Zero-WAM看視頻幹活

Papers arxiv:2608.

26103 Copy markdown Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization Published on Aug 26 · Submitted by Yujie Zhao on Aug 28 · Robbyant Research Upvote 17 +9 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 Abstract Zero-WAM enables robotic manipulation of unseen tasks by conditioning a causal video-action model on in-context human video guidance, supported by an automatically generated dataset and a future-chunk prediction objective.

Generated by thinkingmachines/Inkling-Small Zero-shot cross-task generalization, where a policy must execute manipulation tasks never seen during training, remains a central challenge in robot learning.

In large language models, a novel task can be performed simply by specifying it in the context, without any parameter update.This form of in-context learning (ICL) turns generalization into a problem of task specification.

To achieve cross-task generalization, we bring this paradigm to robotic manipulation, and argue that the natural task specification for manipulation is a human video: unlike language, it provides rich visual cues about the intended task evolution.

We present Zero-WAM, a causal video-action model that executes unseen tasks by following in-context human video guidance.

To address the scarcity of task-rich paired human-robot data, we propose an automatic pipeline that converts task-sampled robot trajectories into semantically matched human videos, yielding HumanGen, a dataset of 74.2K human-robot ICL pairs across 8.6K tasks.

For model training, we further introduce an in-context future chunk prediction (IFP) objective that suppresses shortcuts learned from seen tasks and forces the policy to draw task information from the video prompt.On seven unseen tasks in RoboTwin 2.0 simulation, Zero-WAM achieves a 47.

0% average success rate, an absolute improvement of 29.5 percentage points over the strongest video-action baseline.

In real-world evaluations, it follows human video guidance to generalize to unseen task configurations involving multi-object scenes, long-horizon manipulation, and fine-grained insertion.

View arXiv page View PDF Project page GitHub 158 Add to collection Community HomieZ Paper submitter 2 days ago Webiste: https://robbyant-research.github.io/Zero-WAM Code: https://github.com/robbyant-research/Zero-WAM Paper: https://arxiv.org/abs/2608.

26103 Reply librarian-bot 1 day ago This is an automated message from the Librarian Bot.I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API Native Video-Action Pretraining for Generalizable Robot Control (2026) WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time (2026) WorldScape Policy 2.

0: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory (2026) JoyAI-RA 0.5: Scaling Robot Manipulation Learning via Dual Action Alignment (2026) DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulation (2026) GigaWorld-Policy-0.

5: A Faster and Stronger WAM Empowered by AutoResearch (2026) StageWAM: Joint-Embedding Stage Prediction for World-Action Models in Robot Manipulation (2026) Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend Reply EditPreview Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images Comment · Sign up or log in to comment Upvote 17 +5 Get this paper in your agent: hf papers read 2608.26103 Don't have the latest CLI?curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0 No model linking this paper Cite arxiv.org/abs/2608.

26103 in a model README.md to link it from this page.Datasets citing this paper 0 No dataset linking this paper Cite arxiv.org/abs/2608.26103 in a dataset README.md to link it from this page.Spaces citing this paper 0 No Space linking this paper Cite arxiv.org/abs/2608.26103 in a Space README.

md to link it from this page.Collections including this paper 2