MetaFine 竞赛方案：可模仿的老师让 19M 小模型精细操作得分翻倍
Learning from an Imitable Teacher: Competition Solution for the MetaFine Challenge
CoRL 竞赛第二名团队公开方案：不微调 VLA，用 19M 小模型加改造过的示教数据就把分数做到 π₀ 的两倍多，做模仿学习的值得看看他们的踩坑细节。
Team Friday 在 CoRL 2026 的 MetaFine 精细操作竞赛中获得第二名，总分 0.947，是 π₀ 基线的两倍以上。方案没有微调大型 VLA 模型，而是为五个仿真任务各训练一个 19M 参数的策略，数据全部由仿真器中的特权脚本教师生成。分析失败回合后发现，几乎总能成功的教师反而教不好学生：停顿变成卡顿、固定习惯变成错误捷径。把教师改成可模仿的风格后，最难的字母插入任务得分从 0.44 提升到 0.82，最终达到 0.88，数据只多 32%。
Learning from an Imitable Teacher: Competition Solution for the MetaFine Challenge
The MetaFine Open Competition (RoboFineMani workshop, CoRL 2026) evaluates fine-grained manipulation beyond binary success. Its five simulated tasks, from grasping a bottle by an instructed part to inserting letter-shaped pegs with 4 mm clearance, are scored on perception under lighting and camera changes, instruction understanding, and behavior. This report presents Team Friday's solution, which got second place with an overall score of 0.947, more than twice the $π_0$ baseline. Instead of fine-tuning a large vision-language-action (VLA) model, we train one 19M-parameter policy per task with a separate instruction classifier and focus on the data, all generated in the simulator by a privileged scripted teacher, including its corrections of the student's mistakes. By analyzing failed episodes, we find that a teacher that almost always succeeds can still teach a memoryless student badly: its pauses become stalls, its fixed habits become shortcuts, and it never shows the errors the student makes. Making the teacher \emph{imitable} raised the official score on letter insertion, the hardest task, from 0.44 to 0.82 with 32\% more data and the same architecture, and finally to 0.88. We summarize practical lessons on demonstration data and evaluation, which we hope will help in imitation learning for precise manipulation.