SOURCE-LINKED INTELLIGENCE

AdaMerge: Tuning-Free Patch Compression for Multi-Vector Visual Document Retrieval

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Multi-vector visual document retrieval (VDR) models such as ColPali and ColNomic achieve strong accuracy by representing each document with hundreds to thousands of patch-level embeddings, at substantial storage and latency cost. Existing compression methods either prune unimportant patches or merge similar ones into clusters; the recent state-of-the-art merging method Prune-then-Merge (PtM) consistently outperforms pruning-only baselines at high compression, but requires a per-dataset cluster budget m to be tuned by grid search. We observe that the merge-cosine sequence produced by hierarchic

Read original source ↗ Open in workspace

recordType

paper

region

Global