Visual Token Compression

Follow this topic Ask about this topic

Momentum

20 papers in the last four weeks, up 67% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 184

Aug 30, 2026cs.AI

Spatial Matryoshka Training for Multi-Granularity Visual Document Retrieval

Multi-modal late-interaction retrievers achieve strong retrieval on visually rich documents by representing each page as per patch embeddings and matching at the token level. However, this approach incurs high storage costs. Existing compression methods typically fix a single compression level at indexing time, limiting flexibility. We present ColSNAP (Spatial Nested Average Pooling)1, a training method that generates a nested hierarchy of compression levels directly from a backbone's patch grid. By spatially pooling patch embeddings into pro- gressively coarser tiers and training all tiers simultaneously, a single model learns to support retrieval at multiple compression levels without architectural changes. Crucially, a single encoding pass yields every tier, enabling the accuracy-storage trade-off to be configured at indexing time to match avail- able storage budgets, rather than being fixed during training. We demonstrate that models trained using ColSNAP maintain near full-resolution retrieval performance under substantial compression and that ColSNAP transfers effectively across multiple late-interaction backbones, and achieves most of its improvements via a lightweight adaptation stage applied to a pre-trained retriever.

Trishan Singha Roy, Arkadeep Acharya, Vishwajeet Kumar +2

IIT Delhi · IBM

Hierarchical Representation Learning Matryoshka Representation Learning Multi-Vector Retrieval Visual Document Retrieval Visual Token Compression

Aug 27, 2026cs.CV

PACE: A Unified Condense-and-Extract Paradigm for Fast VLM Inference

Vision-Language Models (VLMs) demonstrate exceptional visual reasoning capabilities, yet their inference costs escalate rapidly with the proliferation of visual tokens. Existing visual token pruning methods exhibit two fundamental limitations. First, most approaches operate exclusively post-vision encoder, leaving the substantial latency of the visual encoding phase unoptimized. Second, under strict token budgets, these methods often fail to jointly preserve holistic visual contexts and fine-grained details, leading to performance degradation. To address these bottlenecks, we propose PACE (Pixel-Adaptive Condense and Extract), a training-free inference framework that accelerates both the vision encoder and the Large Language Model (LLM) via a unified Condense-and-Extract paradigm. During the Condense stage, an Adaptive Pixel Compressor (APC) evaluates visual information density prior to encoding, adaptively downsampling redundant inputs, curtailing encoder computation while preserving global context and essential visual cues. In the Extract stage, a Dynamic Dual-Attention Extractor (DDAE) selectively retains visual tokens via a fusion of internal visual signals from the encoder and semantic signals from the LLM, safeguarding task-critical details. By integrating PACE into Qwen2.5-VL-7B, the model retains 93.8% of its original performance while utilizing only 10% of the visual tokens, yielding a 3.1x speedup in time to first token (TTFT). Our code is available at https://github.com/jjL357/PACE.

Junjie Liu, Shengyuan Ye, Xu Chen

Sun Yat-sen University · Power Dispatch Control Center, Guangdong Power Grid Co., Ltd. Guangzhou, China · Shenzhen Loop Area Institute, Shenzhen, China

Efficient VLM Inference Visual Token Pruning Visual Token Compression

Aug 26, 2026eess.SP

Token-Oriented Semantic Communication with Pretrained Vision Transformers

Token communications realize the semantic communication principle at the granularity of transformer tokens, providing a promising direction for client--server collaborative inference in resource-constrained edge systems. However, directly transmitting token embeddings presents two practical challenges: substantial communication cost and limited interoperability across model-specific token embedding spaces. To address these challenges, we propose a \emph{token-oriented} semantic communication framework. In this framework, token-level task relevance determines which compressed image latents are transmitted, enabling token-granular transmission without directly transmitting token embeddings. The framework is modular, coordinating three pretrained components---a lightweight client-side vision transformer (ViT), a learned image compression (LIC) model, and a large server-side ViT---without end-to-end training. The key enabler is the one-to-one spatial alignment between ViT patch tokens and the LIC latent vectors, which allows token-level task relevance to directly determine which latent vectors are transmitted. Building on this alignment, token-aligned LIC selectively transmits task-relevant latents, layer-selective attention rollout estimates token relevance from a selected range of attention layers in a single forward pass, and surrogate token substitution adapts the frozen server model by optimizing a single learnable token. Experiments on ImageNet show that the proposed framework achieves a more favorable rate--accuracy trade-off than recent semantic communication schemes, hand-crafted codecs, and task-agnostic LIC models.

Jiwoong Im, Minwoo Kim, Jaeho Lee +2

Department of Electrical Engineering, Pohang University of Science and Technology (POSTECH), Pohang 37673, South Korea

Learned Image Compression Semantic Communication Visual Token Compression

Aug 21, 2026cs.CV

Just Noticeable Difference Modeling for Token Compression in Vision-Language-Action Models

Token compression has become a key technique for reducing the inference cost of large foundation models, with approaches such as token pruning and KV-cache reuse widely adopted in vision-language models and recently explored for embodied agents. In embodied agents, tokens not only support perception and semantic understanding but also directly affect latency-sensitive closed-loop robot action prediction. Existing schemes typically guide compression using redundancy or importance cues, such as visual similarity, attention scores, and saliency. However, these cues only indirectly measure the key factor for safe compression: how much a token can change before causing an unacceptable deviation in downstream actions. This receiver-dependent tolerance is closely related to the principle of just noticeable difference (JND). Classical JND characterizes signal tolerance in the human visual system, while machine-oriented JND extends this concept to downstream machine responses. Building on this progression, we introduce Action-JND, which extends JND modeling to embodied perception by defining noticeability through the language-conditioned action response of a vision-language-action (VLA) policy in closed-loop control. A token change is considered admissible only when the induced action deviation remains within a tolerated margin. To realize this concept, we develop a lightweight token-wise JND estimator in deep visual-feature space to predict the maximum tolerable perturbation while preserving policy responses. The resulting action-tolerance score serves as a plug-and-play criterion for VLA compression paradigms, including stale-KV reuse and token pruning, prioritizing action-tolerant tokens for compression. Experiments on the LIBERO benchmark with OpenVLA and OpenVLA-OFT demonstrate that Action-JND consistently improves compression reliability, especially under aggressive compression ratios.

