# Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention

arXiv: https://arxiv.org/abs/2510.02912 · HTML: https://mlsanity.com/paper/2510.02912/

## Key facts

- Cited by 47 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 80 of its 100 references that are in the map.
- First posted on arXiv 3 Oct 2025.

## 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 80)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [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)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [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)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [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)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [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)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [ShareGPT4V: Improving Large Multi-Modal Models with Better Captions](https://mlsanity.com/paper/2311.12793/) (2023)

## Built on by (most cited first, 30 of 47)

- [OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models](https://mlsanity.com/paper/2602.04804/) (2026)
- [Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods](https://mlsanity.com/paper/2510.07143/) (2025)
- [Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference](https://mlsanity.com/paper/2511.16449/) (2025)
- [VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs](https://mlsanity.com/paper/2510.16598/) (2025)
- [The Model Knows Which Tokens Matter: Automatic Token Selection via Noise Gating](https://mlsanity.com/paper/2603.07135/) (2026)
- [ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention](https://mlsanity.com/paper/2602.07574/) (2026)
- [Improving Visual Token Reduction via Rectifying Distortions for Efficient Multimodal LLM Inference](https://mlsanity.com/paper/2606.01711/) (2026)
- [Stepwise Token Selection for Efficient Multimodal Large Language Models](https://mlsanity.com/paper/2606.16067/) (2026)
- [Seeing the End at Step Zero: Accelerating Diffusion MLLMs via MLP Sparsity-Aware Truncation](https://mlsanity.com/paper/2607.14557/) (2026)
- [TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding](https://mlsanity.com/paper/2511.16595/) (2025)
- [Energy-Driven Adaptive Visual Token Pruning for Efficient Vision-Language Models](https://mlsanity.com/paper/2603.05950/) (2026)
- [ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models via Spatial-Temporal Forest Modeling](https://mlsanity.com/paper/2603.22911/) (2026)
- [RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference](https://mlsanity.com/paper/2605.00392/) (2026)
- [HIPPO: Accelerating Video Large Language Models Inference via Holistic-aware Parallel Speculative Decoding](https://mlsanity.com/paper/2601.08273/) (2026)
- [Focus-Scan-Refine: From Human Visual Perception to Efficient Visual Token Pruning](https://mlsanity.com/paper/2602.05809/) (2026)
- [Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs](https://mlsanity.com/paper/2603.16932/) (2026)
- [SinkPruner: Sink-Free Visual Token Pruning for Multimodal Large Language Models](https://mlsanity.com/paper/2609.01004/) (2026)
- [Token Pruning for In-Context Generation in Diffusion Transformers](https://mlsanity.com/paper/2602.01609/) (2026)
- [TRIO: Token Reduction via Inference-Objective Guidance for Efficient Vision-Language Models](https://mlsanity.com/paper/2602.04657/) (2026)
- [DynaTok: Temporally Adaptive and Positional Bias-Aware Token Compression for Video-LLMs](https://mlsanity.com/paper/2605.19322/) (2026)
- [Spectral Heat Flow for Conservative Token Condensation in Vision-Language Models](https://mlsanity.com/paper/2607.10640/) (2026)
- [RoRA: Role-Oriented Regional Allocation for Visual Token Pruning in MLLMs](https://mlsanity.com/paper/2608.07088/) (2026)
- [AdaTok: Adaptive Token Compression with Object-Aware Representations for Efficient Multimodal LLMs](https://mlsanity.com/paper/2511.14169/) (2025)
- [ETA-VLA: Efficient Token Adaptation via Temporal Fusion and Intra-LLM Sparsification for Vision-Language-Action Models](https://mlsanity.com/paper/2603.25766/) (2026)
- [Decoupled Similarity for Task-Aware Token Pruning in Large Vision-Language Models](https://mlsanity.com/paper/2604.11240/) (2026)
- [Evading Visual Aphasia: Contrastive Adaptive Semantic Token Pruning for Vision-Language Models](https://mlsanity.com/paper/2605.09429/) (2026)
- [Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation](https://mlsanity.com/paper/2606.29805/) (2026)
- [DiffPrune: differentiable information throttling for token pruning in vision-language models](https://mlsanity.com/paper/2608.01985/) (2026)
- [When Vision Becomes Text: Visual Token Pruning via Cross-Modal Residual Guidance in VLMs](https://mlsanity.com/paper/2608.10489/) (2026)
- [Not All Attention Heads Contribute to Critical Visual Token Selection: Head-Aware Pruning Matters More](https://mlsanity.com/paper/2608.25332/) (2026)

## Abstract (arXiv)

Despite their powerful capabilities, Multimodal Large Language Models (MLLMs) suffer from considerable computational overhead due to their reliance on massive visual tokens. Recent studies have explored token pruning to alleviate this problem, which typically uses text-vision cross-attention or [textttCLS] attention to assess and discard redundant visual tokens. In this work, we identify a critical limitation of such attention-first pruning approaches, i.e., they tend to preserve semantically similar tokens, resulting in pronounced performance drops under high pruning ratios. To this end, we propose HoloV, a simple yet effective, plug-and-play visual token pruning framework for efficient inference. Distinct from previous attention-first schemes, HoloV rethinks token retention from a holistic perspective. By adaptively distributing the pruning budget across different spatial crops, HoloV ensures that the retained tokens capture the global visual context rather than isolated salient features. This strategy minimizes representational collapse and maintains task-relevant information even under aggressive pruning. Experimental results demonstrate that our HoloV achieves superior performance across various tasks, MLLM architectures, and pruning ratios compared to SOTA methods. For instance, LLaVA1.5 equipped with HoloV preserves 95.8% of the original performance after pruning 88.9% of visual tokens, achieving superior efficiency-accuracy trade-offs.