works on
computer-use benchmarking 1interactive agents 1long-horizon tasks 1safety auditing 1tool-use evaluation 1

From the 1 of 7 linked papers with an AI index.

collaborators
Showing cs.ROShow all

1 paper · 1 filter

cs.RO2026

FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies

Xintong Hu, Xuhong Huang, Jinyu Zhang +11

Vision-Language-Action (VLA) models are increasingly expected to not only complete robot tasks, but also follow human instructions about how those tasks should be executed. However…