The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Multi-vector vision-language retrievers enable fine-grained Visual Document Retrieval (VDR) through late interaction, but storing and scoring hundreds of visual patch embeddings per page incurs substantial overhead. Existing training-free methods rely on pruning or merging: pruning degrades sharply under aggressive compression, whereas merging does not explicitly prioritize important regions when forming representatives.
arXiv:2609.22562v1 Announce Type: new Abstract: Multi-vector visual document retrieval (VDR) models such as ColPali and ColNomic achieve strong accuracy by representing each document with hundreds to...
arXiv:2608. 16309v1 Announce Type: cross Abstract: Static pruning is widely used to accelerate sparse neural retrieval, yet existing studies each validate their conclusions within a single custom pipeline, leaving it unclear which findings transfer to modern engines with different index organizations and dynamic pruning mechanisms.
arXiv:2607. 07033v1 Announce Type: cross Abstract: Large vision-language models incur substantial inference costs because high-resolution inputs introduce thousands of visual tokens, many of which are redundant for a given query.
LearnPrunerV2 is a fully learnable token‑pruning framework for Vision‑Language Models that replaces heuristic pruning with lightweight modules in every backbone layer. These modules estimate token importance by combining visual saliency and query relevance via a shadow token, revealing a consistent staircase redundancy pattern across layers. The method introduces Budget‑Deterministic Pruning to set fixed per‑layer budgets, achieving state‑of‑the‑art efficiency while preserving 99.8% of performance even after pruning 77.8% of visual tokens on LLaVA‑v1.5.
VisCache introduces a two-stage, plug‑and‑play framework for pruning visual key‑value caches in Vision Large Language Models without retraining. The first stage filters out temporally redundant keyframes, while the second stage, PruneKV, applies a parabolic layer‑wise budget and asymmetric update to selectively prune keys and fuse values, preserving essential context. Experiments show up to 2.35× speedup and significant memory savings with only 19–28% of the original cache retained, outperforming existing baselines.