# Position-Enhanced Visual Instruction Tuning for Multimodal Large Language Models

arXiv: https://arxiv.org/abs/2308.13437 · HTML: https://mlsanity.com/paper/2308.13437/

## Key facts

- Cited by 59 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 29 of its 34 references that are in the map.
- First posted on arXiv 25 Aug 2023.

## 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, 29 of 29)

- [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)
- [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)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [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)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding](https://mlsanity.com/paper/2104.12763/) (2021)
- [Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models](https://mlsanity.com/paper/2303.04671/) (2023)
- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [From Recognition to Cognition: Visual Commonsense Reasoning](https://mlsanity.com/paper/1811.10830/) (2018)
- [Language Is Not All You Need: Aligning Perception with Language Models](https://mlsanity.com/paper/2302.14045/) (2023)
- [MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action](https://mlsanity.com/paper/2303.11381/) (2023)
- [GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest](https://mlsanity.com/paper/2307.03601/) (2023)
- [COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images](https://mlsanity.com/paper/1601.07140/) (2016)
- [M3IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning](https://mlsanity.com/paper/2306.04387/) (2023)
- [MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning](https://mlsanity.com/paper/2212.10773/) (2022)
- [ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning](https://mlsanity.com/paper/2307.09474/) (2023)
- [PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models](https://mlsanity.com/paper/2205.11169/) (2022)

## Built on by (most cited first, 30 of 59)

- [Generative Multimodal Models are In-Context Learners](https://mlsanity.com/paper/2312.13286/) (2023)
- [A Survey on Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2402.00253/) (2024)
- [SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models](https://mlsanity.com/paper/2406.01584/) (2024)
- [LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning](https://mlsanity.com/paper/2311.18651/) (2023)
- [Osprey: Pixel Understanding with Visual Instruction Tuning](https://mlsanity.com/paper/2312.10032/) (2023)
- [TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering](https://mlsanity.com/paper/2311.16465/) (2023)
- [The Revolution of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2402.12451/) (2024)
- [OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding](https://mlsanity.com/paper/2406.19389/) (2024)
- [LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models](https://mlsanity.com/paper/2312.02949/) (2023)
- [Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want](https://mlsanity.com/paper/2403.20271/) (2024)
- [CapsFusion: Rethinking Image-Text Data at Scale](https://mlsanity.com/paper/2310.20550/) (2023)
- [LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge](https://mlsanity.com/paper/2311.11860/) (2023)
- [VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM](https://mlsanity.com/paper/2501.00599/) (2024)
- [RegionGPT: Towards Region Understanding Vision Language Model](https://mlsanity.com/paper/2403.02330/) (2024)
- [GROUNDHOG: Grounding Large Language Models to Holistic Segmentation](https://mlsanity.com/paper/2402.16846/) (2024)
- [Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model](https://mlsanity.com/paper/2312.12423/) (2023)
- [Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs](https://mlsanity.com/paper/2310.00582/) (2023)
- [ScanReason: Empowering 3D Visual Grounding with Reasoning Capabilities](https://mlsanity.com/paper/2407.01525/) (2024)
- [Image Textualization: An Automatic Framework for Creating Accurate and Detailed Image Descriptions](https://mlsanity.com/paper/2406.07502/) (2024)
- [See, Say, and Segment: Teaching LMMs to Overcome False Premises](https://mlsanity.com/paper/2312.08366/) (2023)
- [ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models](https://mlsanity.com/paper/2407.21534/) (2024)
- [3D Aware Region Prompted Vision Language Model](https://mlsanity.com/paper/2509.13317/) (2025)
- [Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2412.11077/) (2024)
- [Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey](https://mlsanity.com/paper/2312.16602/) (2023)
- [EarthMarker: A Visual Prompting Multi-modal Large Language Model for Remote Sensing](https://mlsanity.com/paper/2407.13596/) (2024)
- [What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning](https://mlsanity.com/paper/2311.01487/) (2023)
- [Artemis: Towards Referential Understanding in Complex Videos](https://mlsanity.com/paper/2406.00258/) (2024)
- [u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model](https://mlsanity.com/paper/2311.05348/) (2023)
- [ChatterBox: Multi-round Multimodal Referring and Grounding](https://mlsanity.com/paper/2401.13307/) (2024)
- [VLM-PL: Advanced Pseudo Labeling Approach for Class Incremental Object Detection via Vision-Language Model](https://mlsanity.com/paper/2403.05346/) (2024)

## Abstract (arXiv)

Recently, Multimodal Large Language Models (MLLMs) that enable Large Language Models (LLMs) to interpret images through visual instruction tuning have achieved significant success. However, existing visual instruction tuning methods only utilize image-language instruction data to align the language and image modalities, lacking a more fine-grained cross-modal alignment. In this paper, we propose Position-enhanced Visual Instruction Tuning (PVIT), which extends the functionality of MLLMs by integrating an additional region-level vision encoder. This integration promotes a more detailed comprehension of images for the MLLM. In addition, to efficiently achieve a fine-grained alignment between the vision modules and the LLM, we design multiple data generation strategies to construct an image-region-language instruction dataset. Finally, we present both quantitative experiments and qualitative analysis that demonstrate the superiority of the proposed model. Code and data will be released at https://github.com/PVIT-official/PVIT.