Don't Run with Scissors: Pruning Breaks VLA Models but They Can Be Recovered

ICLR 2026 Conference Submission21771 Authors

Keywords: Pruning, Vision-Language-Action, Robotics

TL;DR: We observe that pruning severely harms VLA models, and introduce GLUESTICK a recovery algorithm that restores task success and safety.

Abstract: Vision–Language–Action (VLA) models have advanced robotic capabilities but remain challenging to deploy on resource-limited hardware. Pruning has enabled efficient compression of large language models (LLMs), yet it is largely understudied in robotics. Surprisingly, we observe that pruning VLA models leads to drastic degradation and increased safety violations. We introduce GLUESTICK, a post-pruning recovery method that restores much of the original model's functionality while retaining sparsity benefits. Our method performs a one-time interpolation between the dense and pruned models in weight-space to compute a corrective term. This correction is used during inference by each pruned layer to recover lost capabilities with minimal overhead. GLUESTICK requires no additional training, is agnostic to the pruning algorithm, and introduces a single hyperparameter that controls the tradeoff between efficiency and accuracy. Across diverse VLA architectures and tasks in manipulation and navigation, GLUESTICK achieves competitive memory efficiency while substantially recovering success rates and reducing safety violations. Videos, code, and additional materials are in: https://gluestick-vla.github.io/

Primary Area: foundation or frontier models, including LLMs

Submission Number: 21771