Zlio
Everything in AI and robotics, on one page.
Updated 23:31 UTC · Next update 00:00 UTC
Zlio Daily, the newsletter, is coming soon. The day's essential AI and robotics news in your inbox. Leave your email and we'll tell you when it launches.
One email when we launch. No spam, unsubscribe anytime. Privacy
Robotics · first seen 16 November 2026, 00:00 UTC

ScaleVLA scales vision-language-action models to 552B parameters

Tests whether frontier-scale pretraining, not just small backbones, is the path to better robot policies.

A paper asks whether frontier-scale vision-language representations improve robot control and scales vision-language-action policies to 552 billion parameters, far larger than typical VLA backbones.

Params
552B
Domain
industry

Read it at HF Papers →

Share LinkedIn X Bluesky WhatsApp

Coverage: 1 sources, in order

  1. HF Papers Read the article →

← Front page