This paper revisit VLM inference and presents a new efficient guidance scheme that complements similarity-based guidance, and proposes Cross Modal Residual (CMR), a training-free visual token compression method that combines CMR, text-attention relevance, and residual-space diversity to retain task-relevant and complementary tokens.
Abstract
Abundant visual information strengthens vision-language model (VLM) perception, yet massive visual tokens raise inference costs. Existing visual token pruning methods rely on similarity-based guidance, which exploits pairwise text-vision and vision-vision token correlations for compression. However, such methods only capture local layer-level signals and overlook the whole inference process in VLM. In this paper, we revisit VLM inference and present a new efficient guidance scheme that complements similarity-based guidance. In particular, we identify a key observation: as LLM layers deepen, text tokens continuously aggregate visual information via self-attention and progressively absorb partial visual content into textual representations. To quantify this phenomenon, we propose Cross Modal Absorption (CMA) from a geometric representation perspective to measure how much visual information is absorbed by text, revealing that more visual tokens in deeper layers can be approximately explained by the text subspace. We accordingly propose Cross Modal Residual (CMR). It projects visual tokens onto the text subspace via Tikhonov regularized least squares and exploits reconstruction residuals to quantify visual information that cannot be explained by text. Finally, based on CMR, we present SIEVE, a training-free visual token compression method that combines CMR, text-attention relevance, and residual-space diversity to retain task-relevant and complementary tokens. Experiments on diverse VLM architectures verify the effectiveness of SIEVE. For instance, on LLaVA-NeXT-7B, SIEVE keeps only $11.1\%$ of visual tokens while preserving $97.5\%$ of the original average performance, achieving $3.62\times$ prefill speedup, $2.49\times$ end-to-end speedup, and a $6.02\times$ KV-cache reduction.
Mechanistic analyses show that HAFI restores task-dependent spectral allocation while retaining semantic attention, establishing frequency enrichment as a distinct and effective route for improving VLM perception.
Jin Cui, Chuanchang Su, Jia-Yi Lu 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
Current text-to-image systems typically employ a"text encoder plus diffusion decoder"paradigm, in which text semantics directly modulate continuous latent noise. Despite their success, these methods lack an explicit, interpretable intermediate representation that effectively bridges high-level linguistic semantics and low-level visual signals. In this paper, we propose Vision-of-Thought (VoT), a framework that introduces a discrete visual-thinking layer between vision-language models (VLMs) and diffusion transformers (DiTs). Instead of treating VLMs merely as text encoders, we use them as multimodal planners that generate discrete VoT tokens representing high-level visual plans, such as objects and layouts, before rendering pixels. We train a specialized VoT tokenizer in the VLM semantic space with a closed-loop objective that combines VLM alignment, feature reconstruction, and vector-quantization losses. These objectives make the tokens semantically readable by the VLM while preserving the visual information needed for generation. Experimental results demonstrate that VoT improves semantic alignment and provides a structured interface for interpretable and controllable generation.
Jingxiang Sun, Chao Liao, Zheng-Xiong Luo et al.· 0 citations
The core of SSVAL is Visual Anchor Prompt Injection (VAPI), which introduces prompts that absorb rich knowledge from external VFMs during training, enabling them to serve as stable visual anchors that mitigate representation deviation during inference.
Qian-Long Yang, Bowen Ye, Xianda Guo 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
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.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
