精选理由
小米用10万小时人造数据训练机器人，发现加数据比加参数更管用，虽然成功率还不高，但这路子值得关注。
小米训练Xiaomi-Robotics-1时使用了超过100,000小时的人类手持相机采集的运动数据，而非机器人自身数据。结果表明，增加数据量对性能的提升远超扩大模型参数规模。目前性能增长尚未出现饱和，但绝对成功率仍然较低。这项研究挑战了机器人领域“更大模型更优”的常规假设。
原文 · Decoder
Xiaomi-Robotics-1 shows that more data beats bigger models when training robots to move
Xiaomi trained Xiaomi-Robotics-1 on more than 100,000 hours of motion data collected by people using camera-equipped handheld grippers rather than robots. Adding data improved performance far more than increasing model size. The gains haven't plateaued, though absolute success rates remain low. The article Xiaomi-Robotics-1 shows that more data beats bigger models when training robots to move appeared first on The Decoder .