# From Holistic to Localized: Local Enhanced Adapters for Efficient Visual Instruction Fine-Tuning

arXiv: https://arxiv.org/abs/2411.12787 · HTML: https://mlsanity.com/paper/2411.12787/

## Key facts

- Cited by 3 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 34 of its 43 references that are in the map.
- First posted on arXiv 19 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, 30 of 34)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [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)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [DeepSeek-VL: Towards Real-World Vision-Language Understanding](https://mlsanity.com/paper/2403.05525/) (2024)
- [Vision Transformer with Deformable Attention](https://mlsanity.com/paper/2201.00520/) (2022)
- [Honeybee: Locality-enhanced Projector for Multimodal LLM](https://mlsanity.com/paper/2312.06742/) (2023)
- [LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images](https://mlsanity.com/paper/2403.11703/) (2024)
- [Mixture of LoRA Experts](https://mlsanity.com/paper/2404.13628/) (2024)
- [xGen-MM (BLIP-3): A Family of Open Large Multimodal Models](https://mlsanity.com/paper/2408.08872/) (2024)
- [LLaVA-MoLE: Sparse Mixture of LoRA Experts for Mitigating Data Conflicts in Instruction Finetuning MLLMs](https://mlsanity.com/paper/2401.16160/) (2024)
- [Harder Tasks Need More Experts: Dynamic Routing in MoE Models](https://mlsanity.com/paper/2403.07652/) (2024)
- [AdaMoLE: Fine-Tuning Large Language Models with Adaptive Mixture of Low-Rank Adaptation Experts](https://mlsanity.com/paper/2405.00361/) (2024)
- [FoodLMM: A Versatile Food Assistant using Large Multi-modal Model](https://mlsanity.com/paper/2312.14991/) (2023)

## Built on by (most cited first, 3 of 3)

- [Benchmarking Gaslighting Negation Attacks Against Reasoning Models](https://mlsanity.com/paper/2506.09677/) (2025)
- [Disentangling Semantic Attention from Structural Bias in the Attention Manifold](https://mlsanity.com/paper/2607.24017/) (2026)
- [BananaVLM: A Domain-Adapted Vision Language Model for Banana Crop Disease Diagnosis](https://mlsanity.com/paper/2609.25040/) (2026)

## Abstract (arXiv)

Efficient Visual Instruction Fine-Tuning (EVIT) seeks to adapt Multimodal Large Language Models (MLLMs) to downstream tasks with minimal computational overhead. However, as task diversity and complexity increase, EVIT faces significant challenges in resolving data conflicts. To address this limitation, we propose the Dual Low-Rank Adaptation (Dual-LoRA), a holistic-to-local framework that enhances the adapter's capacity to address data conflict through dual structural optimization. Specifically, we utilize two subspaces: a skill space for stable, holistic knowledge retention, and a rank-rectified task space that locally activates the holistic knowledge. Additionally, we introduce Visual Cue Enhancement (VCE), a multi-level local feature aggregation module designed to enrich the vision-language projection with local details. Our approach is both memory- and time-efficient, requiring only 1.16× the inference time of the standard LoRA method (with injection into the query and value projection layers), and just 73% of the inference time of a 4-expert LoRA-MoE. Extensive experiments on various downstream tasks and general MLLM benchmarks validate the effectiveness of our proposed methods.