# Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey

arXiv: https://arxiv.org/abs/2312.16602 · HTML: https://mlsanity.com/paper/2312.16602/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 120 of its 145 references that are in the map.
- First posted on arXiv 27 Dec 2023.

## Builds on (most cited first, 30 of 120)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [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)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [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)
- [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)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)

## Built on by (most cited first, 29 of 29)

- [MM-LLMs: Recent Advances in MultiModal Large Language Models](https://mlsanity.com/paper/2401.13601/) (2024)
- [Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning](https://mlsanity.com/paper/2405.10292/) (2024)
- [The Revolution of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2402.12451/) (2024)
- [LLaRA: Supercharging Robot Learning Data for Vision-Language Policy](https://mlsanity.com/paper/2406.20095/) (2024)
- [Visual Large Language Models for Generalized and Specialized Applications](https://mlsanity.com/paper/2501.02765/) (2025)
- [Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks](https://mlsanity.com/paper/2504.18838/) (2025)
- [Social-LLaVA: Enhancing Robot Navigation through Human-Language Reasoning in Social Spaces](https://mlsanity.com/paper/2501.09024/) (2024)
- [The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective](https://mlsanity.com/paper/2407.08583/) (2024)
- [MMReason: An Open-Ended Multi-Modal Multi-Step Reasoning Benchmark for MLLMs Toward AGI](https://mlsanity.com/paper/2506.23563/) (2025)
- [MetaToken: Detecting Hallucination in Image Descriptions by Meta Classification](https://mlsanity.com/paper/2405.19186/) (2024)
- [RS-GPT4V: A Unified Multimodal Instruction-Following Dataset for Remote Sensing Image Understanding](https://mlsanity.com/paper/2406.12479/) (2024)
- [Towards Understanding Visual Grounding in Visual Language Models](https://mlsanity.com/paper/2509.10345/) (2025)
- [When Continue Learning Meets Multimodal Large Language Model: A Survey](https://mlsanity.com/paper/2503.01887/) (2025)
- [PAINT: Paying Attention to INformed Tokens to Mitigate Hallucination in Large Vision-Language Model](https://mlsanity.com/paper/2501.12206/) (2025)
- [Mitigating Image Captioning Hallucinations in Vision-Language Models](https://mlsanity.com/paper/2505.03420/) (2025)
- [A Review of 3D Object Detection with Vision-Language Models](https://mlsanity.com/paper/2504.18738/) (2025)
- [DefectTwin: When LLM Meets Digital Twin for Railway Defect Inspection](https://mlsanity.com/paper/2409.06725/) (2024)
- [HARMONY: Hidden Activation Representations and Model Output-Aware Uncertainty Estimation for Vision-Language Models](https://mlsanity.com/paper/2510.22171/) (2025)
- [VOLMO: Versatile and Open Large Models for Ophthalmology](https://mlsanity.com/paper/2603.23953/) (2026)
- [Visual Compositional Tuning](https://mlsanity.com/paper/2504.21850/) (2025)
- [Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service Environment](https://mlsanity.com/paper/2506.10030/) (2025)
- [CIMR: Contextualized Iterative Multimodal Reasoning for Robust Instruction Following in LVLMs](https://mlsanity.com/paper/2507.22074/) (2025)
- [ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models](https://mlsanity.com/paper/2605.15687/) (2026)
- [Can Foundation Models Reliably Identify Spatial Hazards? A Case Study on Curb Segmentation](https://mlsanity.com/paper/2406.07202/) (2024)
- [VSLLaVA: a pipeline of large multimodal foundation model for industrial vibration signal analysis](https://mlsanity.com/paper/2409.07482/) (2024)
- [Score2Instruct: Scaling Up Video Quality-Centric Instructions via Automated Dimension Scoring](https://mlsanity.com/paper/2506.21011/) (2025)
- [Sparse Shortcuts: Facilitating Efficient Fusion in Multimodal Large Language Models](https://mlsanity.com/paper/2602.00505/) (2026)
- [Is One-Shot In-Context Learning Helpful for Data Selection in Task-Specific Fine-Tuning of Multimodal LLMs?](https://mlsanity.com/paper/2603.28058/) (2026)
- [Towards Unconstrained Human-Object Interaction](https://mlsanity.com/paper/2604.14069/) (2026)

## Abstract (arXiv)

Traditional computer vision generally solves each single task independently by a dedicated model with the task instruction implicitly designed in the model architecture, arising two limitations: (1) it leads to task-specific models, which require multiple models for different tasks and restrict the potential synergies from diverse tasks; (2) it leads to a pre-defined and fixed model interface that has limited interactivity and adaptability in following user' task instructions. To address them, Visual Instruction Tuning (VIT) has been intensively studied recently, which finetunes a large vision model with language as task instructions, aiming to learn from a wide range of vision tasks described by language instructions a general-purpose multimodal model that can follow arbitrary instructions and thus solve arbitrary tasks specified by the user. This work aims to provide a systematic review of visual instruction tuning, covering (1) the background that presents computer vision task paradigms and the development of VIT; (2) the foundations of VIT that introduce commonly used network architectures, visual instruction tuning frameworks and objectives, and evaluation setups and tasks; (3) the commonly used datasets in visual instruction tuning and evaluation; (4) the review of existing VIT methods that categorizes them with a taxonomy according to both the studied vision task and the method design and highlights the major contributions, strengths, and shortcomings of them; (5) the comparison and discussion of VIT methods over various instruction-following benchmarks; (6) several challenges, open directions and possible future works in visual instruction tuning research.