Visual Token Pruning

Ask about this topic

Overview

Visual token pruning studies how to remove or merge image and video patches before or inside vision transformers and vision-language models, reducing computation and memory for tasks such as visual question answering, video understanding, document reading, and robot control. Methods use attention or text-query relevance, feature diversity and spatial coverage, and signals such as entropy, spectral structure, or geometry; learned selectors and adaptive budgets choose different tokens or compression rates for different inputs. Pruning can happen before visual encoding, across language-model layers, or during video processing, and is evaluated on both task benchmarks and practical measures such as prefill latency, FLOPs, and memory. The central tension is that a token that seems redundant early may become important for later reasoning, while selection overhead and hardware execution can prevent fewer tokens from yielding faster end-to-end inference.

Latest papers

CardsList

276 papers43 papers in the last four weeks, up 59% on the four weeks before. 0.2% of all new papers.

Mar 16, 2026

Look Before Acting: Enhancing Vision Foundation Representations for Vision-Language-Action Models

Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for robotic manipulation, in which reliable action prediction critically depends on accurately interpreting and integrating visual observations conditioned on language instructions. Although recent works have sought to enhance the visual capabilities of VLA models, most approaches treat the LLM backbone as a black box, providing limited insight into how visual information is grounded into action generation. Therefore, we perform a systematic analysis of multiple VLA models across different action-generation paradigms and observe that sensitivity to visual tokens progressively decreases in deeper layers during action generation. Motivated by this observation, we propose DeepVision-VLA, built on a Vision-Language Mixture-of-Transformers (VL-MoT) framework. This framework enables shared attention between the vision foundation model and the VLA backbone, injecting multi-level visual features from the vision expert into deeper layers of the VLA backbone to enhance visual representations for precise and complex manipulation. In addition, we introduce Action-Guided Visual Pruning (AGVP), which leverages shallow-layer attention to prune irrelevant visual tokens while preserving task-relevant ones, reinforcing critical visual cues for manipulation with minimal computational overhead. DeepVision-VLA outperforms prior state-of-the-art methods by 9.0% and 7.5% on simulated and real-world tasks, respectively, providing new insights for the design of visually enhanced VLA models.

Yulin Luo, Hao Chen, Zhuangzhe Wu +10

State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University · The Chinese University of Hong Kong · Simplexity Robotics

Spatial Grounding for VLA ModelsVision-Language-Action ModelsVision-Language ModelsRobotic ManipulationVisual Token Pruning
AskPDF
Mar 16, 2026

Balancing Saliency and Coverage: Semantic Prominence-Aware Budgeting for Visual Token Compression in VLMs

Large Vision-Language Models (VLMs) achieve strong multimodal understanding capabilities by leveraging high-resolution visual inputs, but the resulting large number of visual tokens creates a major computational bottleneck. Recent work mitigates this issue through visual token compression, typically compressing tokens based on saliency, diversity, or a fixed combination of both. We observe that the distribution of semantic prominence varies substantially across samples, leading to different optimal trade-offs between local saliency preservation and global coverage. This observation suggests that applying a static compression strategy across all samples can be suboptimal. Motivated by this insight, we propose PromPrune, a sample-adaptive visual token selection framework composed of semantic prominence-aware budget allocation and a two-stage selection pipeline. Our method adaptively balances local saliency preservation and global coverage according to the semantic prominence distribution of each sample. By allocating token budgets between locally salient regions and globally diverse regions, our method maintains strong performance even under high compression ratios. On LLaVA-NeXT-7B, our approach reduces FLOPs by 88% and prefill latency by 22% while preserving 97.5% of the original accuracy.

Jaehoon Lee, Mingi Jung, Soohyuk Jang +3

Interdisciplinary Program in AI, Seoul National University · Department of Electrical and Computer Engineering, Seoul National University · Department of Artificial Intelligence, Chung-Ang University

Efficient VLM InferenceVisual Token PruningVisual Token Compression
AskPDF
Mar 15, 2026

ASAP: Attention-Shift-Aware Pruning for Efficient LVLM Inference

While Large Vision-Language Models (LVLMs) demonstrate exceptional multi-modal capabilities, the quadratic computational cost of processing high-resolution visual tokens remains a critical bottleneck. Though recent token reduction strategies attempt to accelerate inference, such methods inadequately exploit attention values and fail to address token redundancy. More critically, they overlook the ``attention shift'' phenomenon inherent in LVLMs, which skews token attention scores. In this work, we propose ASAP, a novel training-free, KV-Cache-compatible pruning recipe that comprehensively addresses these limitations. First, we mitigate the attention shift by utilizing a dynamic bidirectional soft attention mask, ensuring the selection of genuinely informative tokens rather than naive attention-based selection. Second, we posit that high semantic redundancy within the token set degrades performance. We therefore introduce a weighted soft merging component that merges semantically similar tokens, preserving only the most feature-dense visual patches for subsequent layers. ASAP achieves virtually lossless compression of visual context, retaining 99.02% of the original LLaVA-NeXT-7B performance while aggressively slashing computational FLOPs by ~80%.

Surendra Pathak, Bo Han

George Mason University, Fairfax, VA, USA

Efficient VLM InferenceVisual Token PruningLVLM PruningVisual Token Compression
AskPDF
Mar 12, 2026

Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing

Multi-modal large language models (MLLMs) have advanced general-purpose video understanding but struggle with long, high-resolution videos -- they process every pixel equally in their vision transformers (ViTs) or LLMs despite significant spatiotemporal redundancy. We introduce AutoGaze, a lightweight module that removes redundant patches before processed by a ViT or an MLLM. Trained with next-token prediction and reinforcement learning, AutoGaze autoregressively selects a minimal set of multi-scale patches that can reconstruct the video within a user-specified error threshold, eliminating redundancy while preserving information. Empirically, AutoGaze reduces visual tokens by 4x-100x and accelerates ViTs and MLLMs by up to 19x, enabling scaling MLLMs to 1K-frame 4K-resolution videos and achieving superior results on video benchmarks (e.g., 67.0% on VideoMME). Furthermore, we introduce HLVid: the first high-resolution, long-form video QA benchmark with 5-minute 4K-resolution videos, where an MLLM scaled with AutoGaze improves over the baseline by 10.1% and outperforms the previous best MLLM by 4.5%. Project page: https://autogaze.github.io/.

