arXiv cs.AI· Borui Xu, Han Chen, Bingsheng He, Ming Wu, Jason Zeng, Michael Heinrich·· 12 小时前AI 评分31
VLA-Retain：基准测试 VLA 视觉微调的跨维度影响
VLA-Retain: Benchmarking Cross-Dimension Effects of Vision Tuning in VLAs
AI 导读
VLA-Retain 基准对比五个开源 VLA 模型在 Camera-view 或 Sensor-noise 数据上微调后与各自基座 checkpoint 在 LIBERO-Plus 七个扰动维度上的表现。
正文 · 原文
Abstract:Vision-language-action (VLA) models transfer knowledge from large-scale pretraining into robot control, but their manipulation performance remains sensitive to changes in observation conditions, which recent work addresses by fine-tuning the visual module on target-domain data. However, it remains unclear how such adaptation affects robustness beyond the target condition, as existing robustness benchmarks only evaluate models without fine-tuning and adaptation studies only report the target gain. Measuring this cross-dimension effect requires separating target gains from off-target changes, isolating adaptation effects from architectural differences, ruling out generic forgetting, and comparing tuning choices. Therefore, we introduce VLA-Retain, a benchmark that compares five open VLA models, tuned on Camera-view or Sensor-noise data, with their own base checkpoints on LIBERO-Plus dataset spanning seven perturbation dimensions. Our study reveals four findings. First, targeted vision tuning is not local, and its target gain does not predict retention. Mean off-target gain is negative in 8 of 10 model--domain configurations. Under Camera-view tuning, X-VLA gains $69.4$ percentage points on the target but loses $4.6$ points on average elsewhere, whereas OpenVLA-OFT gains $39.3$ and $1.4$ points, respectively. Second, these regressions are not explained only by performance loss on the same tasks without perturbations. Third, broader training coverage raises overall gain over target-specific training but does not eliminate dimension-level regressions. Fourth, tuning strategies are model-dependent, as DELTA-style feature preservation raises X-VLA's mean off-target gain to $+1.2$ points but lowers OpenVLA-OFT's to $-23.1$. Overall, these findings show that target-domain success alone is insufficient and highlight cross-dimensional retention as a key criterion for targeted VLA adaptation.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.27698 [cs.CV] |
| (or arXiv:2610.27698v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.27698 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Borui Xu [view email]
[v1]
Tue, 20 Oct 2026 06:17:00 UTC (2,115 KB)
来源：arXiv cs.AI · arxiv.org