Zhuoyuan Li, Rui Zhao, Jin Wang +5

Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong · School of Computer Science and Engineering, Nanyang Technological University, Singapore 639798 · Bytedance Inc. +2

Vision-Language-Action Models Visual Token Pruning Visual Token Compression

Aug 13, 2026cs.CV

MergeOver: Post-Training Token Merging for Recursive Vision Transformers

Vision Transformers (ViTs) demonstrate exceptional performance in computer vision but suffer from large parameter counts and quadratic computational complexity, severely limiting their deployment on resource-constrained edge hardware. While recursive weight-sharing reduces parameter counts and token merging mitigates computational and memory bottlenecks, integrating these two paradigms without costly retraining is non-trivial, leaving this intersection largely unexplored. We propose MergeOver, a post-training approach that integrates Token Merging (ToMe) into the recursively weight-shared Sliced Recursive Transformer (SReT). Through an Unmerge tracking stack, constraint-safe merge-rate adjustment, and synchronised token-mass tracking across spatial permutations, MergeOver resolves the spatial and merging constraints of this integration. We further employ a stage-wise single-shot schedule that performs token reduction at the first block of each stage and maintains a fixed sequence length throughout its subsequent recursive iterations. Benchmarked on ImageNet-1K, our selected configuration reduces top-1 accuracy by 1.47 percentage points. On the GPU, it reduces peak activation memory by 37.3% and 38.4% at batch sizes 1 and 16, while throughput decreases by 21.7% at batch size 1 but increases by 21.7% at batch size 16. On a Raspberry Pi 5 (ARM CPU), it reduces latency by 2.4% and 17.6% at batch sizes 1 and 16. These results show that MergeOver can recover a meaningful part of the throughput and memory cost that recursive weight-sharing introduces, without retraining, and provides a baseline for combining token merging with hierarchical recursive transformers.

Junseo Kim, Uraz Odyurt, Amirreza Yousefzadeh

Computer Architecture for Embedded Systems, University of Twente Enschede, The Netherlands

Vision Transformer Efficient ViTs Visual Token Merging Image Classification Visual Token Compression

Aug 11, 2026cs.CV

When Vision Becomes Text: Visual Token Pruning via Cross-Modal Residual Guidance in VLMs

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.

Congyang Ou, Ruike Song, Yang Zhou +3

Northwestern Polytechnical University · Chongqing University · MiLM Plus, Xiaomi Inc.

Efficient VLM Inference Large Vision-Language Models Visual Token Pruning Visual Token Compression

Aug 10, 2026cs.HC

Can Coding Agents Solve Repository-Level Issues with Rendered Code? An Exploratory Study of Visual Representations

Visual modality has recently been explored as a way to compress textual tokens, including rendering code as images for static code understanding. We study whether this representation can serve as operational context for agentic coding, where an agent must navigate repositories, edit source files, and verify executable patches. Using SWE-bench Verified, we evaluate rendered code in repository-level repair workflows and introduce controlled agent settings to separate unguided repository exploration from more structured repair stages. Our results show a mixed picture. Rendered code consistently reduces prompt-token cost, but the savings do not increase linearly with the nominal visual compression ratio. It largely preserves end-to-end repair accuracy, but does not overcome the performance limits of the underlying model or agent architecture, and can become unstable under aggressive compression. Further analysis suggests that visual code is most useful when raw source reading is a major bottleneck; once repository localization is structured, much of the remaining cost comes from patch--test trial-and-error, where visual compression has limited leverage. Overall, our study positions rendered code as a viable but conditional compression mechanism for realistic coding agents.

Weijie Liang, Yuanfeng Song, Xing Chen +3

The Hong Kong University of Science and Technology, Hong Kong, China · ByteDance, China

Automated Program Repair AI Coding Agents Repository-Level Code Generation Visual Token Compression

Aug 10, 2026cs.CV

Not All Visual Tokens Are Equally Safe to Remove:Consequence-Sensitive Visual Token Compression

Visual token compression for vision--language models (VLMs) has largely relied on criteria such as attention, redundancy, and uncertainty to maximize average accuracy under a fixed compute budget, implicitly assuming that all errors carry equal cost. However, the consequence of an incorrect prediction on downstream tasks is rarely symmetric: misreading an invoice amount can be far more costly than misclassifying a background color. Motivated by this, we introduce consequence-sensitive visual token compression, which allocates visual computation across requests according to their potential error costs. Our method follows a calibrate-then-allocate procedure, estimating consequence-specific error-budget curves offline and applying the calibrated token budgets online using consequence signals available from question or task information. On a controlled within-task benchmark, high- and low-consequence questions are drawn from the same document images, so content alone cannot reveal which questions are costly to get wrong. In this setting, our method reduces high-stakes errors from 0.300 to 0.133 under the same total token budget, whereas a content-driven allocator performs no better than uniform allocation. Measuring how error rates change with token budget across different cost ratios, we derive an allocation frontier: uniform allocation is optimal when errors are equally costly, and token transfer toward high-consequence questions becomes increasingly beneficial as the cost gap grows. This allocation principle generalizes well across three dense vision-language benchmarks, two budget realization mechanisms (token deletion and resolution reallocation), two VLM architectures, and multiple token selection strategies. On a realistic mixed workload, consequence-sensitive allocation reduces cost-weighted error by 38% while achieving approximately 21% lower latency than full-resolution inference.