Baifeng Shi, Stephanie Fu, Long Lian +10

UC Berkeley · NVIDIA · Clarifai +1

Efficient VLM InferenceVisual Token PruningTemporal Video UnderstandingVideo QA
AskPDF
Mar 12, 2026

ForensicZip: More Tokens are Better but Not Necessary in Forensic Vision-Language Models

Multimodal Large Language Models (MLLMs) enable interpretable multimedia forensics by generating textual rationales for forgery detection. However, processing dense visual sequences incurs high computational costs, particularly for high-resolution images and videos. Visual token pruning is a practical acceleration strategy, yet existing methods are largely semantic-driven, retaining salient objects while discarding background regions where manipulation traces such as high-frequency anomalies and temporal jitters often reside. To address this issue, we introduce ForensicZip, a training-free framework that reformulates token compression from a forgery-driven perspective. ForensicZip models temporal token evolution as a Birth-Death Optimal Transport problem with a slack dummy node, quantifying physical discontinuities indicating transient generative artifacts. The forensic scoring further integrates transport-based novelty with high-frequency priors to separate forensic evidence from semantic content under large-ratio compression. Experiments on deepfake and AIGC benchmarks show that at 10% token retention, ForensicZip achieves 2.97×2.97\times speedup and over 90% FLOPs reduction while maintaining state-of-the-art detection performance.

Yingxin Lai, Zitong Yu, Jun Wang +3

Great Bay University · Shenzhen University · Harbin Institute of Technology +1

Visual Token PruningVisual Token CompressionEfficient VLM InferenceDeepfake Detection
AskPDF
Mar 12, 2026

MedPruner: Training-Free Hierarchical Token Pruning for Efficient 3D Medical Image Understanding in Vision-Language Models

While specialized Medical Vision-Language Models (VLMs) have achieved remarkable success in interpreting 2D and 3D medical modalities, their deployment for 3D volumetric data remains constrained by significant computational inefficiencies. Current architectures typically suffer from massive anatomical redundancy due to the direct concatenation of consecutive 2D slices and lack the flexibility to handle heterogeneous information densities across different slices using fixed pruning ratios. To address these challenges, we propose MedPruner, a training-free and model-agnostic hierarchical token pruning framework specifically designed for efficient 3D medical image understanding. MedPruner introduces a two-stage mechanism: an Inter-slice Anchor-based Filtering module to eliminate slice-level temporal redundancy, followed by a Dynamic Information Nucleus Selection strategy that achieves adaptive token-level compression by quantifying cumulative attention weights. Extensive experiments on three 3D medical benchmarks and across three diverse medical VLMs reveal massive token redundancy in existing architectures. Notably, MedPruner enables models such as MedGemma-1.5 to maintain or even exceed their original performance while retaining fewer than 5% of visual tokens, thereby reducing visual-token overhead and validating the necessity of dynamic token selection for practical clinical deployment. Our code is available at https://github.com/CUHK-AIM-Group/MedPruner.

Shengyuan Liu, Zanting Ye, Yunrui Lin +6

Chinese University of Hong Kong · Westlake University · Southern Medical University +4

Efficient VLM Inference3D Medical ImagingMedical VLMsVisual Token Pruning
AskPDF
Mar 11, 2026

Language-Guided Token Compression with Reinforcement Learning in Large Vision-Language Models

Large Vision-Language Models (LVLMs) incur substantial inference costs due to the processing of a vast number of visual tokens. Existing methods typically struggle to model progressive visual token reduction as a multi-step decision process with sequential dependencies and often rely on hand-engineered scoring rules that lack adaptive optimization for complex reasoning trajectories. To overcome these limitations, we propose TPRL, a reinforcement learning framework that learns adaptive pruning trajectories through language-guided sequential optimization tied directly to end-task performance. We formulate visual token pruning as a sequential decision process with explicit state transitions and employ a self-supervised autoencoder to compress visual tokens into a compact state representation for efficient policy learning. The pruning policy is initialized through learning from demonstrations and subsequently fine-tuned using Proximal Policy Optimization (PPO) to jointly optimize task accuracy and computational efficiency. Our experimental results demonstrate that TPRL removes up to 66.7% of visual tokens and achieves up to a 54.2% reduction in FLOPs during inference while maintaining a near-lossless average accuracy drop of only 0.7%. Code is released at mypink{https://github.com/MagicVicCoder/TPRL}.

Sihan Cao, Jianwei Zhang, Pengcheng Zheng +7

School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China · School of Robotics and Advanced Manufacture, Harbin Institute of Technology, Shenzhen, China · College of Information and Control Engineering, Xi’an University of Architecture and Technology, Xi’an, China

Efficient VLM InferenceVisual Token PruningLVLM PruningVisual Token CompressionRL for VLMs
AskPDF
Mar 10, 2026

Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-Diversity

Vision-language models (VLMs) face significant computational inefficiencies caused by excessive generation of visual tokens. While prior work shows that a large fraction of visual tokens are redundant, existing compression methods struggle to balance importance preservation and information diversity. To address this, we propose PruneSID, a training-free Synergistic Importance-Diversity approach featuring a two-stage pipeline: (1) Principal Semantic Components Analysis (PSCA) for clustering tokens into semantically coherent groups, ensuring comprehensive concept coverage, and (2) Intra-group Non-Maximum Suppression (NMS) for pruning redundant tokens while preserving key representative tokens within each group. Additionally, PruneSID incorporates an information-aware dynamic compression ratio mechanism that optimizes token compression rates based on image complexity, enabling more effective average information preservation across diverse scenes. Extensive experiments demonstrate state-of-the-art performance, achieving 96.3% accuracy on LLaVA-1.5 with only 11.1% token retention, and 92.8% accuracy at extreme compression rates (5.6%) on LLaVA-NeXT, outperforming prior methods by 2.5% with 7.8 ×\times faster prefilling speed compared to the original model. Our framework generalizes across diverse VLMs and both image and video modalities, showcasing strong cross-modal versatility. Code is available at https://github.com/ZhengyaoFang/PruneSID.

