# QG-VTC: Question-Guided Visual Token Compression in MLLMs for Efficient VQA

arXiv: https://arxiv.org/abs/2504.00654 · HTML: https://mlsanity.com/paper/2504.00654/

## Key facts

- Cited by 4 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 34 of its 45 references that are in the map.
- First posted on arXiv 1 Apr 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 34)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [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)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration](https://mlsanity.com/paper/2311.04257/) (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)
- [Honeybee: Locality-enhanced Projector for Multimodal LLM](https://mlsanity.com/paper/2312.06742/) (2023)
- [LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents](https://mlsanity.com/paper/2311.05437/) (2023)
- [DiffRate : Differentiable Compression Rate for Efficient Vision Transformers](https://mlsanity.com/paper/2305.17997/) (2023)
- [LLaVA-Interactive: An All-in-One Demo for Image Chat, Segmentation, Generation and Editing](https://mlsanity.com/paper/2311.00571/) (2023)
- [CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers](https://mlsanity.com/paper/2305.17455/) (2023)

## Built on by (most cited first, 4 of 4)

- [VCM: Vision Concept Modeling Based on Implicit Contrastive Learning with Vision-Language Instruction Fine-Tuning](https://mlsanity.com/paper/2504.19627/) (2025)
- [Re-purposing SAM into Efficient Visual Projectors for MLLM-Based Referring Image Segmentation](https://mlsanity.com/paper/2509.13676/) (2025)
- [MGA-VQA: Secure and Interpretable Graph-Augmented Visual Question Answering with Memory-Guided Protection Against Unauthorized Knowledge Use](https://mlsanity.com/paper/2511.17881/) (2025)
- [Don't Send What You Don't Need: Question-Guided Token Pruning as a Privacy Defense for Vision-Language Models](https://mlsanity.com/paper/2609.15671/) (2026)

## Abstract (arXiv)

Recent advances in Multi-modal Large Language Models (MLLMs) have shown significant progress in open-world Visual Question Answering (VQA). However, integrating visual information increases the number of processed tokens, leading to higher GPU memory usage and computational overhead. Images often contain more redundant information than text, and not all visual details are pertinent to specific questions. To address these challenges, we propose QG-VTC, a novel question-guided visual token compression method for MLLM-based VQA tasks. QG-VTC employs a pretrained text encoder and a learnable feed-forward layer to embed user questions into the vision encoder's feature space then computes correlation scores between the question embeddings and visual tokens. By selecting the most relevant tokens and softly compressing others, QG-VTC ensures fine-tuned relevance to user needs. Additionally, a progressive strategy applies this compression across different vision encoder layers, gradually reducing token numbers. This approach maximizes retention of question-relevant information while discarding irrelevant details. Experimental results show that our method achieves performance on par with uncompressed models using just 1/8 of the visual tokens. The code and model will be publicly available on GitHub.