# Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy

arXiv: https://arxiv.org/abs/2411.15453 · HTML: https://mlsanity.com/paper/2411.15453/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 27 of its 43 references that are in the map.
- First posted on arXiv 23 Nov 2024.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [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)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [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)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [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)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback](https://mlsanity.com/paper/2312.00849/) (2023)
- [LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models](https://mlsanity.com/paper/2403.15388/) (2024)
- [AI Alignment: A Comprehensive Survey](https://mlsanity.com/paper/2310.19852/) (2023)
- [Valley: Video Assistant with Large Language model Enhanced abilitY](https://mlsanity.com/paper/2306.07207/) (2023)
- [MobileVLM V2: Faster and Stronger Baseline for Vision Language Model](https://mlsanity.com/paper/2402.03766/) (2024)
- [Should You Mask 15% in Masked Language Modeling?](https://mlsanity.com/paper/2202.08005/) (2022)
- [An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM](https://mlsanity.com/paper/2403.18406/) (2024)
- [Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers](https://mlsanity.com/paper/2304.10716/) (2023)

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

- [Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention](https://mlsanity.com/paper/2510.02912/) (2025)
- [Beyond Intermediate States: Explaining Visual Redundancy through Language](https://mlsanity.com/paper/2503.20540/) (2025)
- [Scale Your Instructions: Enhance the Instruction-Following Fidelity of Unified Image Generation Model by Self-Adaptive Attention Scaling](https://mlsanity.com/paper/2507.16240/) (2025)
- [Learning from Prompt itself: the Hierarchical Attribution Prompt Optimization](https://mlsanity.com/paper/2601.02683/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have strong instruction-following capability to interpret and execute tasks as directed by human commands. Multimodal Large Language Models (MLLMs) have inferior instruction-following ability compared to LLMs. However, there is a significant gap in the instruction-following capabilities between the MLLMs and LLMs. In this study, we conduct a pilot experiment, which demonstrates that spatially down-sampling visual tokens significantly enhances the instruction-following capability of MLLMs. This is attributed to the substantial redundancy in visual modality. However, this intuitive method severely impairs the MLLM's multimodal understanding capability. In this paper, we propose Visual-Modality Token Compression (VMTC) and Cross-Modality Attention Inhibition (CMAI) strategies to alleviate this gap between MLLMs and LLMs by inhibiting the influence of irrelevant visual tokens during content generation, increasing the instruction-following ability of the MLLMs while retaining their multimodal understanding capacity. In VMTC module, the primary tokens are retained and the redundant tokens are condensed by token clustering and merging. In CMAI process, we aggregate text-to-image attentions by text-to-text attentions to obtain a text-to-image focus score. Attention inhibition is performed on the text-image token pairs with low scores. Our comprehensive experiments over instruction-following capabilities and VQA-V2, GQA, TextVQA, MME and MMBench five benchmarks, demonstrate that proposed strategy significantly enhances the instruction following capability of MLLMs while preserving the ability to understand and process multimodal inputs.