ScaleVLA scales VLA models to 552B parameters: 10 demos beat 2B backbone trained on 50

GalaxyGeneralRobotics · hf · 2026-11-17

Teams from Tsinghua, Peking University, SJTU, and Galbot introduce ScaleVLA, connecting a 552B DeepSeek-V4.1-Flash backbone to a trainable action DiT, and systematically compare VLM backbones from 2B to 552B under a shared setup.

Conclusion: frontier VLMs can serve as representational foundations for efficient, generalizable robot policies, not just reasoning agents.

Original post →

More from Embodied

Embodied channel →