Zhuohao Li, Jiawei He, Yuxuan Yan, Lang Zhou, Yinghao Li, Yanrui Li, Tianyu Zhang, Yi-Yang Song · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28431 · open-access PDF
World-Action Models (WAMs) telah muncul sebagai paradigma yang menjanjikan untuk kebijakan generalist yang dipenuhi dengan memodelkan evolusi dunia masa depan dan tindakan robot melalui berbagai tugas manipulasi. Namun, mewakili masa depan yang beragam hanyalah langkah pertama: WAM yang mampu juga harus menghasilkan masa depan yang sesuai dengan persyaratan tugas saat ini dan kemajuan eksekusi. Dalam manipulasi cakrawala panjang di mana segmen observasi-aksi serupa terjadi di berbagai tugas dan tahap, pendekatan yang ada dapat menghasilkan peluncuran lokal yang masuk akal namun disesuaikan untuk mendorong ke tahap tugas yang salah, yaitu, ph.
Machine translation (Meta M2M100); the English original follows.
World-Action Models (WAMs) have emerged as a promising paradigm for embodied generalist policies by jointly modeling future world evolution and robot actions across diverse manipulation tasks. However, representing diverse futures is only the first step: a capable WAM must also generate futures that match the requirements of the current task and execution progress. In long-horizon manipulation where similar observation-action segments occur across different tasks and stages, existing approaches may generate locally plausible yet misdirected rollouts to drift toward wrong task stage, i.e., a ph
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=2610.28431, 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