ExecVLA: Following Fine-Grained Execution Constraints in Vision-Language-Action Models with Bi-Level Action Representation
Its authors withdrew this paper, so there is no full text to read or summarize.
Lists
Only you see this
Abstract
We study fine-grained execution-constraint following in vision-language-action (VLA) models. Given an invariant task goal, the policy must follow instruction-specified execution constraints, including interaction targets, motion patterns, spatial relations, and terminal configurations. This setting exposes a limitation of goal-oriented VLAs: trajectories that complete the same task are not interchangeable when the instruction specifies how the task must be executed. We propose ExecVLA, a framework that separates a goal-oriented component from an execution-specific component through a bi-level action representation and supervised bi-level reasoning tokens. We further introduce explicit goal-invariance and execution-predictability objectives so that the goal-level representation remains stable across executions of the same goal, while the execution-level representation retains the constraints that distinguish those executions. We construct execution-constraint-following datasets in simulation and on a Realman-75 robot, with goal and fine-grained reasoning annotations. Experiments on LIBERO and the real robot show improved goal completion and, more importantly, substantially more reliable adherence to instruction-specified execution constraints.
BibTeX
@misc{han2027execvla,
author = {Gaoge Han and Zhengqing Gao and Ziwen Li and Jiaxin Huang and Shaoli Huang and Fakhri Karray and Mingming Gong and Tongliang Liu},
title = {{ExecVLA: Following Fine-Grained Execution Constraints in Vision-Language-Action Models with Bi-Level Action Representation}},
year = {2027},
url = {https://openreview.net/forum?id=BCw1oqG73w},
howpublished = {OpenReview},
note = {Submitted to ICLR 2027},
}Loading related content...