Nvidia's Octi shifts dexterous manipulation to sim-based RL, academia rejoices
KyleMorgenstein · x · 2026-10-14
Kyle Morgenstein called Nvidia Octi + Abhishek's lab collaboration a "generational run," arguing dexterous manipulation will be solved in simulation.
Jerry Cheng added it's the best academia news of the week: labs no longer need to compete on the incalculable cost of training WAM and can refocus on RL for dexterity — with the recipe also promising better handling of low-level motor skills. He called for more papers on better simulation and sampling.
More from Embodied
- Ukrainian FPV Drone Sim Leaves Early Access, Players Generate Training Data — generativist · 2026-10-14
- Menlo Research teases mystery robotics kit build in new photo — victormustar · 2026-10-14
- China's Hesai launches spatial camera to boost AI-powered robotics — pstAsiatech · 2026-10-14
- Nvidia's TacitVLA matches CoT performance at up to 3.4x lower latency — arankomatsuzaki · 2026-10-14
- $3,500 Flourish 1 Home Robot Uses a Raspberry Pi and Learns Chores From Your Phone — Matt Wolfe · 2026-10-14
- SlashVibe, a physical controller for AI agents, hits Kickstarter October 27 — sujingshen · 2026-10-14