SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

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

Read original source ↗ Open in workspace

recordType

paper

region

Global