{"ID":23475178,"CreatedAt":"2026-09-18T01:09:05.407443952Z","UpdatedAt":"2026-09-20T18:11:56.143995915Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2609.19990","arxiv_id":"2609.19990","title":"QCPruner: Query-Conditioned Population Coverage for Visual Token Pruning","abstract":"The high visual-token load in multimodal large language models (MLLMs) motivates training-free pruning to reduce later-layer computation, but under a fixed budget, pruning must preserve query-relevant evidence while avoiding redundancy. Existing methods rank tokens, diversify selected subsets, or optimize coverage without using a shared per-visual query utility to weight both visual targets and candidate representatives. We introduce QCPruner, which makes both roles query-conditioned through bilateral utility weighting. Using keyword-matched query anchors, QCPruner fuses two cross-modal cues into utility and applies it to both visual targets and candidate representatives within visual-affinity-based coverage. The resulting nonnegative facility-location objective is monotone and submodular, retains the standard (1-1/e) greedy guarantee, and requires no model training or parameter updates. Across LLaVA-1.5, LLaVA-NeXT, LLaVA-Video, and Qwen2.5-VL, QCPruner achieves the highest average relative performance among evaluated complete-system pruning methods at every reported token budget. At 32 of 576 tokens on LLaVA-1.5-7B, it retains 96.1% of unpruned performance, versus 93.9% for the strongest evaluated baseline. At 256 of 1296 tokens on Qwen2.5-VL-7B, the corresponding values are 96.7% and 92.5%.","short_abstract":"The high visual-token load in multimodal large language models (MLLMs) motivates training-free pruning to reduce later-layer computation, but under a fixed budget, pruning must preserve query-relevant evidence while avoiding redundancy. Existing methods rank tokens, diversify selected subsets, or optimize coverage with...","url_abs":"https://arxiv.org/abs/2609.19990","url_pdf":"https://arxiv.org/pdf/2609.19990v1","authors":"[\"Shengli He\",\"Yongchao Liang\",\"Roumeng He\",\"Junjie Zeng\",\"Jiyuan He\",\"Can Wu\",\"Li Zheng\"]","published":"2026-09-17T09:58:16Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}