Research map / Vision-language and multimodal / Robot action and navigation
RealAppiance: Let High-fidelity Appliance Assets Controllable and Workable as Aligned Real Manauls
Yuzheng Gao, Yuxing Long, Lei Kang, Yuchong Guo, Ziyan Yu, Shangqing Mao, Jiyao Zhang, Ruihai Wu, Dongjiang Li, Hui Shen, Hao Dong
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| proprietary MLLMs vs open-source MLLMs | MLLMs · RealAppliance-Bench Task 1 | F1 (%): GPT-5 80.89 vs Qwen3-VL 235B Thinking 80.06; GLM-4.5V 73.94 | Improved |
| use embodied planning model (RoboBrain 2.0-7B) instead of general MLLM | MLLM · RealAppliance-Bench Task 1 | Recall (%): 86.50 -> 5.78 | Hurt |
| use Gemini/GPT proprietary MLLMs for open-loop planning | MLLMs · RealAppliance-Bench Task 2 | task success rate (%): GPT-5 1.22; Gemini 2.5 Flash 2.65 | No clear effect |
| use general MLLM for part grounding | GPT-5 · RealAppliance-Bench Task 3 | average IoU (%): 12.15 (mAP 8.59) | No clear effect |
| full-process chained inference | MLLMs · RealAppliance-Bench Task 5 | task success rate (%): GPT-5 0.00; ApBot 0.92 | Hurt |
| compare embodied RoboBrain 2.0-7B on closed-loop adjustment | RoboBrain 2.0-7B · RealAppliance-Bench Task 4 | step-wise success rate (%): 31.77 vs GPT-5 29.61 | No clear effect |
Closest papers by meaning
- CheckManual: A New Challenge and Benchmark for Manual-based Appliance Manipulation (CVPR 2025 · similarity 0.90)
- ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks (ICLR 2025 · similarity 0.83)
- GENMANIP: LLM-driven Simulation for Generalizable Instruction-Following Manipulation (CVPR 2025 · similarity 0.82)
- DynScene: Scalable Generation of Dynamic Robotic Manipulation Scenes for Embodied AI (CVPR 2025 · similarity 0.82)
- Scaffolding Dexterous Manipulation with Vision-Language Models (NeurIPS 2025 · similarity 0.82)
- PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation (NeurIPS 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
