# FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models

arXiv: https://arxiv.org/abs/2505.19536 · HTML: https://mlsanity.com/paper/2505.19536/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 19 of its 66 references that are in the map.
- First posted on arXiv 26 May 2025.

## Placed in

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

## Builds on (most cited first, 19 of 19)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs](https://mlsanity.com/paper/2310.01801/) (2023)
- [Ring Attention with Blockwise Transformers for Near-Infinite Context](https://mlsanity.com/paper/2310.01889/) (2023)
- [LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models](https://mlsanity.com/paper/2403.15388/) (2024)
- [SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference](https://mlsanity.com/paper/2410.04417/) (2024)
- [Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models](https://mlsanity.com/paper/2403.18814/) (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)

## Built on by (most cited first, 29 of 29)

- [N"uwa: Mending the Spatial Integrity Torn by VLM Token Pruning](https://mlsanity.com/paper/2602.02951/) (2026)
- [TrimTokenator-LC: Towards Adaptive Visual Token Pruning for Large Multimodal Models with Long Contexts](https://mlsanity.com/paper/2512.22748/) (2025)
- [IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning](https://mlsanity.com/paper/2602.03060/) (2026)
- [Rethinking Visual Token Reduction in LVLMs Under Cross-Modal Misalignment](https://mlsanity.com/paper/2506.22283/) (2025)
- [ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention](https://mlsanity.com/paper/2602.07574/) (2026)
- [TrimTokenator: Towards Adaptive Visual Token Pruning for Large Multimodal Models](https://mlsanity.com/paper/2509.00320/) (2025)
- [Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation](https://mlsanity.com/paper/2510.23123/) (2025)
- [On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression](https://mlsanity.com/paper/2601.21531/) (2026)
- [IDPruner: Harmonizing Importance and Diversity in Visual Token Pruning for MLLMs](https://mlsanity.com/paper/2602.13315/) (2026)
- [Improving Visual Token Reduction via Rectifying Distortions for Efficient Multimodal LLM Inference](https://mlsanity.com/paper/2606.01711/) (2026)
- [SwimBird: Eliciting Switchable Reasoning Mode in Hybrid Autoregressive MLLMs](https://mlsanity.com/paper/2602.06040/) (2026)
- [RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference](https://mlsanity.com/paper/2605.00392/) (2026)
- [When MLLMs Meet Compression Distortion: A Coding Paradigm Tailored to MLLMs](https://mlsanity.com/paper/2509.24258/) (2025)
- [Fast3Dcache: Training-free 3D Geometry Synthesis Acceleration](https://mlsanity.com/paper/2511.22533/) (2025)
- [ERA: Entropy-Guided Visual Token Pruning with Rectified Attention for Efficient MLLMs](https://mlsanity.com/paper/2606.31982/) (2026)
- [AdaptInfer: Adaptive Token Pruning for Vision-Language Model Inference with Dynamical Text Guidance](https://mlsanity.com/paper/2508.06084/) (2025)
- [Do Vision Language Models Need to Process Image Tokens?](https://mlsanity.com/paper/2604.09425/) (2026)
- [Decoupled Similarity for Task-Aware Token Pruning in Large Vision-Language Models](https://mlsanity.com/paper/2604.11240/) (2026)
- [From Inheritance to Saturation: Disentangling the Evolution of Visual Redundancy for Architecture-Aware MLLM Inference Acceleration](https://mlsanity.com/paper/2604.16462/) (2026)
- [Rotation-Aligned Key Channel Pruning for Efficient Vision-Language Model Inference](https://mlsanity.com/paper/2605.19218/) (2026)
- [DCP-Prune: Ultra-Low Token Pruning with Distribution Consistency Preservation](https://mlsanity.com/paper/2606.16633/) (2026)
- [Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning](https://mlsanity.com/paper/2606.31599/) (2026)
- [Searching for Task-Specific Vision Paths: Evolutionary Block Pruning Across Vision-Language Models](https://mlsanity.com/paper/2607.17052/) (2026)
- [Position Is All You Need: A Free Lunch Token Compression Strategy for MLLM-based Referring Expression Segmentation](https://mlsanity.com/paper/2608.26142/) (2026)
- [Shallow to Deep: Aligning Token Pruning with Stage-wise Roles in LVLMs](https://mlsanity.com/paper/2609.25635/) (2026)
- [CoViST: Visual Token Compression via Composable States](https://mlsanity.com/paper/2609.33397/) (2026)
- [When Text Matters: Design Principles for Visual Token Pruning in Vision-Language Model](https://mlsanity.com/paper/2609.34861/) (2026)
- [Devils in Question Relay: Source-Conditioned Relay Steering to Mitigate Hallucinations in Audio-visual Large Language Models](https://mlsanity.com/paper/2609.37568/) (2026)
- [Feature-Aware Token Attack for Compression-Triggered Stealthy Failures in Large Vision-Language Models](https://mlsanity.com/paper/2609.39134/) (2026)

## Abstract (arXiv)

Large vision-language models (LVLMs) excel at multimodal understanding but suffer from high computational costs due to redundant vision tokens. Existing pruning methods typically rely on single-layer attention scores to rank and prune redundant visual tokens to solve this inefficiency. However, as the interaction between tokens and layers is complicated, this raises a basic question: Is such a simple single-layer criterion sufficient to identify redundancy? To answer this question, we rethink the emergence of redundant visual tokens from a fundamental perspective: information flow, which models the interaction between tokens and layers by capturing how information moves between tokens across layers. We find (1) the CLS token acts as an information relay, which can simplify the complicated flow analysis; (2) the redundancy emerges progressively and dynamically via layer-wise attention concentration; and (3) relying solely on attention scores from single layers can lead to contradictory redundancy identification. Based on this, we propose FlowCut, an information-flow-aware pruning framework, mitigating the insufficiency of the current criterion for identifying redundant tokens and better aligning with the model's inherent behaviors. Extensive experiments show that FlowCut achieves superior results, outperforming SoTA by 1.6% on LLaVA-1.5-7B with 88.9% token reduction, and by 4.3% on LLaVA-NeXT-7B with 94.4% reduction, delivering 3.2x speed-up in the prefilling stage. Our code is available at https://github.com/TungChintao/FlowCut