FabriVLA: A Lightweight Vision-Language-Action Model for Precise Multi-Task Manipulation
arXiv:2607.08575v1 Announce Type: new Abstract: We present FabriVLA, a lightweight Vision-Language-Action model for Precise Multi-Task Manipulation. FabriVLA combines an InternVL3.5 vision-language backbone with a flow-matching action head featuring gated self-attention across action tokens and shallow VLM layer fusion for enriched spatial context. The model is trained via single stage joint optimization from a pretrained VLM and randomly initialized action head. On the Meta-World MT50 benchmar
Overview
arXiv:2607.08575v1 Announce Type: new Abstract: We present FabriVLA, a lightweight Vision-Language-Action model for Precise Multi-Task Manipulation. FabriVLA combines an InternVL3.5 vision-language backbone with a flow-matching action head featuring gated self-attention across action tokens and shallow VLM layer fusion for enriched spatial context. The model is trained via single stage joint optimization from a pretrained VLM and randomly initialized action head. On the Meta-World MT50 benchmark spanning 50 diverse manipulation tasks, FabriVLA achieves a tier-average success rate of 90.0%, demonstrating that a compact VLA built on a 1B scale VLM can achieve strong performance without relying on multi billion parameter VLA backbones.
Source
Originally published at arxiv.org.
Related Articles
- Open-Vocabulary Object-Goal Navigation by Generalizing Semantic Mapping with Dense CLIP
- Physics-Guided Biomechanical Gait Adaptation for Humanoid Locomotion on Extreme Sloped Terrains
- Graph-Loc: Robust Graph-Based LiDAR Pose Tracking with Compact Structural Map Priors under Low Observability and Occlusion
Source: https://arxiv.org/abs/2607.08575