# Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos

arXiv: https://arxiv.org/abs/2312.04746 · HTML: https://mlsanity.com/paper/2312.04746/

## Key facts

- Cited by 86 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 7 Dec 2023.

## Builds on (most cited first, 22 of 22)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model](https://mlsanity.com/paper/2304.15010/) (2023)
- [InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation](https://mlsanity.com/paper/2307.06942/) (2023)
- [PathVQA: 30000+ Questions for Medical Visual Question Answering](https://mlsanity.com/paper/2003.10286/) (2020)
- [Med-Flamingo: a Multimodal Medical Few-shot Learner](https://mlsanity.com/paper/2307.15189/) (2023)
- [PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering](https://mlsanity.com/paper/2305.10415/) (2023)
- [MERLOT: Multimodal Neural Script Knowledge Models](https://mlsanity.com/paper/2106.02636/) (2021)
- [MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data](https://mlsanity.com/paper/2304.08247/) (2023)
- [MIMIC-IT: Multi-Modal In-Context Instruction Tuning](https://mlsanity.com/paper/2306.05425/) (2023)
- [Connecting Vision and Language with Localized Narratives](https://mlsanity.com/paper/1912.03098/) (2019)
- [What does CLIP know about a red circle? Visual prompt engineering for VLMs](https://mlsanity.com/paper/2304.06712/) (2023)
- [Quilt-1M: One Million Image-Text Pairs for Histopathology](https://mlsanity.com/paper/2306.11207/) (2023)
- [MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound](https://mlsanity.com/paper/2201.02639/) (2022)
- [Connecting Vision and Language with Video Localized Narratives](https://mlsanity.com/paper/2302.11217/) (2023)

## Built on by (most cited first, 30 of 86)

- [Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning](https://mlsanity.com/paper/2506.07044/) (2025)
- [LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model](https://mlsanity.com/paper/2402.02544/) (2024)
- [MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models](https://mlsanity.com/paper/2410.13085/) (2024)
- [Perception Tokens Enhance Visual Reasoning in Multimodal Language Models](https://mlsanity.com/paper/2412.03548/) (2024)
- [SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding](https://mlsanity.com/paper/2410.11761/) (2024)
- [A Comprehensive Survey of Foundation Models in Medicine](https://mlsanity.com/paper/2406.10729/) (2024)
- [PathMMU: A Massive Multimodal Expert-Level Benchmark for Understanding and Reasoning in Pathology](https://mlsanity.com/paper/2401.16355/) (2024)
- [WSI-LLaVA: A Multimodal Large Language Model for Whole Slide Image](https://mlsanity.com/paper/2412.02141/) (2024)
- [PathFinder: A Multi-Modal Multi-Agent System for Medical Diagnostic Decision-Making Applied to Histopathology](https://mlsanity.com/paper/2502.08916/) (2025)
- [CPath-Omni: A Unified Multimodal Foundation Model for Patch and Whole Slide Image Analysis in Computational Pathology](https://mlsanity.com/paper/2412.12077/) (2024)
- [CPathAgent: An Agent-based Foundation Model for Interpretable High-Resolution Pathology Image Analysis Mimicking Pathologists' Diagnostic Logic](https://mlsanity.com/paper/2505.20510/) (2025)
- [PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration](https://mlsanity.com/paper/2407.00203/) (2024)
- [Evidence-based diagnostic reasoning with multi-agent copilot for human pathology](https://mlsanity.com/paper/2506.20964/) (2025)
- [MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model](https://mlsanity.com/paper/2406.11193/) (2024)
- [PA-LLaVA: A Large Language-Vision Assistant for Human Pathology Image Understanding](https://mlsanity.com/paper/2408.09530/) (2024)
- [MSCPT: Few-shot Whole Slide Image Classification with Multi-scale and Context-focused Prompt Tuning](https://mlsanity.com/paper/2408.11505/) (2024)
- [MedMO: Grounding and Understanding Multimodal Large Language Model for Medical Images](https://mlsanity.com/paper/2602.06965/) (2026)
- [A Versatile Pathology Co-pilot via Reasoning Enhanced Multimodal Large Language Model](https://mlsanity.com/paper/2507.17303/) (2025)
- [A New Era in Computational Pathology: A Survey on Foundation and Vision-Language Models](https://mlsanity.com/paper/2408.14496/) (2024)
- [Multi-Modal Foundation Models for Computational Pathology: A Survey](https://mlsanity.com/paper/2503.09091/) (2025)
- [Visual Instruction Pretraining for Domain-Specific Foundation Models](https://mlsanity.com/paper/2509.17562/) (2025)
- [HumanVLM: Foundation for Human-Scene Vision-Language Model](https://mlsanity.com/paper/2411.03034/) (2024)
- [GECKO: Gigapixel Vision-Concept Contrastive Pretraining in Histopathology](https://mlsanity.com/paper/2504.01009/) (2025)
- [Medical Large Vision Language Models with Multi-Image Visual Ability](https://mlsanity.com/paper/2505.19031/) (2025)
- [Foundation Models in Medical Imaging: A Review and Outlook](https://mlsanity.com/paper/2506.09095/) (2025)
- [Cost-effective Instruction Learning for Pathology Vision and Language Analysis](https://mlsanity.com/paper/2407.17734/) (2024)
- [Navigating Gigapixel Pathology Images with Large Multimodal Models](https://mlsanity.com/paper/2511.19652/) (2025)
- [PathNavigate: A Training-Free Pathology Agent with Surprise-Guided Scan and Shared Slide Memory for Whole-Slide Image VQA](https://mlsanity.com/paper/2605.23559/) (2026)
- [MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants](https://mlsanity.com/paper/2412.12661/) (2024)
- [Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representation](https://mlsanity.com/paper/2504.18856/) (2025)

## Abstract (arXiv)

Diagnosis in histopathology requires a global whole slide images (WSIs) analysis, requiring pathologists to compound evidence from different WSI patches. The gigapixel scale of WSIs poses a challenge for histopathology multi-modal models. Training multi-model models for histopathology requires instruction tuning datasets, which currently contain information for individual image patches, without a spatial grounding of the concepts within each patch and without a wider view of the WSI. Therefore, they lack sufficient diagnostic capacity for histopathology. To bridge this gap, we introduce Quilt-Instruct, a large-scale dataset of 107,131 histopathology-specific instruction question/answer pairs, grounded within diagnostically relevant image patches that make up the WSI. Our dataset is collected by leveraging educational histopathology videos from YouTube, which provides spatial localization of narrations by automatically extracting the narrators' cursor positions. Quilt-Instruct supports contextual reasoning by extracting diagnosis and supporting facts from the entire WSI. Using Quilt-Instruct, we train Quilt-LLaVA, which can reason beyond the given single image patch, enabling diagnostic reasoning across patches. To evaluate Quilt-LLaVA, we propose a comprehensive evaluation dataset created from 985 images and 1283 human-generated question-answers. We also thoroughly evaluate Quilt-LLaVA using public histopathology datasets, where Quilt-LLaVA significantly outperforms SOTA by over 10% on relative GPT-4 score and 4% and 9% on open and closed set VQA. Our code, data, and model are publicly accessible at quilt-llava.github.io.