Zhengyao Fang, Pengyuan Lyu, Chengquan Zhang +3

Harbin Institute of Technology, Shenzhen · Independent Researcher · Peng Cheng Laboratory

Visual Token PruningVisual Token CompressionEfficient VLM InferenceVideo Token Compression
AskPDF
Mar 7, 2026

FastSTAR: Spatiotemporal Token Pruning for Efficient Autoregressive Video Synthesis

Visual Autoregressive modeling (VAR) has emerged as a highly efficient alternative to diffusion-based frameworks, achieving comparable synthesis quality. However, as this paradigm extends to Spacetime Autoregressive modeling (STAR) for video generation, scaling resolution and frame counts leads to a "token explosion" that creates a massive computational bottleneck in the final refinement stages. To address this, we propose FastSTAR, a training-free acceleration framework designed for high-quality video generation. Our core method, Spatiotemporal Token Pruning, identifies essential tokens by integrating two specialized terms: (1) Spatial similarity, which evaluates structural convergence across hierarchical scales to skip computations in regions where further refinement becomes redundant, and (2) Temporal similarity, which identifies active motion trajectories by assessing feature-level variations relative to the preceding clip. Combined with a Partial Update mechanism, FastSTAR ensures that only non-converged regions are refined, maintaining fluid motion while bypassing redundant computations. Experimental results on InfinityStar demonstrate that FastSTAR achieves up to a 2.01x speedup with a PSNR of 28.29 and less than 1% performance degradation, proving a superior efficiency-quality trade-off for STAR-based video synthesis.

Sungwoong Yune, Suheon Jeong, Joo-Young Kim

Korea Advanced Institute of Science and Technology

Video GenerationAutoregressive Video GenerationToken PruningVisual Token Pruning
AskPDF
Mar 7, 2026

The Model Knows Which Tokens Matter: Automatic Token Selection via Noise Gating

Visual tokens dominate inference cost in vision-language models (VLMs), yet many carry redundant information. Existing pruning methods alleviate this but typically rely on attention magnitude or similarity scores. We reformulate visual token pruning as capacity constrained communication: given a fixed budget K, the model must allocate limited bandwidth to maximally preserve visual information. We propose AutoSelect, which attaches a lightweight Scorer and Denoiser to a frozen VLM and trains with only the standard next token prediction loss, without auxiliary objectives or extra annotations. During training, a variance preserving noise gate modulates each token's information flow according to its predicted importance so that gradients propagate through all tokens; a diagonal attention Denoiser then recovers the perturbed representations. At inference, only the Scorer and a hard top-K selection remain, adding negligible latency. On ten VLM benchmarks, AutoSelect retains 96.5% of full model accuracy while accelerating LLM prefill by 2.85x with only 0.69 ms overhead, and transfers to different VLM backbones without architecture-specific tuning. Code is available at https://github.com/MedHK23/AutoSelect.

Landi He, Xiaoyu Yang, Lijian Xu

Shenzhen University of Advanced Technology

Efficient VLM InferenceVisual Token PruningVision-Language ModelsGated Attention
AskPDF
Mar 6, 2026

History-Conditioned Spatio-Temporal Visual Token Pruning for Efficient Vision-Language Navigation

Vision-Language Navigation (VLN) enables robots to follow natural-language instructions in visually grounded environments, serving as a key capability for embodied robotic systems. Recent Vision-Language-Action (VLA) models have demonstrated strong navigation performance, but their high computational cost introduces latency that limits real-time deployment. We propose a training-free spatio-temporal vision token pruning framework tailored to VLA-based VLN. We apply spatial token selection to the current view, alongside spatio-temporal compression for historical memories, enabling efficient long-horizon inference while reducing redundant computation. Leveraging attention-based token importance and query-guided spatio-temporal filtering, the proposed approach preserves navigation-relevant information without retraining or modifying pretrained models, allowing plug-and-play integration into existing VLA systems. Through experiments on standard VLN benchmarks, we confirm that our method significantly outperforms existing pruning strategies. It successfully preserves superior navigation accuracy under extreme pruning scenarios, all while maintaining the highly competitive inference efficiency. Real-world deployment on a Unitree Go2 quadruped robot further validates reliable and low-latency instruction-following navigation under practical robotic constraints. We hope this work helps bridge the gap between large-scale multimodal modeling and efficient, real-time embodied deployment in robotic navigation systems. Project Page: https://wqtwjt1996.github.io/publications/2026-vln.html

Qitong Wang, Yijun Liang, Ming Li +2

The authors are with the Department of Computer and Information Sciences at the University of Delaware, Newark, DE 19711, USA. · The authors are with the University of Maryland’s Department of Computer Science, College Park, MD 20742, USA. · The author is with the Mohamed bin Zayed University of Artificial Intelligence, Masdar City, Abu Dhabi 7909, UAE.

