Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models
Scaling robot data is crucial for building generalist Vision-Language-Action (VLA) models, yet robot trajectories are harder to scale than web-scale image-text data because embodied collection is costly and sparsely covers the physical world. This makes representation quality a central bottleneck: under a fixed robot-data budget, continued pre-training must turn limited trajectories into transferable visual-action knowledge rather than merely fit actions. We propose VLAct, a VLA-oriented VLM backbone trained on broad, heterogeneous, multi-embodiment robot data before task-specific fine-tuning. VLAct preserves the broad VLM prior and encourages shared action semantics across embodiments th...
| Authors | Senqiao Yang, Chengyao Wang, Yuxin Chen et al. |
|---|---|
| Primary category | cs.RO |
| Published | 27 August 2026 |
| Last updated at source | 6 October 2026 |
Connected in the knowledge graph
- StarVLA/VLAct_Qwen3PI_Libero_Plus_FinetuneModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.