This work introduces an adaptive visual token selection strategy for VLMs that leverages average text-to-visual attention scores to assess the importance of visual tokens, removing redundant ones during pruning based on a set threshold, thereby optimizing the importance calculation.
Abstract
While Vision-Language Models (VLMs) have demonstrated remarkable performance in processing and understanding both text and images, their large parameter sizes lead to significant computational overhead, limiting their deployment on resource-constrained devices. While pruning has been effective for compressing Large Language Models (LLMs), directly applying it to VLMs leads to significant performance drops, largely due to redundant visual tokens interfering with importance estimation. To this end, we propose SlimVLM, a structured pruning framework designed to compress VLMs while preserving their task performance. We introduce an adaptive visual token selection strategy for VLMs that leverages average text-to-visual attention scores to assess the importance of visual tokens, removing redundant ones during pruning based on a set threshold, thereby optimizing the importance calculation. Recognizing the varying tolerance to sparsity across different modules, we also propose a Sensitivity-aware dynamic pruning mechanism that determines the appropriate pruning ratio for each module by calculating the linear reconstruction error between the outputs of the pruned and unpruned modules, ensuring overall performance stability. Experimental results show that SlimVLM outperforms existing methods across multiple multimodal benchmarks, achieving state-of-the-art performance.
Recent high-resolution Multimodal Large Language Models (MLLMs) generate thousands of visual tokens per input, leading to a visual token explosion that introduces severe latency bottlenecks. While token pruning mitigates this issue, state-of-the-art subset-optimization methods typically rely on iterative subset construction to jointly capture visual diversity and instruction relevance. As visual token counts scale, this sequential dependency introduces significant selection overhead, severely limiting the translation of theoretical FLOPs reductions into actual wall-clock speedups. To address this limitation, we propose Single-Forward Pruner (SFPruner), a structural reformulation of visual token pruning that embeds redundancy control directly into the scoring space, bypassing the need for iterative combinatorial optimization. Our non-iterative framework achieves redundancy-aware importance selection in a single forward pass through two complementary mechanisms. First, to attenuate redundancy at the covariance level, we introduce a semantics-guided ridge leverage scheme. By integrating instruction relevance and visual saliency, this mechanism suppresses dominant covariance directions and mitigates representation bias. Second, ranking-based directional masking resolves residual overlap through asymmetric similarity competition, where higher-scoring tokens explicitly suppress redundant lower-scoring alternatives via parallel tensor operations. Extensive evaluations demonstrate that our approach maintains stable selection costs, reducing the token selection process by up to 110 ms, from 112.4 ms to just 2.5 ms at 512 tokens in Qwen2.5-VL. This structural efficiency successfully translates theoretical token reductions into tangible inference speedups while preserving highly competitive performance against state-of-the-art techniques under aggressive compression.
J. Song, Woohyeong Kim, Kyeongbo Kong· 0 citations
VisCache is proposed, a plug-and-play framework for coarse-to-fine KV pruning without training that consistently outperforms existing baselines, establishing a new Pareto frontier between efficiency and performance for long-context VLLM inference.
A training-free, Adaptive Visual Token Pruning (AVTP) framework, applicable to diverse LVLM architectures is proposed, and adaptive pruning ratios in multi-image contexts where images of higher importance retain proportionally more tokens are implemented.
Rongyang Zhang, Chengqiang Lu, Cong Li et al.· 0 citations
An attention-free and lightweight token reduction framework as a plug-and-play module for VLMs, which preserves both important and diverse tokens to produce a compact visual representation, and achieves a favorable accuracy-efficiency trade-off.
Xuanyi Hao, Zuoyuan Zhang, Zhibo Wang et al.· 0 citations
ProViP is proposed, a training-free progressive visual token pruning framework that removes redundant visual tokens based on the embedding similarity of input tokens before reasoning of the LLM backbone, and then prunes tokens during reasoning via head-aware pruning.
Chaofang Ma, Lin Jiang, Carol Jingyi Li et al.· 0 citations
In vision-language models (VLMs), visual tokens usually bear a significant amount of computational overhead despite sparsity of information in them when compared to text tokens. To address this, most existing methods learn a network to prune redundant visual tokens using certain training data. Differently, we propose a text-guided training-free token optimization mechanism dubbed SparseVLM without fine-tuning costs. Given that visual tokens complement text tokens in VLM's linguistic reasoning, we select relevant text tokens to rate the significance of visual tokens using self-attention matrices and, then, prune visual tokens using the proposed strategy to maximize sparsity while retaining information. In particular, we introduce a rank-based strategy to adaptively determine the sparsification ratio for each layer, alongside a token recycling method that compresses pruned tokens into more compact representations. However, the Attention Gravity and Attention Sink phenomena undermine the sparsification reference of SparseVLM: text-visual alignment. To address this, we introduce improved text-visual attention patterns to enhance the fidelity of query-aware vision token selection. First, we correct the Attention Gravity effect, where positional encodings induce disproportionately high attention to vision tokens positioned near textual tokens. We further mitigate the Attention Sink by selecting priority attention heads that suppress the excessive attention absorbed by semantically irrelevant vision tokens. The two parts refine the text-visual alignment from both the token and head perspectives. Finally, for video understanding tasks, we propose Temporal-Balanced Sparsification, complementing spatial relevance with temporal diversity to reduce cross-frame redundancy. Extensive experiments on 23 widely used image and video understanding tasks across 7 vision-language models demonstrate the effectiveness of our SparseVLM+ framework. For example, equipping LLaVA with SparseVLM+ yields a 57.1% reduction in FLOPs and a 38.4% decrease in CUDA latency, while preserving 99.6% of its original accuracy on average. Our code is available at https://github.com/Gumpest/SparseVLMs.
Yuan Zhang, Junpeng Ma, Qizhe Zhang et al.· IEEE Transactions on Pattern...· 2 citations