Jingbo Wen, Liang He, Mingyu Cao +4

1The University of Sydney · 2Tongji University · University of Surrey +3

Efficient VLM Inference Visual Token Compression

Aug 9, 2026cs.CV

Visual Token Codec: Unleashing Spatial Redundancy for ViT Feature Coding

Distributed deployment of large vision foundation models often partitions a ViT backbone and exchanges intermediate token features between computing nodes, making efficient feature compression critical under bandwidth and computation constraints. Existing ViT feature codecs typically flatten heterogeneous global and patch tokens into an L x C pseudo image, causing entropy models to mainly capture sequence-axis dependencies while overlooking the native two-dimensional patch-grid structure. In this paper, we show that ViT patch tokens retain strong local spatial correlations on the original grid. To exploit this structural prior, we propose the Visual Token Codec (VTC), a dual-path learned codec that separates global and patch tokens into dedicated coding paths. Global tokens are compressed with a lightweight factorized prior, whereas patch tokens are encoded on the patch-token grid using a spatial-channel context entropy model. To support intermediate-layer compression and practical rate adaptation, VTC further incorporates feature-matching supervision after subsequent ViT blocks and variable-rate modules within a single codec. Experiments on DINOv2 and SAM3 show that VTC consistently outperforms representative ViT feature coding baselines on classification, segmentation, and detection tasks. At 90% of uncompressed-feature performance, VTC reduces bitrate by 15.7x-37.4x across these tasks. We further provide intermediate-layer rate-utility analyses for practical transmission- and storage-oriented deployment scenarios.

Donghui Feng, Fengxi Zhang, Changsheng Gao +6

Visual Token Compression

Aug 9, 2026cs.CV

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. We introduce AnchorFold, a training-free focus-then-fold framework for document-side index compression. AnchorFold applies Recursive Attention Propagation over visual self-attention graphs, performing multi-step propagation within each attention head and integrating scores across heads and layers. The focus stage selects the highest-centrality tokens as anchors. The fold stage assigns remaining tokens to their most similar anchors in the normalized retrieval space and summarizes each anchor-centered group through centrality-weighted aggregation. This preserves non-anchor contributions while concentrating capacity on structurally important tokens. Across ViDoRe v1/v2 and REAL-MM-RAG with three diverse retrieval backbones, AnchorFold consistently outperforms all evaluated training-free baselines at

γ\leq 0.20

. On ViDoRe v1/v2, it retains 98.3% of full-index NDCG@5 on average at

5\times

compression, achieving near-lossless compression, and 92.4% at

20\times

compression.

Haoyu Zuo, Yibo Yan, Xin Zou +4

Hong Kong University of Science and Technology (Guangzhou) · Alibaba Cloud Computing · Hong Kong University of Science and Technology

Multi-Vector Retrieval Visual Document Retrieval Visual Token Compression

Aug 9, 2026cs.CV

Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation

Vision-language models offer a promising path toward automating radiology report generation, but applying them to full 3D CT volumes poses substantial computational challenges. Modern foundation vision encoders (VEs) can produce tens of thousands of vision tokens per scan, making the visual sequence passed to the large language model (LLM) a primary computational bottleneck. Vision-to-language projectors can compress this sequence to reduce computation, but may discard clinically relevant detail; conversely, effective compression can accommodate higher-resolution inputs while keeping the downstream token count fixed. How this vision-token budget should be allocated across input field of view, spatial resolution, and vision-to-language projection therefore remains an open design question. We systematically evaluate four heterogeneous VEs (CNN- and ViT-based), five token-reducing projectors at up to 64x compression alongside a non-reducing MLP projector baseline, and five instruction-tuned LLMs (1.7B--4B) on two large-scale CT report datasets (CT-RATE and Merlin). At matched LLM token budgets, anatomy-guided region of interest cropping is the most consistent strategy, improving clinical macro F1 in 19 of 20 settings by +3.7 points on average for the 3D ViT Primus encoder and +1.1 for the slice-based 2D ViT Curia encoder. Increasing input resolution further is strongly projector-dependent: the PerceiverResampler, paired with higher-resolution Curia features, yields the strongest configuration in the resolution study on both datasets. Our best configurations achieve state-of-the-art clinical macro F1 on the test sets, reaching 49.5 on CT-RATE and 49.0 on Merlin. Code and models will be published upon publication.

Jonathan Suprijadi, Raphael Stock, Moritz Langenberg +10

Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany

Radiology Report Generation Radiology VLMs Computed Tomography Visual Token Compression

Aug 6, 2026cs.CV

KVAE: Family of Tokenizers for Multimodal Generative Models

Latent diffusion modeling (LDM), a prominent paradigm, utilizes tokenizers to map input signal to compressed representation. This dependency positions tokenizer as an integral part of generation process itself, since it affects learning speed, quality of synthesized samples and lay foundation for later applications. This report presents series of KVAE tokenizers for audio, image and video, all designed for subsequent text-conditioned generation: KVAE-Audio, a continuous full-band 48 kHz tokenizer with a 50 Hz latent of 64 channels; KVAE-3D -- two causal video tokenizers for 4x16x16 and 4x8x8 compression; KVAE-2D, an image model, compressing input by factor of 8 with 32 channels. We demonstrate that reconstruction (PSNR, LPIPS, PESQ, etc.) and generation results on objective (Frechet Distance, CLIP score, CLAP score, etc.) and subjective (side-by-side evaluation) metrics matches or surpasses frontier opensource tokenizers, such as VAEs from Wan-2.2, HunyuanVideo-1.5, FLUX.2, MovieGen, StableAudio and MMAudio. Considering difficulty of development, we share with community training details, model selection method and ablation on design choices. The code is publicly available at https://github.com/kandinskylab/kvae and https://github.com/kandinskylab/kvae-audio.

