| title | LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories |
|---|---|
| authors | Baochang Ren, Xinjie Liu, Xi Chen, Yanshuo Liu, Chenxi Li, Daqi Gao, Zeqin Su, Jintao Xing, Zirui Xue, Rui Li, Xiangyu Zhao, Shuofei Qiao, Minting Pan, Wangmeng Zuo, Lei Bai, Dongzhan Zhou, Ningyu Zhang, Huajun Chen |
| date | 2026-06-11 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.13578 |
| upvotes | 64 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| primer | Vision-language-action models |
| abstract | Scientific laboratories increasingly rely on AI systems to reason about experiments, but the physical act of doing science remains largely outside their reach. AI can help read literature, generate hypotheses, and plan protocols, yet the execution of those protocols at the bench still requires a human operator. Vision-Language-Action (VLA) models provide one possible interface between written protocols and robot execution, but existing policies are trained mostly on household and tabletop demonstrations and rarely encounter the instruments, transparent liquids, or fixed protocol workflows found in scientific laboratories. Closing this gap requires both laboratory-specific supervision and a unified learning framework that can accommodate the diverse robot embodiments used to execute experimental protocols. We therefore identify data and embodiment as central bottlenecks alongside model design. To address the data side, we build RoboGenesis, a simulation-based workflow and data engine that composes configured laboratory workflows from atomic skills, validates and filters rollouts, and exports structured demonstrations across supported robot profiles. On the policy side, we present LabVLA, trained with a two-stage recipe: FAST action token pretraining first makes the Qwen3-VL-4B-Instruct backbone action aware before any continuous control is learned, and flow matching posttraining then attaches a DiT action expert under knowledge insulation. On the LabUtopia benchmark, LabVLA achieves the highest average success rate among all evaluated baselines under both in-distribution and out-of-distribution settings. |
cite
@misc{ren2026labvla,
title={LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories},
author={Baochang Ren and Xinjie Liu and Xi Chen and Yanshuo Liu and Chenxi Li and Daqi Gao and Zeqin Su and Jintao Xing and Zirui Xue and Rui Li and Xiangyu Zhao and Shuofei Qiao and Minting Pan and Wangmeng Zuo and Lei Bai and Dongzhan Zhou and Ningyu Zhang and Huajun Chen},
year={2026},
eprint={2606.13578},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.13578}
}