# Improving Robustness of Vision-Language-Action Models by Restoring Corrupted Visual Inputs

arXiv: https://arxiv.org/abs/2602.01158 · HTML: https://mlsanity.com/paper/2602.01158/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Safety and adversarial attacks, one of 13 directions in Vision-language-action models.
- Builds on 22 of its 26 references that are in the map.
- First posted on arXiv 1 Feb 2026.

## Placed in

- Vision-language-action models / [Safety and adversarial attacks](https://mlsanity.com/vla/safety-and-adversarial-attacks/)

## Builds on (most cited first, 22 of 22)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics](https://mlsanity.com/paper/2506.01844/) (2025)
- [Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges](https://mlsanity.com/paper/2505.04769/) (2025)
- [WoW: Towards a World omniscient World model Through Embodied Interaction](https://mlsanity.com/paper/2509.22642/) (2025)
- [TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking](https://mlsanity.com/paper/2510.07134/) (2025)
- [VISO-Grasp: Vision-Language Informed Spatial Object-centric 6-DoF Active View Planning and Grasping in Clutter and Invisibility](https://mlsanity.com/paper/2503.12609/) (2025)
- [PEAfowl: Perception-Enhanced Multi-View Vision-Language-Action for Bimanual Manipulation](https://mlsanity.com/paper/2601.17885/) (2026)
- [PB-NBV: Efficient Projection-Based Next-Best-View Planning Framework for Reconstruction of Unknown Objects](https://mlsanity.com/paper/2501.10663/) (2025)
- [Image Reconstruction using Enhanced Vision Transformer](https://mlsanity.com/paper/2307.05616/) (2023)
- [D-Feat Occlusions: Diffusion Features for Robustness to Partial Visual Occlusions in Object Recognition](https://mlsanity.com/paper/2504.06432/) (2025)
- [TOTNet: Occlusion-Aware Temporal Tracking for Robust Ball Detection in Sports Videos](https://mlsanity.com/paper/2508.09650/) (2025)
- [Seeing through Unclear Glass: Occlusion Removal with One Shot](https://mlsanity.com/paper/2509.01033/) (2025)

## Built on by (most cited first, 4 of 4)

- [VLA-Forget: Vision-Language-Action Unlearning for Embodied Foundation Models](https://mlsanity.com/paper/2604.03956/) (2026)
- [Lights, Camera, Malfunction: When Illumination Robustness Leaves VLA Models Blind to Color](https://mlsanity.com/paper/2607.14698/) (2026)
- [RawVLA: Embodied Neural Image Signal Processor For Robotic Manipulation](https://mlsanity.com/paper/2609.37530/) (2026)
- [Adapting Vision-Language-Action Models to Unknown Visual Disruptions During Execution](https://mlsanity.com/paper/2610.07946/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) models have emerged as a dominant paradigm for generalist robotic manipulation, unifying perception and control within a single end-to-end architecture. However, despite their success in controlled environments, reliable real-world deployment is severely hindered by their fragility to visual disturbances. While existing literature extensively addresses physical occlusions caused by scene geometry, a critical mode remains largely unexplored: image corruptions. These sensor-level artifacts, ranging from electronic noise and dead pixels to lens contaminants, directly compromise the integrity of the visual signal prior to interpretation. In this work, we quantify this vulnerability, demonstrating that state-of-the-art VLAs such as π0.5 and SmolVLA, suffer catastrophic performance degradation, dropping from 90% success rates to as low as 2%, under common signal artifacts. To mitigate this, we introduce the Corruption Restoration Transformer (CRT), a plug-and-play and model-agnostic vision transformer designed to immunize VLA models against sensor disturbances. Leveraging an adversarial training objective, CRT restores clean observations from corrupted inputs without requiring computationally expensive fine-tuning of the underlying model. Extensive experiments across the LIBERO and Meta-World benchmarks demonstrate that CRT effectively recovers lost performance, enabling VLAs to maintain near-baseline success rates, even under severe visual corruption.