Tongzhou Mu 🤖🦾🦿(@tongzhou_mu):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. 🧵

Tongzhou Mu 🤖🦾🦿

@tongzhou_mu

Scaling video world models for robots @RhodaAI | Built 1st version of ManiSkill | Prev @UCSanDiego @1x_tech @NVIDIA @MSFTResearch

加入 January 2017

998 正在關注 3.7K 粉絲

Tongzhou Mu 🤖🦾🦿@tongzhou_mu

2026.09.10 15:46

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. 🧵