Efficient VLM InferenceToken PruningVision-Language NavigationVision-Language-Action ModelsVisual Token Pruning
AskPDF
Mar 6, 2026

Energy-Driven Adaptive Visual Token Pruning for Efficient Vision-Language Models

Visual token reduction is critical for accelerating Vision-Language Models (VLMs), since visual inputs are represented as token sequences that introduce substantial computational overhead in the LLM backbone. However, most pruning pipelines treat efficiency primarily as a token selection problem and retain a fixed visual token budget across inputs, overlooking the substantial variation in image information density. We propose E-AdaPrune, an energy driven adaptive pruning framework that determines an image specific token budget from the singular value spectrum of the visual feature matrix and passes this budget to existing token selectors. By preserving a certain proportion of spectral energy, our method allocates more tokens to information dense scenes while assigning fewer tokens to redundant scenes, without introducing additional learnable parameters. We evaluate E-AdaPrune across four VLM backbones, three token selectors, and nine benchmarks under matched average token budgets. Results show that E-AdaPrune removes a substantial amount of redundant computation from simple cases and converts the saved budget into larger gains on information rich cases. Notably, on SQAI^\mathrm{I} with Qwen2.5-VL-3B, E-AdaPrune uses 35.8% fewer tokens for simple cases with only a 0.52% relative performance decrease. The saved budget is redirected to hard cases, which receive 52.5% more tokens and achieve a 1.94% relative performance improvement.

Jialuo He, Huangxun Chen

The Hong Kong University of Science and Technology (Guangzhou)

Efficient VLM InferenceVisual Token PruningLarge Vision-Language Models
AskPDF
Mar 6, 2026

Video Compression Meets Video Generation: Latent Inter-Frame Pruning with Attention Recovery

Current video generation models suffer from high computational latency, making real-time applications prohibitively costly. In this paper, we address this limitation by exploiting the temporal redundancy inherent in video latent patches. To this end, we propose the Latent Inter-frame Pruning with Attention Recovery (LIPAR) framework, which detects and skips recomputing duplicated latent patches. Additionally, we introduce a novel Attention Recovery mechanism that approximates the attention values of pruned tokens, thereby removing visual artifacts arising from naively applying the pruning method. Empirically, our method increases video editing throughput by 1.53×1.53\times, achieving an average of 19.3 FPS on an NVIDIA RTX 4090 with the 1.3B Self-Forcing model (4-step denoising, FP16). The proposed method does not compromise generation quality and can be seamlessly integrated with the model without additional training. Our approach effectively bridges the gap between traditional compression algorithms and modern generative pipelines.

Dennis Menn, Yuedong Yang, Bokun Wang +6

University of Texas at Austin · Meta

Video GenerationVideo Token CompressionVisual Token Pruning
AskPDF
Mar 5, 2026

Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding

Video Temporal Grounding (VTG) localizes the temporal boundaries of query-relevant moments in long, untrimmed videos, making video-language-model prohibitively expensive. While recent training-free token pruning has shown success in video question answering, naively applying these objectives to VTG causes drastic degradation, as VTG crucially depends on boundary-sensitive evidence and cross-frame reasoning chains. We therefore identify two VTG-specific pruning principles: evidence retention, which keeps query-critical patches especially around event boundaries, and connectivity strength, which preserves cross-frame connectivity for long-range evidence aggregation. Building on these insights, we propose SemVID, a training-free pruning framework that constructs a compact yet coherent token subset with complementary semantic roles. SemVID first allocates per-frame budgets by balancing query relevance and inter-frame variation to avoid over-pruned segments, and then selects three types of tokens: object tokens for diverse query-critical evidence, motion tokens to capture meaningful transitions and serve as cross-frame relays, and context tokens for scene continuity. Extensive experiments show that SemVID achieves a strong accuracy-efficiency trade-off, retaining up to 95.4% mIoU with only 12.5% visual tokens and delivering up to a 5.8x prefill speedup, consistently outperforming prior methods under the same budgets. Our code is available at https://github.com/JiaqiLi404/SemVID

Jiaqi Li, Shuntian Zheng, Yixian Shen +4

University of Warwick, Coventry CV4 7AL, United Kingdom · University of Amsterdam, Amsterdam 1012 WX, Netherlands · Amazon AGI, The United States of America

Temporal Video GroundingVision-Language GroundingVisual Token PruningVisual Token Compression
AskPDF
Mar 4, 2026

EvoPrune: Early-Stage Visual Token Pruning for Efficient MLLMs

Multimodal Large Language Models (MLLMs) have shown strong performance in vision-language tasks, but their inference efficiency is severely limited by the exponential growth of visual tokens in complex scenarios such as high-resolution images and videos. Existing visual token pruning methods mainly operate after visual encoding, overlooking the substantial computational cost incurred during the encoding stage. To address this issue, we propose EvoPrune, an early-stage visual token pruning method for MLLMs that performs pruning directly during visual encoding. Specifically, EvoPrune employs a layer-wise pruning strategy guided by token similarity, diversity, and attention-based importance to retain the most informative visual tokens at selected encoding layers. Extensive experiments on image and video benchmarks validate the effectiveness of EvoPrune. In particular, on the VideoMME dataset, EvoPrune achieves 2×\times inference speedup with less than 1% performance degradation, demonstrating its potential for latency-sensitive MLLM deployment.