Andrey Shutkin, Denis Parkhomenko, Ivan Kirillov +11

Kandinsky Lab

Variational Autoencoders Audio Token Compression Audio Tokenization Multimodal Token Compression Video Token Compression Visual Token Compression

Aug 5, 2026cs.CV

Persistent Object Narratives for Token-Efficient Video Language Models

Video large language models (Video-LLMs) have made strong progress in open-ended video understanding. However, their visual interfaces remain token-intensive and provide limited explicit structure for linking recurring object evidence across time. We introduce SlotNarrative, a slot-based interface that organizes a video into persistent object narratives represented by compact object-state tokens. Rather than compressing frame-wise features before establishing temporal correspondence, SlotNarrative first groups visual features into object-like slots and then associates recurring observations with clip-level object entries through a lightweight, parameter-free memory that integrates multiple complementary matching cues. Each retained entry is serialized into two token types: an identity token that summarizes persistent object appearance and a set of state tokens that encode segment-level appearance, geometry, visibility, and trajectory information. This design yields an interface of only 144 allocated visual-token positions for a frozen Video-LLM, independent of the number of sampled frames. Across multiple datasets, SlotNarrative achieves a favorable trade-off between accuracy and visual-token count compared with prior compact Video-LLM interfaces. Experimental results establish persistent object narratives as a compact, structured, and temporally organized visual interface for Video-LLMs. Our code will be made publicly available.

Junzhe Chen, Siyuan Meng, Xiaojie Guo

Tianjin University

Visual Tokenization Video-Language Models Video Representation Learning Visual Token Compression Temporal Video Understanding

Aug 5, 2026cs.CV

HiSC: Hierarchical Spatial Clustering Token Compression for Efficient 3D Scene Understanding

3D vision-language models (3D VLMs) enable spatial reasoning over multi-view scenes but suffer from substantial token redundancy due to duplicated observations and large uninformative regions, leading to high computational cost. Although visual token compression has shown promise in accelerating 2D VLMs, it fails to capture the structured nature of 3D scenes and leads to incomplete spatial coverage and loss of fine-grained details. In this paper, we propose \textbf{HiSC}, a training-free framework for hierarchical spatial clustering token compression in 3D VLMs. HiSC lifts token compression from token-level selection to cluster-level processing by organizing tokens into spatially grounded clusters using joint geometric and semantic cues. Specifically, we first introduce a \textbf{spatial graph-based merging (SGraM) strategy} that models cross-view redundancy as spatial connectivity and consolidates physically consistent regions, effectively merging extremely similar redundant tokens prior to LLM inference. We then propose a \textbf{spatial clustering-based pruning (SCluP) paradigm} within LLM inference, which performs hierarchical compression across clusters and within clusters, preserving object instance completeness while retaining fine-grained details for important regions. Extensive experiments on diverse 3D reasoning benchmarks show validate the effectiveness of HiSC, particularly under high visual token pruning ratios. Besides, HiSC achieves over 90% token reduction with minimal performance degradation. Code is accessible at https://github.com/elecreak/HiSC.

Jiuhe Qu, Yingping Liang, Ying Fu

Beijing Institute of Technology Beijing, China

3D Spatial Reasoning Visual Token Pruning Visual Token Compression 3D Scene Understanding 3D VLMs

Aug 5, 2026cs.CV

CARVE: Cross-Slice Anisotropic Reallocation of Visual Evidence for Efficient 3D Medical Volume Understanding

Slice-based MLLMs leverage mature 2D encoders by representing 3D volumes as sequences of 2D slices. However, this slice-wise formulation produces thousands of visual tokens that burden the LLM backbone, many of which capture overlapping visual evidence across adjacent slices. To understand how effectively a growing visual token budget improves performance, we perform scaling analyses on two 3D medical VQA benchmarks and find diminishing returns: cost keeps rising while accuracy saturates, and improving in-plane resolution is more effective than adding slices at comparable budgets. The budget should therefore be allocated more selectively rather than simply enlarged, yet most token compression methods are designed for 2D images or videos, where redundancy arises from spatial layout or temporal motion rather than from near-duplicate content along the depth axis. We present CARVE, a training-free framework that compresses visual tokens prior to LLM inference and casts token reduction as budget-constrained 2.5D allocation. CARVE partitions the depth axis into coherent windows and allocates tokens non-uniformly according to normalized cross-slice evidence. Under a shared budget, CARVE builds spatial anchors on representative slices and retrieves locally varying evidence from the full volume, then merges remaining eligible tokens into nearby anchors within each window. Removing roughly 80% of the visual tokens on Hulu-Med-7B, CARVE leads all compression baselines on every AMOS-MM report-generation metric, with 6.2 points higher retention of full-token quality than the strongest baseline, and preserves 98.1% of full-token performance across three VQA benchmarks.

