SOURCE-LINKED INTELLIGENCE

GramLoop: Training-Free Gram-Gated Replay for Robust Dense Prediction

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

We aim to improve frozen DINOv3 dense-prediction models under distribution shift by adding inference computation inside the visual backbone, without changing model weights, task adapters, or prediction heads. The challenge is that repeated transformer-block computation must refine dense features without disrupting the pairwise patch relations that DINOv3 uses to preserve spatial structure. We introduce GramLoop, a training-free framework that replays a short transformer window and controls each replay through final-layer cosine-Gram consistency. Each proposal is propagated through the frozen s

Read original source ↗ Open in workspace

recordType

paper

region

Global