NVIDIA Introduces ADEPT: Pre-training Dexterity for Faster Robot Downstream Learning
KyleMorgenstein · x · 2026-08-21
NVIDIA's Dex team introduces ADEPT, a pre-training and post-training paradigm. It uses RL entirely in simulation to acquire dexterity once, then reuses it to learn downstream tasks much faster via zero-shot deployment of visuo-tactile policies in the real world.
Related event: NVIDIA Unveils ADEPT: Dexterity Pretraining Speeds Up Robot Learning by 3x(3 posts)→
More from Embodied
- Volvo and NVIDIA expand partnership to bring safe automated driving to next-gen cars — nvidia · 2026-10-16
- Tevel's robotic system harvests fruit around the clock using computer vision — LexiLove · 2026-10-16
- SHOES: 10 minutes of real-robot RL lets quadrupeds walk in shoes, CoRL 2026 paper — kscottz · 2026-10-16
- Tesla Cybercab robotaxis logged zero crashes in first two weeks of public rides, NHTSA data shows — elonmusk · 2026-10-16
- Robotics LLMs tested on 16 tasks: GPT-6 Astra hits 17.2% success vs Fable's 9.1% — pabbeel · 2026-10-16
- WEDGE paper generates training environments conditioned on navigation agent failures — _akhaliq · 2026-10-16