# Cross-View Action Consistency for Camera-Robust Vision-Language-Action Policies

arXiv: https://arxiv.org/abs/2608.06965 · HTML: https://mlsanity.com/paper/2608.06965/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in 3D and spatial-aware VLA, one of 13 directions in Vision-language-action models.
- Builds on 22 of its 25 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## Placed in

- Vision-language-action models / [3D and spatial-aware VLA](https://mlsanity.com/vla/3d-and-spatial-aware-vla/)
- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

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

- [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)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [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)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model](https://mlsanity.com/paper/2501.15830/) (2025)
- [LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models](https://mlsanity.com/paper/2510.13626/) (2025)
- [Masked Visual Pre-training for Motor Control](https://mlsanity.com/paper/2203.06173/) (2022)
- [Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?](https://mlsanity.com/paper/2303.18240/) (2023)
- [FlowPolicy: Enabling Fast and Robust 3D Flow-based Policy via Consistency Flow Matching for Robot Manipulation](https://mlsanity.com/paper/2412.04987/) (2024)
- [Multi-View Masked World Models for Visual Robotic Manipulation](https://mlsanity.com/paper/2302.02408/) (2023)
- [BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models](https://mlsanity.com/paper/2506.07961/) (2025)
- [View-Invariant Policy Learning via Zero-Shot Novel View Synthesis](https://mlsanity.com/paper/2409.03685/) (2024)
- [GeoAware-VLA: Implicit Geometry Aware Vision-Language-Action Model](https://mlsanity.com/paper/2509.14117/) (2025)
- [Do You Know Where Your Camera Is? View-Invariant Policy Learning with Camera Conditioning](https://mlsanity.com/paper/2510.02268/) (2025)
- [OG-VLA: Orthographic Image Generation for 3D-Aware Vision-Language Action Model](https://mlsanity.com/paper/2506.01196/) (2025)
- [VLA Models Are More Generalizable Than You Think: Revisiting Physical and Spatial Modeling](https://mlsanity.com/paper/2512.02902/) (2025)
- [Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy](https://mlsanity.com/paper/2508.13103/) (2025)
- [AnyCamVLA: Zero-Shot Camera Adaptation for Viewpoint Robust Vision-Language-Action Models](https://mlsanity.com/paper/2603.05868/) (2026)

## Built on by (most cited first, 1 of 1)

- [AnyviewMeter: Adapting Robotic Reward Models with Camera Geometry and Multi-View Attention](https://mlsanity.com/paper/2609.20106/) (2026)

## Abstract (arXiv)

Vision-language-action (VLA) policies fine-tuned from a fixed scene camera can fail when the camera is moved, even when the task, objects, language, and robot state are unchanged. We study scene-camera viewpoint robustness using only a scene RGB image, language, and proprioception, without camera labels, extrinsics, depth, or point-cloud inputs. The wrist stream is masked throughout to prevent an unperturbed visual shortcut from confounding attribution to scene-camera variation. For flow-based VLAs, we propose to regularize the action-flow velocity field, the quantity directly integrated to generate continuous action chunks. We construct action-equivalent view pairs by resetting original LIBERO demonstrations to the same MuJoCo state and rendering nominal and perturbed scene-camera views. Both views are supervised by flow matching, while a cross-view loss encourages their predicted action-flow velocities to agree at the same sampled flow coordinates. On the LIBERO-Plus camera-perturbation track, our method reaches 87.2±0.4% (4,797 rollouts per seed across 3 training seeds), +7.4pp over flow-matching-only training on the same paired data (79.8±0.8%, also 3 seeds) and +12.5pp over naive mixed-camera SFT, while maintaining nominal-camera ID performance (95.0±0.8%; same-data FM-only: 95.0±4.3%). A shuffled-pair control collapses to 25.8%, showing that the gain depends on action-equivalent pairing. On a real robot, we evaluate three tabletop tasks with 10 rollouts per task and camera placement; held-out-camera success improves from 53.3% to 74.4% under the same single-scene-RGB inference interface.