Zhenyu Yi, Qiang Hu, Zhenhao Li +3

School of Biomedical Engineering, Shanghai Jiao Tong University · 2Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology

3D Medical Imaging Medical VQA Multimodal Token Compression Visual Token Compression

Aug 4, 2026cs.CV

RUTA: Principled Visual Token Allocation via Rate-Utility Optimization

High-resolution images and long videos provide vision-language models with rich context for multimodal reasoning and fine-grained perception, but the resulting long visual token sequences make large language model-side computation and memory costly. Existing visual token reducers often operate at prescribed rates, while recent methods adapt token counts across inputs using method-specific learned thresholds or importance predictors. We introduce RUTA, a principled Rate-Utility Token Allocation method that performs pre-LLM reduction by jointly learning which tokens to retain and how many to allocate to each image-query pair. RUTA constructs query-conditioned candidate tokens and predicts a retention probability for each candidate. During training, these probabilities parameterize independent Bernoulli gates, while their sum provides a differentiable training-time estimate of the token count for each pair. Retained tokens serve as anchors that aggregate information from non-retained tokens according to semantic affinity and spatial proximity. RUTA is optimized with a penalized rate-utility objective that balances downstream task loss against expected token usage. Averaged across five benchmarks and measured relative to each backbone's full-token baseline, RUTA uses only

2.0\%

and

4.2\%

of visual tokens while preserving

88.2\%

and

94.4\%

of task performance on LLaVA-NeXT-7B and Qwen3-VL-8B, respectively.

Jian Zou, Xiaoyu Xu, Zhihua Wang +3

City University of Hong Kong · Google Inc.

Efficient VLM Inference Visual Token Pruning Visual Token Compression

Aug 4, 2026cs.CV

OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models

Omni-modal large language models (Omni-LLMs) have achieved remarkable performance on audio-visual understanding tasks, but processing long and highly redundant visual and audio token sequences incurs substantial computational overhead, demanding aggressive token compression for efficient deployment. Existing methods often degrade at low token budgets: pre-LLM compression may discard structurally important and globally distributed evidence, whereas inner-LLM compression often underexploits query-conditioned audio-visual collaboration. To address these limitations, we propose OmniPack, a training-free framework that coordinates structural compression before the LLM with task-relevant semantic refinement within the LLM. Before the LLM, OmniPack removes structural redundancy through modality-specific importance, global coverage, and similarity-aware merging. After sufficient multimodal interaction, it further consolidates diverse, task-relevant representations through textual guidance and audio-visual collaboration. Extensive experiments on five benchmarks with three Omni-LLM backbones demonstrate that OmniPack consistently achieves the best performance-efficiency trade-off across diverse retention ratios, outperforming all existing methods. Notably, on Qwen2.5-Omni-7B, OmniPack preserves 98.0% of the original performance while reducing FLOPs to 16.7%, and still retains 92.9% of the original performance with only 6.8% of the original FLOPs.

Wanshun Su, Yang Shi, Feihu Liu +10

Northwestern Polytechnical University · Peking University · Alibaba Group +1

Efficient Multimodal Inference Audio Token Compression Multimodal Large Language Models Multimodal Token Compression Visual Token Compression

Aug 4, 2026cs.CV

When Do Fewer Visual Tokens Accelerate Multimodal Inference? A Break-Even Study Across Decision Locations and Hardware

Fewer visual tokens do not guarantee lower end-to-end latency. We evaluate break-even with a reproducible protocol that accounts for decision overhead, shared work, and the operators each policy can avoid. A stage-level decomposition reconciles these components with measured end-to-end latency. In a 30-example pilot, the two tested autoregressive probes remain slower than Full despite state reuse. A lightweight post-vision predictor yields paired confidence intervals below zero on RTX 3090 and A100 and remains significant after a conservative all-pairs Holm correction. A pre-vision image-size rule also yields intervals below zero on both GPUs, although neither comparison remains significant after the same correction. Pre-vision routing has a structural opportunity unavailable to post-vision pruning: it can avoid preprocessing and vision encoding. On A100, this opportunity outweighs a nearly eightfold larger downstream token reduction by the post-vision policy. Reported quality is conditional on examples answered correctly by Full and is not benchmark accuracy.

Hao Dou, Ruiwen Tian

Harbin Institute of Technology, Harbin, China

Efficient VLM Inference Visual Token Pruning Visual Token Compression

Aug 3, 2026cs.CV

Messages, Not Tokens: Grounded Coresets for Faithful VLM Compression

Modern vision language models (VLMs) turn high-resolution images into long sequences of visual tokens. Every token traverses the language decoder and persists in its prompt KV cache, inflating inference cost and motivating aggressive visual compression. Existing score-based methods assign each token an independent importance score and retain the Top-K. However, text queries consume collective, signed attention messages from the visual population, not isolated patches. Consequently, equally sized Top-K sets can repeatedly cover one salient region, omit sparse but complementary evidence and discard information carried by the removed population. We therefore formulate faithful visual compression as constructing a compact coreset for decoder messages, and introduce our training-free Grounded Message Coreset Pruning (GMC) which jointly allocates support across query-grounded, appearance, and coordinate-aware evidence, then transports discarded states into selected representatives at their original multimodal positions before physical compaction and native attention resume. This decomposes faithful compression into two coupled components, including selecting carriers that cover the required message modes and realizing the signed population message on those carriers. We further derive bounds connecting their errors to signed-message distortion, visual innovation, and candidate-margin stability. Experiments across multiple VLM families and diverse benchmarks demonstrate strong performance, with GMC-H2 retaining 97.78% Full-relative mean capability on Qwen2.5-VL-7B using 80.2% fewer visual tokens, while GMC-L16 reaches 100.36%. Controlled interventions verify that collective support and population realization jointly drive these gains.

