Multimodal Reinforcement Learning Robotics

TG-VLA

Full-size, whole-body Vision-Language-Action framework for humanoid robots

A full-size, whole-body Vision-Language-Action framework for humanoid robots, described as comprising HEX, HAF-VLA, and DSRL-DCT components for mobile manipulation.

Model Intelligence

Benchmarkable

Model level

family

Recent stories

1 linked story

releasePRIMARY2026-07-05

X-Humanoid introduces TG-VLA with claimed 100% mobile-manipulation success

X-Humanoid unveiled TG-VLA as a full-size whole-body VLA framework for humanoids, built around HEX, HAF-VLA, and DSRL-DCT. The company claims DSRL-DCT reached 100% success in mobile-manipulation tasks by freezing the VLA and learning a smaller noise-selection policy.