5 citations · 6 across the 3 of their papers we have counts for
3 papers · 1 filter
Pre-training Visual Dexterity in Simulation
Sarthak Kamat, Adam Rashid, Satvik Sharma +4
Large-scale pre-training has made robot policy fine-tuning increasingly data-efficient, but this progress has largely been driven by datasets and embodiments built around simple pa…
Learning Humanoid Locomotion over Challenging Terrain
Ilija Radosavovic, Sarthak Kamat, Trevor Darrell +1
Humanoid robots can, in principle, use their legs to go almost anywhere. Developing controllers capable of traversing diverse terrains, however, remains a considerable challenge. C…
Humanoid Locomotion as Next Token Prediction
Ilija Radosavovic, Bike Zhang, Baifeng Shi +5
We cast real-world humanoid control as a next token prediction problem, akin to predicting the next word in language. Our model is a causal transformer trained via autoregressive p…