VPRune: Efficient Training-free Pre-LLM Visual Token Pruning
On the map: Multimodal LLMs / vision-language models → Visual token pruning and efficiency
Abstract (arXiv)
Visual token pruning is a promising approach to reducing the inference cost of large vision-language models (LVLMs), yet aggressive token reduction often causes substantial performance degradation. We identify three key factors behind this degradation: text-guided selection bias, information loss from discarded tokens, and positional distortion caused by sequence compaction. Based on these observations, we propose VPRune, a training-free pre-LLM pruning framework consisting of visual-only diversity selection, similarity-guided token recycling, and position-preserving restoration. Experiments on FastVLM-1.5B across multiple vision-language benchmarks demonstrate that VPRune achieves a favorable accuracy--compression trade-off, with particularly pronounced advantages under aggressive compression. Furthermore, evaluations on edge-device show that VPRune effectively reduces end-to-end inference latency while maintaining superior task performance, demonstrating its practicality for resource-constrained LVLM deployment.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 18 of its 21 references that are in the map. First posted on arXiv 21 Sep 2026.
Builds on
18 of 21 references.
Closest ancestors · 9
Same direction, newest first
- 2025FlashVLM: Text-Guided Visual Token Selection for Large Multimodal Models23 Dec
- 2025HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models1 Aug
- 2025Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning27 Jun
- 2025Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs12 Jun
- 2025VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models28 May
- 2024FastVLM: Efficient Vision Encoding for Vision Language Models17 Dec
- 2024VisionZip: Longer is Better but Not Necessary in Vision Language Models5 Dec
- 2024TokenPacker: Efficient Visual Projector for Multimodal LLM2 Jul
- 2024An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models11 Mar
Other references · 9
- 2023Visual Instruction Tuningcited by 7,792
- 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
- 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
- 2019Towards VQA Models That Can Readcited by 1,696
- 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,696
- 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,449
- 2016A Diagram Is Worth A Dozen Imagescited by 793
- 2023FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterizationcited by 161
- 2024BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devicescited by 25
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026EvoPrune: Early-Stage Visual Token Pruning for Efficient MLLMs
- 2026CRISP: Pre-LLM Yet Text-Driven Visual Token Pruning for Efficient LVLM Inference
- 2025TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model
- 2025A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models
- 2026The Model Knows Which Tokens Matter: Automatic Token Selection via Noise Gating
- 2026SlimVLM: Sensitivity-aware Dynamic Structured Pruning with Adaptive Visual Token Selection for Efficient Vision-Language Models
- 2025ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance
- 2026AsymVLM: Asymmetric Token Pruning for Efficient Vision-Language Model Inference