AI Summary
Xiaomi's Robotics-1 model demonstrates that scaling training data significantly outperforms simply increasing model size, achieving this through over 100,000 hours of motion data collected via human-operated camera-equipped grippers. While the performance improvements from additional data show no signs of plateauing, the model's absolute success rates remain relatively low, suggesting room for substantial future improvements.
From the source
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.
The full text couldn't be loaded here (the source may require a subscription).
View original at The Decoder