Yuhao Chen, Bin Shan, Xin Ye +1

ByteDance, Beijing, China

Efficient VLM InferenceVisual Token PruningLarge Vision-Language Models
AskPDF
Mar 2, 2026

StepVAR: Structure-Texture Guided Pruning for Visual Autoregressive Models

Visual AutoRegressive (VAR) models based on next-scale prediction enable efficient hierarchical generation, yet the inference cost grows quadratically at high resolutions. We observe that the computationally intensive later scales predominantly refine high-frequency textures and exhibit substantial spatial redundancy, in contrast to earlier scales that determine the global structural layout. Existing pruning methods primarily focus on high-frequency detection for token selection, often overlooking structural coherence and consequently degrading global semantics. To address this limitation, we propose StepVAR, a training-free token pruning framework that accelerates VAR inference by jointly considering structural and textural importance. Specifically, we employ a lightweight high-pass filter to capture local texture details, while leveraging Principal Component Analysis (PCA) to preserve global structural information. This dual-criterion design enables the model to retain tokens critical for both fine-grained fidelity and overall composition. To maintain valid next-scale prediction under sparse tokens, we further introduce a nearest neighbor feature propagation strategy to reconstruct dense feature maps from pruned representations. Extensive experiments on state-of-the-art text-to-image and text-to-video VAR models demonstrate that StepVAR achieves substantial inference speedups while maintaining generation quality. Quantitative and qualitative evaluations consistently show that our method outperforms existing acceleration approaches, validating its effectiveness and general applicability across diverse VAR architectures.

Keli Liu, Zhendong Wang, Wengang Zhou +1

University of Science and Technology of China

Inference AccelerationVisual Autoregressive ModelsVisual Token PruningAutoregressive Image GenerationAutoregressive Video Generation
AskPDF
Mar 1, 2026

AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models

Large Vision-Language Models (LVLMs) have adopted visual token pruning strategies to mitigate substantial computational overhead incurred by extensive visual token sequences. While prior works primarily focus on either attention-based or diversity-based pruning methods, in-depth analysis of these approaches' characteristics and limitations remains largely unexplored. In this work, we conduct thorough empirical analysis using effective rank (erank) as a measure of feature diversity and attention score entropy to investigate visual token processing mechanisms and analyze the strengths and weaknesses of each approach. Our analysis reveals two insights: (1) Our erank-based quantitative analysis shows that many diversity-oriented pruning methods preserve substantially less feature diversity than intended; moreover, analysis using the CHAIR dataset reveals that the diversity they do retain is closely tied to increased hallucination frequency compared to attention-based pruning. (2) We further observe that attention-based approaches are more effective on simple images where visual evidence is concentrated, while diversity-based methods better handle complex images with distributed features. Building on these empirical insights, we show that incorporating image-aware adjustments into existing hybrid pruning strategies consistently improves their performance. We also provide a minimal instantiation of our empirical findings through a simple adaptive pruning mechanism, which achieves strong and reliable performance across standard benchmarks as well as hallucination-specific evaluations. Our project page available at https://cvsp-lab.github.io/AgilePruner.

Changwoo Baek, Jouwon Song, Sohyeon Kim +1

Visual Token PruningLarge Vision-Language Models
AskPDF
Feb 28, 2026

TP-Spikformer: Token Pruned Spiking Transformer

Spiking neural networks (SNNs) offer an energy-efficient alternative to traditional neural networks due to their event-driven computing paradigm. However, recent advancements in spiking transformers have focused on improving accuracy with large-scale architectures, which require significant computational resources and limit deployment on resource-constrained devices. In this paper, we propose a simple yet effective token pruning method for spiking transformers, termed TP-Spikformer, that reduces storage and computational overhead while maintaining competitive performance. Specifically, we first introduce a heuristic spatiotemporal information-retaining criterion that comprehensively evaluates tokens' importance, assigning higher scores to informative tokens for retention and lower scores to uninformative ones for pruning. Based on this criterion, we propose an information-retaining token pruning framework that employs a block-level early stopping strategy for uninformative tokens, instead of removing them outright. This also helps preserve more information during token pruning. We demonstrate the effectiveness, efficiency and scalability of TP-Spikformer through extensive experiments across diverse architectures, including Spikformer, QKFormer and Spike-driven Transformer V1 and V3, and a range of tasks such as image classification, object detection, semantic segmentation and event-based object tracking. Particularly, TP-Spikformer performs well in a training-free manner. These results reveal its potential as an efficient and practical solution for deploying SNNs in real-world applications with limited computational resources.

Wenjie Wei, Xiaolong Zhou, Malu Zhang +8

University of Electronic Science and Technology of China · Shenzhen Loop Area Institute · Northumbria University +1

Spiking TransformersToken PruningSpiking Neural NetworksEfficient Transformer InferenceVisual Token Pruning
AskPDF
Feb 28, 2026

What Do Visual Tokens Really Encode? Uncovering Sparsity and Redundancy in Multimodal Large Language Models

Multimodal large language models (MLLMs) project visual tokens into the embedding space of language models, yet the internal structuring and processing of visual semantics remain poorly understood. In this work, we introduce a two-fold analytical framework featuring a novel probing tool, EmbedLens\textbf{EmbedLens}, to conduct a fine-grained analysis. We uncover a pronounced semantic sparsity at the input level: visual tokens consistently partition into sink, dead, and alive categories. Remarkably, only the alive tokens, comprising ≈60%\approx60\% of the total input, carry image-specific meaning. Furthermore, using a targeted patch-compression benchmark, we demonstrate that these alive tokens already encode rich, fine-grained cues (e.g., objects, colors, and OCR) prior to entering the LLM. Internal visual computations (such as visual attention and feed-forward networks) are redundant for most standard tasks. For the small subset of highly vision-centric tasks that actually benefit from internal processing, we reveal that alive tokens naturally align with intermediate LLM layers rather than the initial embedding space, indicating that shallow-layer processing is unnecessary and that direct mid-layer injection is both sufficient. Ultimately, our findings provide a unified mechanistic view of visual token processing, paving the way for more efficient and interpretable MLLM architectures through selective token pruning, minimized visual computation, and mid-layer injection. The code is released at: https://github.com/EIT-NLP/EmbedLens.