Long Qian, Jiaqi Wei, Bingke Zhu +2

Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Engineering, Cardiff University, Cardiff, United Kingdom · School of Future Technology, University of Chinese Academy of Sciences, Beijing, China +1

Efficient VLM Inference Coreset Selection Faithfulness in VLMs Visual Token Pruning Visual Token Compression

Aug 3, 2026cs.CV

Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression

Vision-Text Compression (VTC) renders long texts into images and encodes them through the vision encoder (ViT), compressing thousands of text tokens into far fewer visual tokens. However, since the ViT is pretrained predominantly on natural images, it captures visual attributes (glyphs, font sizes, layout) rather than linguistic semantics, causing rendered-image representations to diverge from native-text representations. We term this cross-path inconsistency and show, via rendering perturbation experiments, that it is a critical yet overlooked bottleneck of VTC. We propose SPIRAL (Self-improving Path Integration and Realignment), a self-supervised alignment framework that closes this gap using only the model's own text-path behavior as supervision, requiring no external teachers or additional annotations. SPIRAL operates at two complementary granularities: token-level on-policy distillation (OPD) for local faithfulness, and sequence-level preference optimization (DPO) for global coherence. On VTCBench, SPIRAL improves the overall score of Qwen3-VL-8B from 35.10 to 54.02, approaching the native text-input performance (55.60) and outperforming models up to 30x larger. The two granularities exhibit complementary strengths: OPD excels at retrieval and is sample-efficient, while DPO is stronger on reasoning and memory and scales better with data. SPIRAL's benefits also generalize to out-of-domain benchmarks, confirming that effective VTC hinges on aligning rendered-image representations back to native-text semantics.

Tianyu Liang, Xiangxi Zheng, Yilin Wang +1

Southeast University Nanjing, China · Nanjing University Nanjing, China · Zhejiang University Hangzhou, China +1

VLM Adaptation Multimodal Token Compression Vision-Language Alignment Visual Token Compression

Aug 3, 2026cs.CV

Decoupling semantics from vision: A framework for faithful visual-text compression evaluation

Recent visual-text compression (VTC) methods, typified by DeepSeek-OCR, report impressive high token compression ratios for long-context modeling tasks by leveraging text-to-image rendering. However, existing evaluation protocols heavily rely on downstream task performance. Such evaluation metrics fail to accurately measure text preservation due to the strong inherent linguistic priors of Multimodal Large Language Models (MLLMs). In this work, we introduce a new evaluation framework that decouples MLLMs' capabilities to faithfully assess VTC quality. Within this framework, we further introduce the ZeroSense Benchmark to ensure low semantic correlation of testing samples. By eliminating textual dependencies, our benchmark guarantees that the evaluation results are purely reflective of VTC quality, unaffected by the semantic inference capabilities of downstream models. Extensive experiments across multiple datasets demonstrate that VTC quality and downstream task accuracy diverge significantly, highlighting the necessity of our decoupled evaluation framework.

Yonghan Gao, Zehong Chen, Lijian Xu +3

Shenzhen University of Advanced Technology · Shenzhen Technology University

Multimodal Model Evaluation Visual Token Compression

Aug 3, 2026cs.CV

CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language Models

In video understanding, vision-language models (VLMs) must ingest massive numbers of visual tokens, causing the computational and memory cost of the prefill stage to rise sharply. Such visual sequences are highly redundant along the spatio-temporal dimension, yet a high compression ratio is often accompanied by the loss of critical details. Existing token-compression methods either employ heuristic, training-free compression with limited content adaptivity or introduce additional modules that require expensive alignment training, leaving the trade-off between efficiency and adaptivity unresolved. To alleviate this limitation, we propose CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens. CRAFT recursively merges tokens by decoupling parameter-free token selection from learnable token fusion: global similarity determines which tokens to merge, while a position-aware weighting module and a content-adaptive channel-wise gate learn how to fuse them. The whole compression pipeline is query-agnostic. Because every retained token is a linear combination of the original tokens, CRAFT preserves their true spatio-temporal coordinates and stays aligned with the pre-trained language model's input distribution. Experiments on multiple representative video benchmarks show that CRAFT consistently outperforms prior state-of-the-art token-compression methods. At about

8\times

compression, it retains roughly

97\%

of the backbone's average accuracy and shows significant efficiency improvement.

Yu Chen, Xiaohong Li, Xiaole Wang +3

1Evermind · 2Shanda Group · 3Peking University

Efficient VLM Inference Large Vision-Language Models Video Token Compression Visual Token Merging Visual Token Compression

Aug 2, 2026cs.CV

Rethinking Video Token Compression with a Global Codebook: Learning Once, Compressing Everywhere

Video large language models (Video-LLMs) represent videos as dense sequences of visual tokens, whose length grows with the temporal and spatial extent of the input. These tokens often contain substantial redundancy arising from repeated visual patterns, leading to unnecessary computation in the subsequent language-model processing. Existing token compression methods, including pruning and merging, perform compression online during inference, repeatedly incurring additional computation for each input video and often relying on model-specific designs that limit their generality, we instead rethink this paradigm by shifting the costly compression process offline. We propose \textbf{ONCE}, a plug-in video token compression framework that introduces an offline-to-online paradigm: a frequency-aware global codebook is learned once in the visual feature space and reused for lightweight online compression through codebook lookup and aggregation, reducing repeated per-video computation and the need for model-specific compression designs. Extensive experiments across multiple video understanding benchmarks and against diverse compression baselines demonstrate that our approach achieves a strong accuracy-efficiency trade-off, maintaining competitive performance while achieving the lowest inference latency among compared methods.

