ActionUNet: Improving Robustness of VLA Models with Efficient Multi-scale Fine-t
Overview
This research proposes ActionUNet, an efficient multi-scale fine-tuning framework for Vision-Language-Action (VLA) models. By integrating a lightweight temporal U-Net and a conditional SIREN decoder, the method enhances temporal continuity and reduces mechanical oscillations, leading to improved success rates in simulated and real-world robotic tasks.
From arXiv Robotics — research abstracts
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · Reported success rate: 9.8 percent · Basis not reported
“execution failures while preserving the base VLA model's generalization and manipulation robustness. Extensive experiments on RoboTwin 2.0 and LIBERO-Plus benchmarks, together with real-world hard evaluations, demonstrate that ActionUNet significantly improves {\pi}0.5 success rates by absolute 9.8%, 6.1%, and 11.4%, respectively, while also generalizing to the regression-based OpenVLA-OFT backbone, highlighting its”
Exact source · revision 1Source owner not reported
Artifact availability · code: available
“effectiveness and efficiency as a fine-tuning strategy. Code and implementation details are available at https://github.com/Di-Zhu123/ActionUNet.”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalActionUNet: Improving Robustness of VLA Models with Efficient Multi-scale Fine-tuning
This research proposes ActionUNet, an efficient multi-scale fine-tuning framework for Vision-Language-Action (VLA) models. By integrating a lightweight temporal U-Net and a conditional SIREN decoder, the method enhances temporal continuity and reduces mechanical oscillations, leading to improved success rates in simulated and real-world robotic tasks.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).