无需专家示范即可生成运动技能反馈，让自动教练更实用。
AIDE: Automated Instruction via Distilled Expertise for Reference-Free Motor Skill Coaching
- 用教师模型从专家-学习者姿态对比中提炼反馈，学生模型仅靠学习者姿态生成反馈
- 在ExpertAF数据集上超越纯参考自由基线，接近需专家示范的方法性能
- 适合开发低成本、高可扩展的智能运动教学系统
生成自然语言的运动技能指导反馈可加速学习，但专家教练稀缺且成本高。现有基于参考的方法需在训练和推理时都依赖专家示范，限制了实际应用。我们提出AIDE（Automated Instruction via Distilled Expertise），该框架仅在训练阶段使用专家参考，在推理时仅凭学习者的姿态序列生成反馈。教师模型通过冻结的语言模型，从配对的学习者-专家姿态中学习生成反馈，输出学习者标记与差异标记，编码二者差异。学生模型继承教师的编码器和权重初始化，将显式的专家比较替换为仅基于学习者姿态的辅助模块，生成互补标记。在ExpertAF数据集上，AIDE在多数指标上优于参考自由基线，且性能接近需专家示范于训练与推理的方法，大型语言模型评估结果支持这些发现。
原文摘要 · Abstract (English)
Generating natural-language coaching feedback on motor skills can accelerate learning, yet expert coaches are scarce and expensive. Existing reference-based methods require expert demonstrations at both training and inference time, limiting practical deployment. We propose AIDE (Automated Instruction via Distilled Expertise), a framework that exploits expert references only during training and generates feedback from a learner's pose sequence alone at inference. A teacher model first learns to generate feedback from paired learner-expert poses via a frozen language model, producing separate learner tokens and difference tokens that encode the learner-expert difference. A student model then inherits the teacher's encoder and weight initialization, replacing the explicit expert comparison with an auxiliary module that produces complementary tokens from the learner's pose alone. On the ExpertAF dataset, AIDE outperforms reference-free baselines on most metrics and performs comparably to methods requiring expert demonstrations at both training and inference, with LLM-based evaluation supporting these findings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。