Yingqi Fan, Junlong Tong, Anhao Zhao +1

Institute of Digital Twin, Eastern Institute of Technology, Ningbo · Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative · Shanghai Jiao Tong University +1

Multimodal Large Language ModelsMultimodal Model InterpretabilityVisual Token Pruning
AskPDF
Feb 27, 2026

UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking

One-stream Transformer-based trackers achieve advanced performance in visual object tracking but suffer from significant computational overhead that hinders real-time deployment. While token pruning offers a path to efficiency, existing methods are fragmented. They typically prune the search region, dynamic template, and static template in isolation, overlooking critical inter-component dependencies, which yields suboptimal pruning and degraded accuracy. To address this, we introduce UTPTrack, a simple and Unified Token Pruning framework that, for the first time, jointly compresses all three components. UTPTrack employs an attention-guided, token type-aware strategy to holistically model redundancy, a design that seamlessly supports unified tracking across multimodal and language-guided tasks within a single model. Extensive evaluations on 10 benchmarks demonstrate that UTPTrack achieves a new state-of-the-art in the accuracy-efficiency trade-off for pruning-based trackers, pruning 65.4% of vision tokens in RGB-based tracking and 67.5% in unified tracking while preserving 99.7% and 100.5% of baseline performance, respectively. This strong performance across both RGB and multimodal scenarios underlines its potential as a robust foundation for future research in efficient visual tracking. Code will be released at https://github.com/EIT-NLP/UTPTrack.

Hao Wu, Xudong Wang, Jialiang Zhang +5

Institute of Digital Twin, Eastern Institute of Technology, Ningbo · Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative · Shanghai Jiao Tong University +2

Visual Object TrackingVisual Token PruningEfficient ViTsMultimodal Token Compression
AskPDF
Feb 27, 2026

HiDrop: Hierarchical Vision Token Reduction in MLLMs via Late Injection, Concave Pyramid Pruning, and Early Exit

The quadratic computational cost of processing vision tokens in Multimodal Large Language Models (MLLMs) hinders their widespread adoption. While progressive vision token pruning offers a promising solution, current methods misinterpret shallow layer functions and use rigid schedules, which fail to unlock the full efficiency potential. To address these issues, we propose HiDrop, a framework that aligns token pruning with the true hierarchical function of MLLM layers. HiDrop features two key innovations: (1) Late Injection, which bypasses passive shallow layers to introduce visual tokens exactly where active fusion begins; and (2) Concave Pyramid Pruning with an Early Exit mechanism to dynamically adjust pruning rates across middle and deep layers. This process is optimized via an inter-layer similarity measure and a differentiable top-k operator. To ensure practical efficiency, HiDrop further incorporates persistent positional encoding, FlashAttention-compatible token selection, and parallel decoupling of vision computation to eliminate hidden overhead associated with dynamic token reduction. Extensive experiments show that HiDrop compresses about 90% visual tokens while matching the original performance and accelerating training by 1.72 times. Our work not only sets a new state-of-the-art for efficient MLLM training and inference but also provides valuable insights into the hierarchical nature of multimodal fusion. The code is released at https://github.com/EIT-NLP/HiDrop.

Hao Wu, Yingqi Fan, Jinyang Dai +3

Institute of Digital Twin, Eastern Institute of Technology, Ningbo · Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative · University of Science and Technology of China +2

Efficient VLM InferenceLarge Vision-Language ModelsMultimodal Token CompressionVisual Token Pruning
AskPDF
Feb 27, 2026

ST-Lite: Training-Free KV Cache Compression with Spatio-Trajectory Guidance for Long-Horizon GUI Agents

Training-free KV cache compression is essential for deploying vision-language GUI agents under memory and latency constraints, yet existing methods are designed for generic language workloads and ignore the distinctive structure of GUI interaction traces. We characterize three GUI-specific workload properties--high inter-frame visual redundancy, extremely small UI-element spatial footprints, and near-uniform cross-layer attention sparsity--that cause existing schemes to retain as few as 39% of oracle-important KV pairs at the standard 20% budget. To address this, we propose ST-Lite, a training-free compression scheme whose three components each target one property: Trajectory-aware Semantic Gating (TSG) filters redundant historical frames, Component-centric Spatial Saliency (CSS) preserves fine-grained element boundaries, and a flat per-layer budget avoids hierarchical misallocation. Across seven GUI benchmarks and two backbones in the deployment-relevant 10%-40% window, ST-Lite consistently outperforms all existing compression baselines, matching or exceeding Full Cache task accuracy on the primary backbone at the 20% budget while delivering up to 2.35x decoding speedup at fivefold compression. The implementation is available at https://github.com/94wen94/ST-Lite.

Bowen Zhou, Zhou Xu, Wanli Li +3

Tsinghua University, Shenzhen, China · Zhejiang University, Hangzhou, China · The Chinese University of Hong Kong, Hong Kong, China

KV-Cache CompressionGUI AgentsVisual Token Pruning
AskPDF
Feb 26, 2026

Spatio-Temporal Token Pruning for Efficient High-Resolution GUI Agents

Pure-vision GUI agents provide universal interaction capabilities but suffer from severe efficiency bottlenecks due to the massive spatiotemporal redundancy inherent in high-resolution screenshots and historical trajectories. We identify two critical misalignments in existing compression paradigms: the temporal mismatch, where uniform history encoding diverges from the agent's "fading memory" attention pattern, and the spatial topology conflict, where unstructured pruning compromises the grid integrity required for precise coordinate grounding, inducing spatial hallucinations. To address these challenges, we introduce GUIPruner, a training-free framework tailored for high-resolution GUI navigation. It synergizes Temporal-Adaptive Resolution (TAR), which eliminates historical redundancy via decay-based resizing, and Stratified Structure-aware Pruning (SSP), which prioritizes interactive foregrounds and semantic anchors while safeguarding global layout. Extensive evaluations across diverse benchmarks demonstrate that GUIPruner consistently achieves state-of-the-art performance, effectively preventing the collapse observed in large-scale models under high compression. Notably, on Qwen2-VL-2B, our method delivers a 3.4x reduction in FLOPs and a 3.3x speedup in vision encoding latency while retaining over 94% of the original performance, enabling real-time, high-precision navigation with minimal resource consumption.

