# Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration

arXiv: https://arxiv.org/abs/2412.13180 · HTML: https://mlsanity.com/paper/2412.13180/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 36 of its 44 references that are in the map.
- First posted on arXiv 17 Dec 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Visual token pruning and efficiency](https://mlsanity.com/mllm/visual-token-pruning-and-efficiency/)
- Efficient LLM inference and serving / [Visual token pruning in multimodal models](https://mlsanity.com/inference/visual-token-pruning-in-multimodal-models/)

## Builds on (most cited first, 30 of 36)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [A Diagram Is Worth A Dozen Images](https://mlsanity.com/paper/1603.07396/) (2016)
- [An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models](https://mlsanity.com/paper/2403.06764/) (2024)
- [LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models](https://mlsanity.com/paper/2403.15388/) (2024)
- [Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding](https://mlsanity.com/paper/2311.08046/) (2023)
- [Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models](https://mlsanity.com/paper/2402.07865/) (2024)
- [VisionZip: Longer is Better but Not Necessary in Vision Language Models](https://mlsanity.com/paper/2412.04467/) (2024)
- [PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction](https://mlsanity.com/paper/2410.17247/) (2024)
- [Visual Spatial Reasoning](https://mlsanity.com/paper/2205.00363/) (2022)
- [TallyQA: Answering Complex Counting Questions](https://mlsanity.com/paper/1810.12440/) (2018)
- [AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark](https://mlsanity.com/paper/2410.03051/) (2024)
- [NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples](https://mlsanity.com/paper/2410.14669/) (2024)
- [LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference](https://mlsanity.com/paper/2406.18139/) (2024)
- [Matryoshka Multimodal Models](https://mlsanity.com/paper/2405.17430/) (2024)
- [Revisiting Token Pruning for Object Detection and Instance Segmentation](https://mlsanity.com/paper/2306.07050/) (2023)

## Built on by (most cited first, 30 of 41)

- [Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More](https://mlsanity.com/paper/2502.11494/) (2025)
- [Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention](https://mlsanity.com/paper/2510.02912/) (2025)
- [Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark](https://mlsanity.com/paper/2504.14693/) (2025)
- [FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering](https://mlsanity.com/paper/2506.21710/) (2025)
- [FlexSelect: Flexible Token Selection for Efficient Long Video Understanding](https://mlsanity.com/paper/2506.00993/) (2025)
- [Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods](https://mlsanity.com/paper/2510.07143/) (2025)
- [N"uwa: Mending the Spatial Integrity Torn by VLM Token Pruning](https://mlsanity.com/paper/2602.02951/) (2026)
- [The Model Knows Which Tokens Matter: Automatic Token Selection via Noise Gating](https://mlsanity.com/paper/2603.07135/) (2026)
- [FiLA-Video: Spatio-Temporal Compression for Fine-Grained Long Video Understanding](https://mlsanity.com/paper/2504.20384/) (2025)
- [LVLM_CSP: Accelerating Large Vision Language Models via Clustering, Scattering, and Pruning for Reasoning Segmentation](https://mlsanity.com/paper/2504.10854/) (2025)
- [Attention Debiasing for Token Pruning in Vision Language Models](https://mlsanity.com/paper/2508.17807/) (2025)
- [Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding](https://mlsanity.com/paper/2603.05663/) (2026)
- [HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models](https://mlsanity.com/paper/2604.07812/) (2026)
- [Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models](https://mlsanity.com/paper/2606.12412/) (2026)
- [Streamline Without Sacrifice -- Squeeze out Computation Redundancy in LMM](https://mlsanity.com/paper/2505.15816/) (2025)
- [GreedyPrune: Retenting Critical Visual Token Set for Large Vision Language Models](https://mlsanity.com/paper/2506.13166/) (2025)
- [SwiftVLM: Efficient Vision-Language Model Inference via Cross-Layer Token Bypass](https://mlsanity.com/paper/2602.03134/) (2026)
- [CAPA: Contribution-Aware Pruning and FFN Approximation for Efficient Large Vision-Language Models](https://mlsanity.com/paper/2602.00247/) (2026)
- [ASAP: Attention-Shift-Aware Pruning for Efficient LVLM Inference](https://mlsanity.com/paper/2603.14549/) (2026)
- [SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning](https://mlsanity.com/paper/2603.23483/) (2026)
- [KiToke: Kernel-based Interval-aware Token Compression for Video Large Language Models](https://mlsanity.com/paper/2604.03414/) (2026)
- [PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding](https://mlsanity.com/paper/2605.30126/) (2026)
- [DiffPrune: differentiable information throttling for token pruning in vision-language models](https://mlsanity.com/paper/2608.01985/) (2026)
- [When and Where to Look: Adaptive Visual Evidence Scheduling for Efficient Long Video Understanding](https://mlsanity.com/paper/2608.03918/) (2026)
- [Baseline-Relative Counterfactual Refinement for Bit-Aware Visual Token Communication](https://mlsanity.com/paper/2608.16192/) (2026)
- [S2Prune: Spatially Structured Visual Token Pruning for Multimodal Large Language Models](https://mlsanity.com/paper/2609.01224/) (2026)
- [ShaRP: SHAllow-LayeR Pruning for Efficient Video Large Language Models](https://mlsanity.com/paper/2512.05385/) (2025)
- [LinMU: Multimodal Understanding Made Linear](https://mlsanity.com/paper/2601.01322/) (2026)
- [ConsensusDrop: Fusing Visual and Cross-Modal Saliency for Efficient Vision Language Models](https://mlsanity.com/paper/2602.00946/) (2026)
- [NeuroCanvas: VLLM-Powered Robust Seizure Detection by Reformulating Multichannel EEG as Image](https://mlsanity.com/paper/2602.04769/) (2026)

## Abstract (arXiv)

Recent works on accelerating Vision-Language Models achieve strong performance across a variety of vision-language tasks despite highly compressing visual information. In this work, we examine the popular acceleration approach of early pruning of visual tokens inside the language model. Surprisingly, we find that while strong performance is maintained across many tasks, it exhibits drastically different behavior for a subset of vision-centric tasks such as localization. Upon further investigation, we uncover a core issue with the acceleration approach where most tokens towards the top of the image are pruned away. Yet, on many benchmarks aiming to evaluate vision-centric capabilities, strong performance persists with the flawed pruning strategy, highlighting these benchmarks' limited ability to assess fine-grained visual capabilities. Based on these findings, we propose FEATHER (Fast and Effective Acceleration wiTH Ensemble cRiteria), a straightforward approach that resolves the discovered early-layer pruning issue and further enhances the preservation of relevant tokens via multistage pruning with early uniform sampling to ensure broad image coverage. With comparable computational savings, we find that FEATHER achieves more than 5x performance improvement on the vision-centric localization benchmarks compared to the original acceleration approach.