# Reformulating Vision-Language Foundation Models and Datasets Towards Universal Multimodal Assistants

arXiv: https://arxiv.org/abs/2310.00653 · HTML: https://mlsanity.com/paper/2310.00653/

## Key facts

- Cited by 25 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 26 of its 35 references that are in the map.
- First posted on arXiv 1 Oct 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, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (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)
- [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)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [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)
- [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)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)
- [A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge](https://mlsanity.com/paper/2206.01718/) (2022)
- [VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts](https://mlsanity.com/paper/2111.02358/) (2021)
- [Visual Dialog](https://mlsanity.com/paper/1611.08669/) (2016)
- [MultiModal-GPT: A Vision and Language Model for Dialogue with Humans](https://mlsanity.com/paper/2305.04790/) (2023)
- [Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence](https://mlsanity.com/paper/2209.02970/) (2022)
- [A Minimal Span-Based Neural Constituency Parser](https://mlsanity.com/paper/1705.03919/) (2017)

## Built on by (most cited first, 25 of 25)

- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback](https://mlsanity.com/paper/2312.00849/) (2023)
- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [NVILA: Efficient Frontier Visual Language Models](https://mlsanity.com/paper/2412.04468/) (2024)
- [RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness](https://mlsanity.com/paper/2405.17220/) (2024)
- [Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback](https://mlsanity.com/paper/2404.14233/) (2024)
- [STORM: Token-Efficient Long Video Understanding for Multimodal LLMs](https://mlsanity.com/paper/2503.04130/) (2025)
- [ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward Modeling](https://mlsanity.com/paper/2402.06118/) (2024)
- [CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs](https://mlsanity.com/paper/2501.16629/) (2025)
- [Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization](https://mlsanity.com/paper/2502.13146/) (2025)
- [Exploring Perceptual Limitation of Multimodal Large Language Models](https://mlsanity.com/paper/2402.07384/) (2024)
- [Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey](https://mlsanity.com/paper/2409.11564/) (2024)
- [Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization](https://mlsanity.com/paper/2504.18397/) (2025)
- [Mitigating Hallucination Through Theory-Consistent Symmetric Multimodal Preference Optimization](https://mlsanity.com/paper/2506.11712/) (2025)
- [Megrez-Omni Technical Report](https://mlsanity.com/paper/2502.15803/) (2025)
- [From Generalist to Specialist: Adapting Vision Language Models via Task-Specific Visual Instruction Tuning](https://mlsanity.com/paper/2410.06456/) (2024)
- [How to Bridge the Gap between Modalities: Survey on Multimodal Large Language Model](https://mlsanity.com/paper/2311.07594/) (2023)
- [Prompt-Aware Adapter: Towards Learning Adaptive Visual Tokens for Multimodal Large Language Models](https://mlsanity.com/paper/2405.15684/) (2024)
- [Understanding Multimodal Hallucination with Parameter-Free Representation Alignment](https://mlsanity.com/paper/2409.01151/) (2024)
- [Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models](https://mlsanity.com/paper/2412.05939/) (2024)
- [The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models](https://mlsanity.com/paper/2503.03122/) (2025)
- [A Light and Smart Wearable Platform with Multimodal Foundation Model for Enhanced Spatial Reasoning in People with Blindness and Low Vision](https://mlsanity.com/paper/2505.10875/) (2025)
- [ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning](https://mlsanity.com/paper/2505.19100/) (2025)
- [TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs](https://mlsanity.com/paper/2507.21584/) (2025)
- [Hallucination Mitigation for Large Vision-Language Models via Implicit Feature Stabilization](https://mlsanity.com/paper/2608.29924/) (2026)

## Abstract (arXiv)

Recent Multimodal Large Language Models (MLLMs) exhibit impressive abilities to perceive images and follow open-ended instructions. The capabilities of MLLMs depend on two crucial factors: the model architecture to facilitate the feature alignment of visual modules and large language models; the multimodal instruction tuning datasets for human instruction following. (i) For the model architecture, most existing models introduce an external bridge module to connect vision encoders with language models, which needs an additional feature-alignment pre-training. In this work, we discover that compact pre-trained vision language models can inherently serve as ``out-of-the-box'' bridges between vision and language. Based on this, we propose Muffin framework, which directly employs pre-trained vision-language models to act as providers of visual signals. (ii) For the multimodal instruction tuning datasets, existing methods omit the complementary relationship between different datasets and simply mix datasets from different tasks. Instead, we propose UniMM-Chat dataset which explores the complementarities of datasets to generate 1.1M high-quality and diverse multimodal instructions. We merge information describing the same image from diverse datasets and transforms it into more knowledge-intensive conversation data. Experimental results demonstrate the effectiveness of the Muffin framework and UniMM-Chat dataset. Muffin achieves state-of-the-art performance on a wide range of vision-language tasks, significantly surpassing state-of-the-art models like LLaVA and InstructBLIP. Our model and dataset are all accessible at https://github.com/thunlp/muffin.