Zhou Xu, Bowen Zhou, Qi Wang +2

Tsinghua University, Shenzhen, China · Xidian University, Xi’an, China · The Chinese University of Hong Kong, Hong Kong, China

GUI AgentsVisual Token PruningVisual Token CompressionEfficient VLM Inference
AskPDF
Feb 25, 2026

XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression

Learning-based 3D visual geometry models have significantly advanced with the advent of large-scale transformers. Among these, StreamVGGT leverages frame-wise causal attention to deliver robust and efficient streaming 3D reconstruction. However, it suffers from unbounded growth in the Key-Value (KV) cache due to the massive influx of vision tokens from multi-image and long-video inputs, leading to increased memory consumption and inference latency as input frames accumulate. This ultimately limits its scalability for long-horizon applications. To address this gap, we propose XStreamVGGT, a tuning-free approach that seamlessly integrates pruning and quantization to systematically compress the KV cache, enabling extremely memory-efficient streaming inference. Specifically, redundant KVs generated from multi-frame inputs are initially pruned to conform to a fixed KV memory budget using an efficient token-importance identification mechanism that maintains full compatibility with high-performance attention kernels (e.g., FlashAttention). Additionally, leveraging the inherent distribution patterns of KV tensors, we apply dimension-adaptive KV quantization within the pruning pipeline to further minimize memory overhead while preserving numerical accuracy. Extensive evaluations show that XStreamVGGT achieves mostly negligible performance degradation while substantially reducing memory usage by 4.42×\times and accelerating inference by 5.48×\times, enabling practical and scalable streaming 3D applications. The code is available at https://github.com/ywh187/XStreamVGGT/.

Zunhai Su, Weihao Ye, Hansen Feng +5

Shenzhen International Graduate School, Tsinghua University · Institute of Artificial Intelligence, Xiamen University · China Star Optoelectronics Technology +2

Streaming 3D ReconstructionKV-Cache Compression3D ViTsKV-Cache QuantizationVisual Token Pruning
AskPDF
Feb 24, 2026

BFA++: Hierarchical Best-Feature-Aware Token Prune for Multi-View Vision Language Action Model

Vision-Language-Action (VLA) models have achieved significant breakthroughs by leveraging Large Vision Language Models (VLMs) to jointly interpret instructions and visual inputs. However, the substantial increase in visual tokens, particularly from multi-view inputs, poses serious challenges to real-time robotic manipulation. Existing acceleration techniques for VLMs, such as token pruning, often result in degraded performance when directly applied to VLA models, as they overlook the relationships between different views and fail to account for the dynamic and task-specific characteristics of robotic operation. To address this, we propose BFA++, a dynamic token pruning framework designed specifically for VLA models. BFA++ introduces a hierarchical pruning strategy guided by two-level importance predictors: an intra-view predictor highlights task-relevant regions within each image to suppress spatial noise, while an inter-view predictor identifies critical camera views throughout different manipulation phases to reduce cross-view redundancy. This design enables efficient token selection while preserving essential visual cues, resulting in improved computational efficiency and higher manipulation success rates. Evaluations on the RoboTwin benchmark and real-world robotic tasks demonstrate that BFA++ consistently outperforms existing methods. BFA++ improves the success rate by about 10% on both the π0 and RDT models, achieving speedup of 1.8X and 1.5X, respectively. Our results highlight that context-sensitive and task-aware token pruning serves as a more effective strategy than full visual processing, enabling faster inference and improved manipulation accuracy in real-world robotic systems.

Haosheng Li, Weixin Mao, Zihan Lan +6

Institute of Software, Chinese Academy of Sciences, Beijing, China. · University of Chinese Academy of Sciences, Beijing, China. · LimX Dynamic, Shenzhen, China. +3

Efficient VLA Model InferenceVisual Token PruningVision-Language-Action Models
AskPDF
Feb 23, 2026

ApET: Approximation-Error Guided Token Compression for Efficient VLMs

Recent Vision-Language Models (VLMs) have demonstrated remarkable multimodal understanding capabilities, yet the redundant visual tokens incur prohibitive computational overhead and degrade inference efficiency. Prior studies typically relies on [CLS] attention or text-vision cross-attention to identify and discard redundant visual tokens. Despite promising results, such solutions are prone to introduce positional bias and, more critically, are incompatible with efficient attention kernels such as FlashAttention, limiting their practical deployment for VLM acceleration. In this paper, we step away from attention dependencies and revisit visual token compression from an information-theoretic perspective, aiming to maximally preserve visual information without any attention involvement. We present ApET, an Approximation-Error guided Token compression framework. ApET first reconstructs the original visual tokens with a small set of basis tokens via linear approximation, then leverages the approximation error to identify and drop the least informative tokens. Extensive experiments across multiple VLMs and benchmarks demonstrate that ApET retains 95.2% of the original performance on image-understanding tasks and even attains 100.4% on video-understanding tasks, while compressing the token budgets by 88.9% and 87.5%, respectively. Thanks to its attention-free design, ApET seamlessly integrates with FlashAttention, enabling further inference acceleration and making VLM deployment more practical. Code is available at https://github.com/MaQianKun0/ApET.

