-conditioned LingBot-VA baseline in all three settings.

Key Points

  1. Zero-WAM conditions robot execution on human demonstration videos as in-context task prompts, aiming to generalize to tasks not seen during robot training.
  2. The paper introduces HumanGen, a 74.2K-pair dataset across 8.6K tasks, built by automatically converting task-sampled robot trajectories into semantically matched human videos.
  3. An in-context future chunk prediction objective and task-balanced robotic pretraining are shown to improve unseen-task performance, including a 46.95% average success rate on seven unseen RoboTwin tasks.

References

This page was created using generative AI such as GPT-5, Claude Opus 4, Gemini 3, Gemini 3.1 Flash Image, and their higher-end successor versions. No guarantee can be made regarding its contents.