ScaleVLA Scales Vision-Language-Action Models to 552B Parameters
The non-obvious takeaway is that scaling the VLM backbone pays off most where small models struggle: contact-rich, precise manipulation and low-data regimes, not just high-level reasoning. Robotics labs and embodied-AI teams can use the controlled 2B-to-552B comparison to decide backbone size against latency budgets, since 216 ms per action chunk shows frontier-scale policies are deployable. The paper is on arXiv for anyone building on LIBERO-PRO benchmarks or real-world insertion tasks.