# AnyviewMeter: Adapting Robotic Reward Models with Camera Geometry and Multi-View Attention

arXiv: https://arxiv.org/abs/2609.20106 · HTML: https://mlsanity.com/paper/2609.20106/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion and multimodal model alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 29 of its 35 references that are in the map.
- First posted on arXiv 17 Sep 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 29 of 29)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [PETR: Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2203.05625/) (2022)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training](https://mlsanity.com/paper/2210.00030/) (2022)
- [Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering](https://mlsanity.com/paper/2106.02634/) (2021)
- [LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models](https://mlsanity.com/paper/2510.13626/) (2025)
- [Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations](https://mlsanity.com/paper/2111.13152/) (2021)
- [LIV: Language-Image Representations and Rewards for Robotic Control](https://mlsanity.com/paper/2306.00958/) (2023)
- [RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback](https://mlsanity.com/paper/2402.03681/) (2024)
- [Temporal Cycle-Consistency Learning](https://mlsanity.com/paper/1904.07846/) (2019)
- [Stop Regressing: Training Value Functions via Classification for Scalable Deep RL](https://mlsanity.com/paper/2403.03950/) (2024)
- [Cameras as Rays: Pose Estimation via Ray Diffusion](https://mlsanity.com/paper/2402.14817/) (2024)
- [Cameras as Relative Positional Encoding](https://mlsanity.com/paper/2507.10496/) (2025)
- [Vision Language Models are In-Context Value Learners](https://mlsanity.com/paper/2411.04549/) (2024)
- [Multi-View Masked World Models for Visual Robotic Manipulation](https://mlsanity.com/paper/2302.02408/) (2023)
- [GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers](https://mlsanity.com/paper/2310.10375/) (2023)
- [A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning](https://mlsanity.com/paper/2509.15937/) (2025)
- [Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons](https://mlsanity.com/paper/2603.02115/) (2026)
- [RoboReward: General-Purpose Vision-Language Reward Models for Robotics](https://mlsanity.com/paper/2601.00675/) (2026)
- [Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation](https://mlsanity.com/paper/2512.23703/) (2025)
- [Do You Know Where Your Camera Is? View-Invariant Policy Learning with Camera Conditioning](https://mlsanity.com/paper/2510.02268/) (2025)
- [RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance](https://mlsanity.com/paper/2608.09853/) (2026)
- [SCoPE: Sightline-Coordinate Positional Encoding for Video Diffusion Transformers](https://mlsanity.com/paper/2606.27345/) (2026)
- [Position: Good Embodied Reward Models Need Bad Behavior Data](https://mlsanity.com/paper/2606.01036/) (2026)
- [Cross-View Action Consistency for Camera-Robust Vision-Language-Action Policies](https://mlsanity.com/paper/2608.06965/) (2026)

## Abstract (arXiv)

Robotic reward models evaluate task execution from visual observations, but their predictions can change with camera viewpoint and occlusion even when the underlying task state is unchanged. Adapting a pretrained reward model to a local task therefore requires accounting for how that task is observed. We introduce AnyviewMeter, a geometry-conditioned adaptation framework for robotic reward models that represent task progress as a scalar reward signal. It combines low-rank fine-tuning with token-aligned Plucker rays and synchronous block attention: ray conditioning incorporates camera geometry into visual features and attention queries and keys, while block attention fuses synchronized views inside the pretrained decoder. The framework supports both single-view reward prediction and joint multi-view evaluation through parameter-efficient adaptation of a pretrained Robometer model. On PickCube, single-view adaptation improves progress prediction in every camera group and reduces mean absolute error under a changed field of view by approximately 21% relative to RGB fine-tuning. Across simulated manipulation tasks, joint multi-view prediction reduces progress error by 41-69% compared with averaging single-view RGB predictions and improves temporal ordering in approximately 88% of task-camera groups. On real tasks with fixed and wrist-mounted cameras, mean absolute error decreases by approximately 21% relative to averaged RGB fine-tuning. These results support camera geometry and joint visual evidence as useful components of task-specific robotic reward adaptation.