mlsanityData to 7 Oct 2026

VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration

arXiv 2601.22674 ↗First posted 30 Jan 2026cs.CVcited by 16

On the map: Multimodal LLMs / vision-language models → Visual token pruning and efficiency

also in 1 more
Abstract (arXiv)

Multimodal large language models (MLLMs) suffer from high computational costs due to excessive visual tokens, particularly in high-resolution and video-based scenarios. Existing token reduction methods typically focus on isolated pipeline components and often neglect textual alignment, leading to performance degradation. In this paper, we propose VisionTrim, a unified framework for training-free MLLM acceleration, integrating two effective plug-and-play modules: 1) the Dominant Vision Token Selection (DVTS) module, which preserves essential visual tokens via a global-local view, and 2) the Text-Guided Vision Complement (TGVC) module, which facilitates context-aware token merging guided by textual cues. Extensive experiments across diverse image and video multimodal benchmarks demonstrate the performance superiority of our VisionTrim, advancing practical MLLM deployment in real-world applications. The code is available at: https://github.com/hanxunyu/VisionTrim.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 55 of its 66 references that are in the map. First posted on arXiv 30 Jan 2026.

Builds on

55 of 66 references.

Closest ancestors · 13

Same direction, newest first

  1. 2025VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models28 May
  2. 2025FOLDER: Accelerating Multi-modal Large Language Models with Enhanced Performance5 Jan
  3. 2024[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs8 Dec
  4. 2024VisionZip: Longer is Better but Not Necessary in Vision Language Models5 Dec
  5. 2024AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning4 Dec
  6. 2024PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction22 Oct
  7. 2024SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference6 Oct
  8. 2024TokenPacker: Efficient Visual Projector for Multimodal LLM2 Jul
  9. 2024VoCo-LLaMA: Towards Vision Compression with Large Language Models18 Jun
  10. 2024Matryoshka Query Transformer for Large Vision-Language Models29 May
  11. 2024LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models22 Mar
  12. 2024An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models11 Mar
1 more
  1. 2023CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers27 May

Other references · 42

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2023GPT-4 Technical Reportcited by 18,132
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  6. 2023Visual Instruction Tuningcited by 7,792
  7. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  8. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  9. 2025Qwen2.5-VL Technical Reportcited by 5,418
  10. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  11. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  12. 2023Qwen Technical Reportcited by 3,273
30 more
  1. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  2. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,669
  3. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,498
  4. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,105
  5. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,696
  6. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,624
  7. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,573
  8. 2023Video-LLaVA: Learning United Visual Representation by Alignment Before Projectioncited by 1,385
  9. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,221
  10. 2023Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Modelscited by 1,047
  11. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,033
  12. 2022Token Merging: Your ViT But Fastercited by 995
  13. 2018VizWiz Grand Challenge: Answering Visual Questions from Blind Peoplecited by 852
  14. 2024VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMscited by 749
  15. 2023VILA: On Pre-training for Visual Language Modelscited by 686
  16. 2019ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answeringcited by 559
  17. 2017TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answeringcited by 378
  18. 2023Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understandingcited by 368
  19. 2024LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understandingcited by 341
  20. 2023Honeybee: Locality-enhanced Projector for Multimodal LLMcited by 195
  21. 2024MobileVLM V2: Faster and Stronger Baseline for Vision Language Modelcited by 172
  22. 2024Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolutioncited by 157
  23. 2022Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformerscited by 118
  24. 2024Efficient Multimodal Large Language Models: A Surveycited by 95
  25. 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 66
  26. 2025Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuningcited by 50
  27. 2025N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Modelscited by 28
  28. 2024Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Large Modelscited by 13
  29. 2025StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understandingcited by 9
  30. 2023Label-efficient Segmentation via Affinity Propagationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 16.

16 papers.

Sort:

By area:

  1. 2026Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decodingcited by 6
  2. 2026Unlocking Dense Metric Depth Estimation in VLMscited by 2
  3. 2026Accelerating Multimodal Large Language Models with Prior-Corrected Token Reductioncited by 2
  4. 2026Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understandingcited by 1
  5. 2026EchoPrune: Interpreting Redundancy as Temporal Echoes for Efficient VideoLLMscited by 1
  6. 2026Spectral Evolution-Guided Token Pruning in Multimodal Large Language Modelscited by 1
  7. 2026ForensicZip: More Tokens are Better but Not Necessary in Forensic Vision-Language Modelscited by 0
  8. 2026CIVIC: End-to-End Sequence Compactness for Efficient Vision-Language Modelscited by 0
  9. 2026Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priorscited by 0
  10. 2026DCP-Prune: Ultra-Low Token Pruning with Distribution Consistency Preservationcited by 0
  11. 2026Beyond Independent Optimization: Compression, MoE Routing, and Quantization Interactions in Multimodal Edge Intelligencecited by 0
  12. 2026Keep the Needle, Prune the Haystack: Defect-Preserving Token Pruning for Efficient Zero-Shot Anomaly Detectioncited by 0
4 more
  1. 2026HiSC: Hierarchical Spatial Clustering Token Compression for Efficient 3D Scene Understandingcited by 0
  2. 2026TRACE: Trajectory-robust Admission with Evidence Ordering for Efficient GUI Agentscited by 0
  3. 2026CoViST: Visual Token Compression via Composable Statescited by 0
  4. 2026Still There, No Longer Seen: Exposing Compression-Induced Risk in Large Vision-Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Variation-aware Vision Token Dropping for Faster Large Vision-Language Models
  2. 2024Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration
  3. 2026DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference
  4. 2025VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs
  5. 2025FCoT-VL:Advancing Text-oriented Large Vision-Language Models with Efficient Visual Token Compression
  6. 2026ApET: Approximation-Error Guided Token Compression for Efficient VLMs
  7. 2026Vision Token Reduction via Attention-Driven Self-Compression for Efficient Multimodal Large Language Models
  8. 2026EvoPrune: Early-Stage Visual Token Pruning for Efficient MLLMs