ScaleVLA: Scaling Vision-Language-Action Models to 552 Billion Parameters
Abstract
Frontier Vision-Language Models (VLMs) such as GPT-6 Astra have demonstrated remarkable capabilities in robot control, suggesting that broad pretraining provides knowledge valuable for physical action. Yet most Vision-Language-Action (VLA) policies still rely on much smaller VLM backbones, leaving this potential largely untapped. We ask whether frontier-scale representations can provide a stronger foundation for robot learning. We introduce ScaleVLA, which connects a 552B DeepSeek-V4.1-Flash backbone to a trainable action DiT, and systematically compare VLMs from 2B to 552B under a shared training setup. We evaluate three fundamental capabilities of robot foundation models. In sample efficiency, just 10 demonstrations outperform a 2B backbone trained with 50 (87.8% vs. 85.6%). In generalization, LIBERO-PRO success reaches 45.1%, compared with at most 31.3% for smaller backbones. In precise manipulation, real-world charger insertion improves from 4/10 to 9/10 successes, with gains concentrated in contact-sensitive alignment. Despite its scale, ScaleVLA achieves 216 ms median latency per action chunk. Our findings suggest that frontier VLMs can serve not only as reasoning agents, but also as powerful representational foundations for efficient and generalizable robot policies.
Community
ScaleVLA: Scaling Vision-Language-Action Models to 552 Billion Parameters
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- PINT: A Unified Model with Shared Predictive Intent for Robot Manipulation (2026)
- Learning Low-Latency Action Verification for Frozen Vision-Language-Action Models (2026)
- GAWM: A Compact Latent World-Action Model for Multi-Task Robot Manipulation (2026)
- WAVE-0: Bridging VLA Policies and WAMs with Lightweight Latent Future Prediction (2026)
- APS-VLA: Action-Guided and Future-Aware Token Pruning for Efficient Vision-Language-Action Models (2026)
- HABILIS Brain 0: Geometry-Change Supervision for Vision-Language-Action and Residual Flow Recovery (2026)
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2611.21607 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper