# RawVLA: Embodied Neural Image Signal Processor For Robotic Manipulation

arXiv: https://arxiv.org/abs/2609.37530 · HTML: https://mlsanity.com/paper/2609.37530/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Tactile, force-aware and humanoid VLA, one of 13 directions in Vision-language-action models.
- Builds on 49 of its 60 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Placed in

- Vision-language-action models / [Tactile, force-aware and humanoid VLA](https://mlsanity.com/vla/tactile-force-aware-and-humanoid-vla/)

## Builds on (most cited first, 30 of 49)

- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [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)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025)
- [Evaluating Real-World Robot Manipulation Policies in Simulation](https://mlsanity.com/paper/2405.05941/) (2024)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning](https://mlsanity.com/paper/2601.16163/) (2026)
- [Unprocessing Images for Learned Raw Denoising](https://mlsanity.com/paper/1811.11127/) (2018)
- [THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation](https://mlsanity.com/paper/2402.08191/) (2024)
- [StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing](https://mlsanity.com/paper/2604.05014/) (2026)
- [Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy](https://mlsanity.com/paper/2503.19757/) (2025)
- [VLATest: Testing and Evaluating Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2409.12894/) (2024)
- [Dirty Pixels: Towards End-to-End Image Processing and Perception](https://mlsanity.com/paper/1701.06487/) (2017)
- [Do World Action Models Generalize Better than VLAs? A Robustness Study](https://mlsanity.com/paper/2603.22078/) (2026)
- [Run-time Observation Interventions Make Vision-Language-Action Models More Visually Robust](https://mlsanity.com/paper/2410.01971/) (2024)
- [ReconfigISP: Reconfigurable Camera Image Processing Pipeline](https://mlsanity.com/paper/2109.04760/) (2021)
- [RobustVLA: On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations](https://mlsanity.com/paper/2510.00037/) (2025)
- [Day-to-Night Image Synthesis for Training Nighttime Neural ISPs](https://mlsanity.com/paper/2206.02715/) (2022)
- [GenISP: Neural ISP for Low-Light Machine Cognition](https://mlsanity.com/paper/2205.03688/) (2022)
- [VisionISP: Repurposing the Image Signal Processor for Computer Vision Applications](https://mlsanity.com/paper/1911.05931/) (2019)
- [Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environments](https://mlsanity.com/paper/2210.16046/) (2022)
- [AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection](https://mlsanity.com/paper/2410.22939/) (2024)
- [RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Models](https://mlsanity.com/paper/2511.01331/) (2025)

## Abstract (arXiv)

Vision-language-action (VLA) models typically operate on RGB images produced by a fixed camera image signal processor (ISP), leaving the imaging pipeline outside the learning and evaluation loop. We systematically examine the consequences of this overlooked design choice across five fundamental ISP dimensions: gain, sensor noise, chromatic response, tonal response, and bit depth. Our analysis reveals that RAW-to-RGB processing materially shapes both action prediction and manipulation success, with different ISP dimensions exerting substantially different effects. Guided by these findings, we introduce RawVLA, a streaming neural ISP that adaptively renders RAW observations for frozen VLA policies while concentrating its capacity on the imaging factors relevant to embodied behavior. We further present RawVLA-Bench, a RAW-domain manipulation benchmark to expose image processing as an explicit evaluation variable across clean and adverse acquisition conditions. Experiments on RawVLA-Bench show that RawVLA preserves performance under standard conditions while substantially improving robustness under degraded imaging, establishing adaptive RAW processing as an effective interface between physical cameras and embodied policies.