#artificial intelligence
May 2026
FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies
FineVLA, an open framework for action-aligned fine-grained VLA supervision, is introduced and the largest real-world gains appear on pose, color, and approach direction, and approach direction--factors where goal-level instructions provide no guidance.
Xin-Tong Hu, Xuhong Huang, Jin-Yu Zhang et al.
· arXiv.org · 4 citations