Jiayang He, Tianling Xu, Diancheng Kang +4

Southern University of Science and Technology · Imperial College London · Jilin University

Efficient VLM Inference Video-Language Models Video Token Compression Visual Token Compression

Aug 1, 2026cs.CL

RAGOCR: Optical Compression of Retrieval-Augmented Text via Visual Representation

Retrieval-Augmented Generation (RAG) has become essential for knowledge-intensive question answering, yet scaling RAG pipelines remains challenging due to the prohibitive computational cost of processing lengthy retrieved contexts. Existing compression approaches face a fundamental trade-off: hard compression methods operate online in a query-aware fashion but achieve only modest compression rates and typically require fine-tuning the generative model, while soft compression methods attain higher ratios but rely on costly offline encoding that is entirely agnostic to the input query. To bridge this gap, we introduce RAGOCR, a novel framework that compresses retrieved documents into compact visual representations conditioned on the input query. To further balance compression rate and information fidelity, we introduce a query-aware dynamic resolution mechanism that adaptively allocates visual granularity based on each document's estimated relevance and complexity: highly relevant passages are rendered at higher resolution to preserve fine-grained details, while peripheral documents are aggressively compressed at lower resolution. Experiments on five QA benchmarks using the MedOmniKB retrieval corpus demonstrate that RAGOCR surpasses naive RAG by over 15% in accuracy while requiring only one-eighth the number of input tokens, and consistently outperforms both hard and soft compression baselines across varying retrieval depths.

Jiayang Yu, Jialun Zhong, Lei Zou

Wangxuan Institute of Computer Technology, Peking University Beijing, China

Multimodal RAG Retrieval-Augmented Generation Multimodal Token Compression Visual Token Compression

Jul 31, 2026cs.CV

ORCA: ORgan-Centroid Aggregation for Training-Free 3D CT Visual Token Compression

A 3D CT scan entering a vision-language model produces a long sequence of visual tokens, often thousands to tens of thousands per volume, and this sequence must be compressed before a language model can consume it. Token compression is well studied in general vision, but little of it targets 3D CT specifically. A common baseline is grid average, which pools regular grid cells and can blend distinct anatomy, lesion, and air into one token. We present \textbf{ORCA} (ORgan-Centroid Aggregation), a token compressor for 3D CT. It merges adjacent tokens with organ guidance and adds a sinusoidal encoding of each region's centroid to preserve spatial layout. This preserves the anatomical information a downstream model needs. ORCA is training-free and plug-and-play, producing an adjustable token set without any model change or text query. We evaluate it across two datasets (CT-RATE and Merlin) and five encoders. The evaluation spans two task types: attribute prediction over five families (size, density, location, texture, and disease) and text generation (visual question answering and report generation). At matched token budgets, ORCA improves consistently over existing compression methods. It shrinks the visual context

64\times

and its KV-cache

50\times

, and is

31\times

faster to process each volume. Code released at https://github.com/renjie-liang/ORCA-3DCT.

Renjie Liang, Zijian Xu, Jinqian Pan +6

University of Florida, Gainesville, FL, USA · University of Southern California, Los Angeles, CA, USA · National University of Singapore, Singapore

Medical VLMs Visual Token Merging Computed Tomography Visual Token Compression

Jul 30, 2026cs.CV

ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding

Streaming video understanding requires models to continuously retain useful visual evidence before future questions are known. Existing approaches primarily manage the growing visual context according to token importance, temporal redundancy, or segment-level relevance, but rarely organize evidence around objects that persist and evolve over time. Thus, in this paper, we introduce ObjectStream, a training-free framework that treats latent objects as memory anchors for streaming video understanding. ObjectStream induces spatially coherent latent objects directly from frozen Video-LLM representations, links them across frames into persistent anchors, and maintains their histories under a bounded memory budget, without requiring external object detectors or segmentation models. Built on these anchors, ObjectStream preserves three complementary forms of evidence: persistent object histories, transient object changes, and recent visual context. This design enables existing Video Large Language Models (Video-LLMs) to reason over object identities, interactions, and state changes while leaving the underlying model unchanged. Extensive experiments on online streaming and offline long-video benchmarks demonstrate both effectiveness and efficiency. In online streaming evaluation, ObjectStream improves Qwen2.5-VL-7B by 10.0 points on OVO-Bench Real-Time Visual Perception, while reducing peak GPU mem-ory and TTFT by approximately 50%. On offline long-video benchmarks, it surpasses the full-token baseline while discarding 82.5% of visual tokens. These results highlight latent objects as a practical and effective organizing principle for compact streaming video memory.

Mingkang Dong, Muxin Pu, Jie Li +8

Universiti Malaya · Monash University · SJTU +5

Memory-Augmented VLMs Streaming Video Understanding Long-Video Understanding Memory-Augmented Video Understanding Visual Token Compression

Jul 30, 2026cs.CV

Calibrate Before Reason: Robust Visual Token Reduction against Semantic Drift in VLMs

Large Vision-Language Models (VLMs) suffer from prohibitive inference overhead due to long sequences of visual tokens. However, existing visual token reduction methods mainly improve efficiency by pruning or compressing redundant tokens without examining whether the resulting representation remains semantically consistent with the original representation. Mapping the original N-token visual sequence to K tokens may discard, dilute, or misassign critical visual cues, triggering severe semantic drift that deviates the VLM's understanding. In this paper, we first introduce the principle of 'Calibrate Before Reason' to visual token reduction and propose CaRe, a training-free robust framework that calibrates compact visual representations before reasoning to preserve semantic fidelity in VLMs. CaRe consists of two mutually complementary modules: 1) Perturbation-Robust Calibration Anchoring, which identifies calibration anchors with stable model-side influence under multi-directional perturbations; 2) Confidence-Gated Token Calibration, which extracts reliable calibration signals from unselected tokens and injects them into anchors. Extensive evaluations across diverse VLM architectures and benchmarks verify that CaRe outperforms state-of-the-art token reduction baselines. While pruning 94.4% of visual tokens, our method retains 96.4% of the original full-token performance, delivering up to 2.30 times faster end-to-end inference speed relative to unpruned vanilla models.

