mlsanityData to 7 Oct 2026

CROP: Contextual Region-Oriented Visual Token Pruning

arXiv 2505.21233 ↗First posted 27 May 2025cs.CVcited by 14

On the map: Efficient LLM inference and serving → Visual token pruning in multimodal models

Abstract (arXiv)

Current VLM-based VQA methods often process entire images, leading to excessive visual tokens that include redundant information irrelevant to the posed question. This abundance of unnecessary image details creates numerous visual tokens, drastically increasing memory and computational requirements in VLMs. To address this, we propose Contextual Region-Oriented Visual Token Pruning (CROP), a novel framework to compress visual tokens through a two-step process: Localization and Pruning. Specifically, CROP first employs an efficient model to identify the contextual region relevant to the input query. Subsequently, two distinct strategies are introduced for pruning: (1) Pre-LLM Compression (PLC), which adaptively compresses different image regions with varying ratios, and (2) Inner-LLM Pruning (ILP), a training-free method that prunes tokens within early LLM layers guided by the identified contextual region. Extensive experiments on a wide range of VQA tasks demonstrate that CROP significantly outperforms existing visual token pruning methods and achieves state-of-the-art performance.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Placed in Visual token pruning in multimodal models, one of 12 directions in Efficient LLM inference and serving. Builds on 24 of its 46 references that are in the map. First posted on arXiv 27 May 2025.

Builds on

24 of 46 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification1 Dec
  2. 2024Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration26 Nov

Other references · 22

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  4. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  5. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,498
  6. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
  7. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,881
  8. 2019Towards VQA Models That Can Readcited by 1,696
  9. 2023V*: Guided Visual Search as a Core Mechanism in Multimodal LLMscited by 459
  10. 2023TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understandingcited by 399
  11. 2024SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inferencecited by 378
  12. 2024PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reductioncited by 283
10 more
  1. 2024MLVU: Benchmarking Multi-task Long Video Understandingcited by 275
  2. 2024Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoningcited by 267
  3. 2025MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMscited by 172
  4. 2025LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Tokencited by 164
  5. 2023LLaVA-Interactive: An All-in-One Demo for Image Chat, Segmentation, Generation and Editingcited by 47
  6. 2024TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understandingcited by 37
  7. 2025KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoningcited by 19
  8. 2025Learning Musical Representations for Music Performance Question Answeringcited by 17
  9. 2025LADM: Long-context Training Data Selection with Attention-based Dependency Measurement for LLMscited by 11
  10. 2024TG-LLaVA: Text Guided LLaVA via Learnable Latent Embeddingscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 9.

14 papers.

Sort:

By area:

  1. 2025Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Modelscited by 16
  2. 2025Teaching Vision-Language Models to Ask: Resolving Ambiguity in Visual Questionscited by 11
  3. 2025ACE-RL: Adaptive Constraint-Enhanced Reward for Long-form Generation Reinforcement Learningcited by 9
  4. 2026Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMscited by 2
  5. 2026CoVSpec: Efficient Device-Edge Co-Inference for Vision-Language Models via Speculative Decodingcited by 2
  6. 2025Discovering Semantic Subdimensions through Disentangled Conceptual Representationscited by 1
  7. 2026When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMscited by 1
  8. 2026RUTA: Principled Visual Token Allocation via Rate-Utility Optimizationcited by 1
  9. 2026Baseline-Relative Counterfactual Refinement for Bit-Aware Visual Token Communicationcited by 1
  10. 2025ProtoVQA: An Adaptable Prototypical Framework for Explainable Fine-Grained Visual Question Answeringcited by 0
  11. 2026VideoRouter: Query-Adaptive Dual Routing for Efficient Long-Video Understandingcited by 0
  12. 2026Beyond Accuracy: Auditing Spatial Provenance in Visual Token Pruning for OCR-Critical MLLM Inferencecited by 0
2 more
  1. 2026Don't Send What You Don't Need: Question-Guided Token Pruning as a Privacy Defense for Vision-Language Modelscited by 0
  2. 2026BrainFocus: EEG-Guided ROI Selection for Efficient Vision-Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025VLM-Pruner: Buffering for Spatial Sparsity in an Efficient VLM Centrifugal Token Pruning Paradigm
  2. 2026Multi-Image Visual Token Pruning in Large Visual Language Models
  3. 2025A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models
  4. 2026N"uwa: Mending the Spatial Integrity Torn by VLM Token Pruning
  5. 2025TrimTokenator-LC: Towards Adaptive Visual Token Pruning for Large Multimodal Models with Long Contexts
  6. 2024Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs
  7. 2025Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention
  8. 2026RoRA: Role-Oriented Regional Allocation for Visual Token Pruning in MLLMs