arXiv Computation and Language

Structural Anchor Pruning: Training-Free Multi-Vector Compression for Visual Document Retrieval

Hugging Face Trending Papers
Aug 9

AnchorFold: A Focus-Then-Fold Framework via Recursive Attention Propagation for Efficient Multi-Vector Visual Document Retrieval

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 AI
Aug 18

Static Pruning Across Sparse Retrieval Regimes: What Transfers, What Breaks, and What Still Helps

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.

By Zirui Song, Yuye Zhu, Yang Yang
arXiv AI
Aug 26

VisCache: Visual KV Cache Pruning for Efficient Vision Large Language Model Inference

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.

By Lyuke Wang, Zhuo Li, Guangxu Zhu
arXiv Computer Vision
1d ago

QCPruner: Query-Conditioned Population Coverage for Visual Token Pruning

arXiv:2609.19990v1 Announce Type: new Abstract: The high visual-token load in multimodal large language models (MLLMs) motivates training-free pruning to reduce later-layer computation, but under a f...

By Shengli He (Guizhou University), Yongchao Liang (Guizhou University), Roumeng He (Shanghai Ocean University), Junjie Zeng (Guizhou University), Jiyuan He (Guizhou University), Can Wu (Guizhou University), Li Zheng (Guizhou University)
arXiv Computation and Language
Aug 28

ET-Prune: Evidence-Aware Dynamic Budgeting for Visual Token Pruning in Text-Rich MLLMs

ET‑Prune is a training‑free framework that dynamically allocates visual token budgets in multimodal large language models based on question‑conditioned evidence. It protects text‑like spatial regions, converts evidence uncertainty into a token floor, and progressively prunes concentrated evidence while retaining diffuse or text‑dense tokens. In six backbone‑benchmark comparisons, ET‑Prune matches or outperforms other pruned methods while keeping roughly half the visual tokens, achieving notable gains on OCRBench‑v2 and MMBench v1.1.

By Zizhong Ding, Junxian Li, Kai Liu, Shaoqiu Zhang, Xiao Xiao, Linghe Kong, Yulun Zhang
arXiv Computer Vision
Aug 27

Not All Attention Heads Contribute to Critical Visual Token Selection: Head-Aware Pruning Matters More

The paper shows that only a small subset of attention heads in vision-language models is responsible for selecting critical visual tokens. By pruning tokens based on similarity before LLM reasoning and then applying head‑aware pruning during reasoning, the proposed ProViP framework achieves high task performance with significant speedups. Experiments on LLaVA‑1.5‑7B demonstrate 95.9% performance retention and a 1.62× inference speedup at an 88.9% pruning ratio.

By Chaofang Ma, Lin Jiang, Carol Jingyi Li, Xingyu Liu, Zeyu Li, Jiang Xu, Wei Zhang
arXiv Computer Vision
Sep 2

From Saliency to Discriminability: Rank-Preserving Visual Token Pruning for VLM Rerankers

arXiv:2609.00667v1 Announce Type: cross Abstract: Large vision-language models used as listwise rerankers must jointly process visual tokens from tens of candidates per query, making token pruning es...

By Siyi Liu, Hanjun Yang, Chenchen Zhang, Xiaorong Zhu, Xinyu Zuo, Lisheng Duan, Haijin Liang, Jin Ma, Junfu Pu, Yongqi Zhang
arXiv Computer Vision
Aug 28

Multi-Image Visual Token Pruning in Large Visual Language Models

The paper introduces Adaptive Visual Token Pruning (AVTP), a training‑free framework that dynamically selects pruning layers and ratios for large vision‑language models (LVLMs) when processing multiple image sequences. By analyzing visual attention distributions across different LVLM architectures, AVTP adapts token retention to image importance, enabling efficient inference without relying on attention‑based computations incompatible with FlashAttention. Experiments show significant speedups—up to 2× for Qwen3VL‑8B—while preserving or even improving accuracy on multi‑image benchmarks.

By Rongyang Zhang, Chengqiang Lu, Cong Li, Hongchao Gu, Tingjia Shen, Xuyang Zhi, Qimeng Wang, Yan Gao, Yi Wu, Yao Hu, Hao Wang, Enhong Chen