SOURCE-LINKED INTELLIGENCE

LAYERSCOPE: A Layerwise Characterization of Video and Multimodal Learned Representations

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

We propose LAYERSCOPE, a label-free, layerwise framework that aims to characterize a model's learned representations in video and multimodal settings. Evaluating downstream performance using representations from final or intermediate layers typically requires large amounts of labeled data, repeated task-specific evaluations, and substantial computation. To address these limitations, LAYERSCOPE uses local, global, distributional, and correspondence-based geometric metrics to compare layerwise representation structure within and across models without requiring task-specific labels. We evaluate s

Read original source ↗ Open in workspace

recordType

paper

region

Global