Jiasheng Li, Zhong Ji, Yan Zhang +1

Tianjin University, Tianjin, China · Tsinghua University, Beijing, China

VLM Robustness Efficient VLM Inference Visual Token Compression

Jul 29, 2026cs.CV

MedARC: Training-Free Adaptive Redundancy Compression of Visual Tokens for 3D Medical Vision-Language Models

Integrating 3D medical images with vision-language models (VLMs) holds substantial promise for computer-aided diagnosis. However, volumetric images generate prohibitively long visual-token sequences with considerable spatial and inter-slice redundancy. Existing token compression methods typically apply uniform reduction or rely on a single importance signal, increasing the risk of removing regions that are clinically relevant to the query or structurally distinctive. To address this limitation, we propose MedARC, a unified, training-free framework for Adaptive Redundancy Compression of visual tokens in 3D medical VLMs. MedARC estimates token importance by integrating three complementary cues: self-attention from the VLM vision encoder, which reflects the model's intrinsic visual focus; similarity between projected visual tokens and text embeddings, which identifies query-relevant regions; and deviations of local visual foundation model features from the volume-level feature center, which highlight structurally distinctive anatomy. The resulting importance distribution guides a saliency-aware merging strategy that preserves informative tokens while consolidating redundant ones rather than simply discarding them. Experiments on CT-RATE and MR-RATE show that MedARC reduces visual-token overhead and inference time while preserving or improving diagnostic performance. Its multi-cue scoring cost is outweighed by the savings from processing fewer tokens, with greater benefits expected for larger language models.

Yitao Zhu, Mengjun Liu, Yingji Fu +2

Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong · School of Integrated Circuits and Electronics, Beijing Institute of Technology, China · 3Mental Health Research Center, The Hong Kong Polytechnic University, Hong Kong +1

Efficient VLM Inference Medical VLMs Multimodal Token Compression Visual Token Compression 3D VLMs

Jul 27, 2026cs.CV

MAViE: A Multi-scale Adaptive Vision Encoder for Fine-grained Visual Perception and Efficient Multimodal Reasoning

Vision-language models commonly project all tokens produced by a pretrained vision encoder into a large language model. However, final-layer features can discard text, local attributes, and spatial relationships, while high-resolution inputs substantially increase context length and inference latency. We introduce \method, a Multi-scale Adaptive Vision Encoder. \method uses position-dependent gates to fuse shallow, intermediate, and deep features from a vision Transformer, preserving global semantics while enhancing edges, text, and local structure. It then performs question-conditioned token routing according to question relevance, local information content, global semantics, and spatial coverage, with a token budget that adapts to image complexity. To mitigate compression loss, we further introduce full-to-compressed representation distillation and a spatial diversity regularizer. In an illustrative simulation under a unified 7B language-model framework, \method reduces the average number of SigLIP-SO400M visual tokens from 729 to 146 (approximately 80.0%) and improves the mean score on VQAv2, GQA, TextVQA, ScienceQA-IMG, and MMBench by 2.2 percentage points, while reducing single-image time to first token from 228,ms to 129,ms. We provide the full model design and evaluation protocol. All reported numbers currently serve only as placeholders for paper organization and experimental design; formal claims require real training runs, independent replications, and official benchmark evaluation.

Shaofei Lei

Efficient VLM Inference Multi-Scale Feature Fusion VLM Reasoning Visual Token Compression

Jul 27, 2026cs.AI

GOTS: Greedy Orthogonal Token Selection for High-Resolution Vision-Language Models

Modern vision-language models (VLMs) increasingly rely on dynamic or high-resolution visual encoding, producing thousands of visual tokens that substantially increase downstream language-model inference cost. Existing token-reduction methods assess token utility through token-wise importance, query relevance, coverage, pairwise diversity, or subset-level objectives. Our key insight is to view visual token reduction through selected-span complementarity: instead of scoring a token in isolation or through pairwise relations, we assess how much of its feature is orthogonal to the span of the already retained subset. Based on this perspective, we propose Greedy Orthogonal Token Selection (GOTS), a training-free and query-agnostic method. At each step, GOTS selects the token with the largest residual energy orthogonal to the current retained span. This rule exactly maximizes the one-step augmented Gram determinant among candidate additions, giving each greedy step a precise local geometric guarantee for subset expansion. Across five high-resolution VLM backbones from the Qwen-VL and InternVL families and eleven diverse benchmarks, GOTS achieves higher average performance retention than the strongest evaluated baselines, and a controlled OCRBench study shows that it reduces model-side time-to-first-token after accounting for selection overhead. Code is available at https://github.com/newLLing/GOTS.

Jun Ling, Tao Huang, Junzhuo Liu +2

School of Computer Science and Engineering, University of Electronic Science and Technology of China

Efficient VLM Inference Large Vision-Language Models Visual Token Pruning Visual Token Compression