{"ID":2835065,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.00287","arxiv_id":"2512.00287","title":"RealAppliance: Let High-fidelity Appliance Assets Controllable and Workable as Aligned Real Manuals","abstract":"Existing appliance assets suffer from poor rendering, incomplete mechanisms, and misalignment with manuals, leading to simulation-reality gaps that hinder appliance manipulation development. In this work, we introduce the RealAppliance dataset, comprising 100 high-fidelity appliances with complete physical, electronic mechanisms, and program logic aligned with their manuals. Based on these assets, we propose the RealAppliance-Bench benchmark, which evaluates multimodal large language models and embodied manipulation planning models across key tasks in appliance manipulation planning: manual page retrieval, appliance part grounding, open-loop manipulation planning, and closed-loop planning adjustment. Our analysis of model performances on RealAppliance-Bench provides insights for advancing appliance manipulation research","short_abstract":"Existing appliance assets suffer from poor rendering, incomplete mechanisms, and misalignment with manuals, leading to simulation-reality gaps that hinder appliance manipulation development. In this work, we introduce the RealAppliance dataset, comprising 100 high-fidelity appliances with complete physical, electronic...","url_abs":"https://arxiv.org/abs/2512.00287","url_pdf":"https://arxiv.org/pdf/2512.00287v1","authors":"[\"Yuzheng Gao\",\"Yuxing Long\",\"Lei Kang\",\"Yuchong Guo\",\"Ziyan Yu\",\"Shangqing Mao\",\"Jiyao Zhang\",\"Ruihai Wu\",\"Dongjiang Li\",\"Hui Shen\",\"Hao Dong\"]","published":"2025-11-29T02:55:20Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\",\"cs.CV\"]","methods":"[\"Language Model\"]","has_code":false}