๊ฐ€์ž… ํ›„ ์ดˆ๋Œ€ ๋งํฌ๋ฅผ ๊ณต์œ ํ•˜๋ฉด ๋™์˜์ƒ ์žฌ์ƒ ๋ฐ ์ดˆ๋Œ€ ๋ณด์ƒ์„ ๋ฐ›์„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

Tongzhou Mu ๐Ÿค–๐Ÿฆพ๐Ÿฆฟ
@tongzhou_mu
Scaling video world models for robots @RhodaAI | Built 1st version of ManiSkill | Prev @UCSanDiego @1x_tech @NVIDIA @MSFTResearch
๊ฐ€์ž… January 2017
998 ํŒ”๋กœ์ž‰ ์ค‘    3.7K ํŒฌ
Does scaling pre-training on general web video improve a complex manipulation task in real deployment? We scale model size and pre-training compute, and test on one industrial task. Yes. The better a pre-trained model predicts web video, the better its post-trained policy. ๐Ÿงต
๋” ๋ณด๊ธฐ