Qiankun Ma, Ziyao Zhang, Haofei Wang +3

Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · Peng Cheng Laboratory · University of Chinese Academy of Sciences +2

Visual Token CompressionEfficient VLM InferenceVisual Token PruningVideo Token Compression
AskPDF
Feb 23, 2026

Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework

Visual Document Retrieval (VDR), which aims to retrieve relevant pages within vast corpora of visually-rich documents, is of significance in current multimodal retrieval applications. The state-of-the-art multi-vector paradigm excels in performance but suffers from prohibitive overhead, a problem that current efficiency methods like pruning and merging address imperfectly, creating a difficult trade-off between compression rate and feature fidelity. To overcome this dilemma, we introduce Prune-then-Merge, a novel two-stage framework that synergizes these complementary approaches. Our method first employs an adaptive pruning stage to filter out low-information patches, creating a refined, high-signal set of embeddings. Subsequently, a hierarchical merging stage compresses this pre-filtered set, effectively summarizing semantic content without the noise-induced feature dilution seen in single-stage methods. Extensive experiments on 29 VDR datasets demonstrate that our framework consistently outperforms existing methods, significantly extending the near-lossless compression range and providing robust performance at high compression ratios.

Yibo Yan, Mingdong Ou, Yi Cao +5

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

Visual Document RetrievalMulti-Vector RetrievalVisual Token CompressionVisual Token MergingVisual Token Pruning
AskPDF
Feb 22, 2026

OTPrune: Distribution-Aligned Visual Token Pruning via Optimal Transport

Multi-modal large language models (MLLMs) achieve strong visual-language reasoning but suffer from high inference cost due to redundant visual tokens. Recent work explores visual token pruning to accelerate inference, while existing pruning methods overlook the underlying distributional structure of visual representations. We propose OTPrune, a training-free framework that formulates pruning as distribution alignment via optimal transport (OT). By minimizing the 2-Wasserstein distance between the full and pruned token distributions, OTPrune preserves both local diversity and global representativeness while reducing inference cost. Moreover, we derive a tractable submodular objective that enables efficient optimization, and theoretically prove its monotonicity and submodularity, providing a principled foundation for stable and efficient pruning. We further provide a comprehensive analysis that explains how distributional alignment contributes to stable and semantically faithful pruning. Comprehensive experiments on wider benchmarks demonstrate that OTPrune achieves superior performance-efficiency tradeoffs compared to state-of-the-art methods. The code is available at https://github.com/xiwenc1/OTPrune.

Xiwen Chen, Wenhui Zhu, Gen Li +9

Morgan Stanley · Clemson University · Arizona State University +4

Visual Token PruningEfficient VLM InferenceLVLM Pruning
AskPDF
Feb 21, 2026

DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference

Vision-language models (VLMs) have achieved remarkable multimodal understanding and reasoning capabilities, yet remain computationally expensive due to dense visual tokenization. Existing efficiency approaches either merge redundant visual tokens or drop them progressively in language backbone, often trading accuracy for speed. In this work, we propose DUET-VLM, a versatile plug-and-play dual compression framework that consists of (a) vision-only redundancy aware compression of vision encoder's output into information-preserving tokens, followed by (b) layer-wise, salient text-guided dropping of visual tokens within the language backbone to progressively prune less informative tokens. This coordinated token management enables aggressive compression while retaining critical semantics. On LLaVA-1.5-7B, our approach maintains over 99% of baseline accuracy with 67% fewer tokens, and still retains >97% even at 89% reduction. With this dual-stage compression during training, it achieves 99.7% accuracy at 67% and 97.6% at 89%, surpassing prior SoTA visual token reduction methods across multiple benchmarks. When integrated into Video-LLaVA-7B, it even surpasses the baseline -- achieving >100% accuracy with a substantial 53.1% token reduction and retaining 97.6% accuracy under an extreme 93.4% setting. These results highlight end-to-end training with DUET-VLM, enabling robust adaptation to reduced visual (image/video) input without sacrificing accuracy, producing compact yet semantically rich representations within the same computational budget. Our code is available at https://github.com/AMD-AGI/DUET-VLM.

Aditya Kumar Singh, Hitesh Kandala, Pratik Prabhanjan Brahma +2

Advanced Micro Devices, Inc. (AMD)

Efficient VLM InferenceMultimodal Token CompressionVisual Token CompressionVisual Token PruningVideo Token Compression
AskPDF
Feb 19, 2026

EntropyPrune: Matrix Entropy Guided Visual Token Pruning for Multimodal Large Language Models

Multimodal large language models (MLLMs) incur substantial inference cost due to the processing of hundreds of visual tokens per image. Although token pruning has proven effective for accelerating inference, determining when and where to prune remains largely heuristic. Existing approaches typically rely on static, empirically selected layers, which limit interpretability and transferability across models. In this work, we introduce a matrix-entropy perspective and identify an "Entropy Collapse Layer" (ECL), where the information content of visual representations exhibits a sharp and consistent drop, which provides a principled criterion for selecting the pruning stage. Building on this observation, we propose EntropyPrune, a novel matrix-entropy-guided token pruning framework that quantifies the information value of individual visual tokens and prunes redundant ones without relying on attention maps. Moreover, to enable efficient computation, we exploit the spectral equivalence of dual Gram matrices, reducing the complexity of entropy computation and yielding up to a 64x theoretical speedup. Extensive experiments on diverse multimodal benchmarks demonstrate that EntropyPrune consistently outperforms state-of-the-art pruning methods in both accuracy and efficiency. On LLaVA-1.5-7B, our method achieves a 68.2% reduction in FLOPs while preserving 96.0% of the original performance. Furthermore, EntropyPrune generalizes effectively to high-resolution and video-based models, highlighting the strong robustness and scalability in practical MLLM acceleration. The code will be publicly available at https://github.com/YahongWang1/EntropyPrune.

Yahong Wang, Juncheng Wu, Zhangkai Ni +6

Tongji University · University of California, Santa Cruz · East China Normal University +1

Token PruningVisual Token PruningEfficient Multimodal InferenceMultimodal Large Language Models
AskPDF