Yunhao Luo, He Wentao, Yinpei Dai, Hyelin Nam, Hongze Fu, Joyce Yue Chai, Nima Fazeli, Jeong Joon Park · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.30125 · cited by 0 works (OpenAlex) · open-access PDF
ومع ذلك، قد لا تظهر هذه الملاحظات خصائص الفيزياء التي تحدد ديناميكية التغيير، مثل توزيع الوزن للأشياء، التخفيف المشترك، أو التردد السطحي. دون تقييم هذه العوامل الفيزيائية للمنتجات العالمية، فإن التوقعات ترغب في التراجع إلى نقطة ما قبل الأبحاث الفلسفية وتأثيرها السلبية في قصص اختبارات جديدة. لهذا الغرض، نحن نقدم PhysiCalWorld، الذي تقييم نموذج العالم المرتبط بالعمل إلى نموذج الفلسفة الفلسفية المرتبطة بالفيزياء المرتبطة بالفيزياء المرتبطة بالفيزياء المرتبطة بالفيزياء المرتبطة بالفيزياء المرتبطة بالفيزياء المرتبطة بال
Machine translation (Meta M2M100); the English original follows.
Existing world models typically perceive a scene through current visual frame or a narrow history window. However, these observations may not reveal the physics properties that determine transition dynamics, such as an object's mass distribution, joint damping, or surface friction. Without calibrating these physics factors for world models, predictions tend to regress toward an empirical prior and induce severe drift in novel test scenes. To this end, we propose PhysiCalWorld, which calibrates action-conditioned world models to the instance-specific dynamics via in-context prompting, without fine-tuning or analytical physics modeling. Our method encodes an exploratory interaction clip collected within the test scene into a compact physics descriptor token, which grounds subsequent predictions in the scene's actual physical behavior. PhysiCalWorld is trained end-to-end with the latent prediction loss alone, without physics labels. At inference time, the descriptor token is extracted once and can be reused across rollouts with negligible compute overhead. We evaluate PhysiCalWorld across four environments covering diverse physics variations and show that it substantially improves rollout prediction accuracy and visual planning success rate. The learned descriptors also form a physically structured latent space and generalize beyond the physics ranges seen during training.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Inference, Calibration, Physics beyond the Standard Model, Physics, Computer science, Space (punctuation)
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.30125, 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