Tag · 3 articles

#dexterous manipulation

Nov 9, 2026

NVIDIA invests in RLWRLD as the Korean startup releases DexBench, a 15-task test for humanoid hands built on NVIDIA's simulator

NVIDIA said on Nov. 9 it will invest directly in Seoul's RLWRLD, which the same day showed DexBench, a dexterity benchmark that runs on Isaac Lab-Arena. The stake buys NVIDIA a say in where robot hands get graded, not just another model maker.

Nov 9, 20262 min readSources verified

2 min readSources verified

Nov 9, 2026

Dexterous Hands & Hardware

Ant Group's Robbyant open-sources LingBot-Touch, a touch model that lifts four robot policies by 14 to 26 points

Robbyant's tactile encoder, trained on nearly 5,000 hours from three kinds of fingertip sensors, raised average success on 26 real two-arm tasks for π0.5, LingBot-VLA and two other policies. Feeding the same policies raw touch data helped half as much, and sometimes hurt.

Nov 9, 20262 min readSources verified

2 min readSources verified

Nov 5, 2026

Embodied AI & Foundation Models

Panasonic's T-Rex adds fast fingertip touch to a robot model and nearly doubles success on 12 contact tasks

T-Rex, built by Panasonic with UC Berkeley, NVIDIA and Stanford researchers, reached 65% on 12 contact-heavy tasks against 35% for the best earlier method. Without touch it scored 42%.

Nov 5, 20262 min readSources verified

2 min readSources verified