@online{Kuzucu2605.30126,
TITLE = {{PARCEL}: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding},
AUTHOR = {Kuzucu, Selim and Tonioni, Alessio and Lup, Vasile and Schiele, Bernt and Tombari, Federico and Naeem, Muhammad Ferjad},
LANGUAGE = {eng},
URL = {https://arxiv.org/abs/2605.30126},
EPRINT = {2605.30126},
EPRINTTYPE = {arXiv},
YEAR = {2026},
ABSTRACT = {Large Vision-Language Models (LVLMs) map visual inputs into dense token sequences, imposing a quadratic computational bottleneck for inference. Elastic visual-token compression addresses this by training a single model that can run at multiple visual-token budgets. However, existing approaches struggle under aggressive compression. Spatial-only compression, as in nested pooling, behaves as an imperfect low-pass filter and induces spectral aliasing that obscures fine-grained detail. Query-only compression, as in nested query resampling, replaces explicit grid-aligned tokens with non-local summaries and substantially degrades spatial grounding. To resolve this representational conflict, we introduce PARCEL (Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding), a visual tokenization architecture that dynamically partitions the labor of feature extraction. PARCEL establishes spatial pool tokens as low-frequency layout anchors and conditions elastic query tokens on these anchors through Pool-Conditioned Query Resampling. This encourages query tokens to focus on complementary visual features rather than redundant spatial mapping. Extensive evaluations across 27 benchmarks show that PARCEL improves the performance-efficiency Pareto frontier, consistently outperforming existing matryoshka baselines across visual-token budgets while preserving the "train once, deploy anywhere" paradigm.},
}