Yude Zou, Yifei Yao, Guanbo Jiao, Jianming Ma, Guanjie Zheng, Xing Gao · 2026 · arXiv
DOI: 10.48550/arXiv.2610.26813 · open-access PDF
세계 행동 모델(WAMs)은 미래의 비디오를 공동으로 예측하고 행동을 생성하지만 작업과 관련이없는 시각적 방해, 즉 로봇 행동에 영향을 미치지 않는 시각적 외모의 변화에 민감하다.우리는 전통적인 WAM 훈련의 격차를 확인합니다 : 비디오 예측은 모양 정보를 보존하도록 표현을 장려하지만 액션 생성은 작업과 관련이없는 모양에 무변화를 명시적으로 강요하지 않습니다.데이터 증폭은 WAM을 그러한 방해에 노출시킵니다.
Machine translation (Meta M2M100); the English original follows.
World Action Models (WAMs) jointly predict future video and generate actions, yet remain sensitive to task-irrelevant visual perturbations, i.e., changes in visual appearance that should not affect robot behavior. We identify a gap in conventional WAM training: video prediction encourages representations to preserve appearance information, while action generation does not explicitly enforce invariance to task-irrelevant appearance. Data augmentation exposes WAMs to such perturbations but does not require perturbed and nominal observations to produce consistent action representations, and align
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26813, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange