---
title: 'Visual Instruction Tuning'
license: CC-BY-4.0
license_url: https://creativecommons.org/licenses/by/4.0/
license_note: 'paper is CC BY 4.0 (verified on arXiv abs page 2026-11-11; icon by-4.0.png, http://creativecommons.org/licenses/by/4.0/); note is our own summary'
source: https://iinventedlight.com/library/notes/2304-08485-visual-instruction-tuning.md
source_license: 'CC BY 4.0'
attribution: 'Summary by iinventedlight (AI-assisted). Source: Haotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae Lee, Visual Instruction Tuning (CC BY 4.0).'
author: 'iinventedlight (AI-assisted)'
date: 2026-11-11
status: published
approved_by: "Cole Withington, 2026-11-11 20:58 PT, Grok Bot chat widget t1717s7407: \"Publish all 100 including the LLMs Encode Clinical Knowledge note\""
checked_on: 2026-11-11
as_of: 2026-11-11
confidence: medium
untested: 'Not reproduced. Abs page and HTML key sections read 2026-11-11. Named code URLs checked for HTTP 200; code not run.'
category: arxiv
topic_area: 'ai-research: multimodal'
tags: arxiv, multimodal, vision-language, instruction-tuning
arxiv_id: 2304.08485
alias: 2304.08485-visual-instruction-tuning
sources:
  - id: S1
    title: 'Visual Instruction Tuning'
    publisher: arXiv
    authors: 'Haotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae Lee'
    url: https://arxiv.org/abs/2304.08485
    version_read: 'v2 (11 Dec 2023)'
    accessed: 2026-11-11
    license: 'CC BY 4.0'
---
# Visual Instruction Tuning

## Summary
This paper introduces LLaVA, a Large Language and Vision Assistant. The authors use language-only GPT-4 to generate multimodal language-image instruction-following data, then instruction-tune an end-to-end model that connects a vision encoder and an LLM. The vision encoder is the pre-trained CLIP visual encoder ViT-L/14, joined to Vicuna by a simple linear layer that maps image features into the word embedding space. They collect 158K unique language-image instruction-following samples in total. When fine-tuned on Science QA, the synergy of LLaVA and GPT-4 reaches a new state-of-the-art accuracy of 92.53%. LLaVA demonstrates impressive multimodal chat abilities, and the authors make the data, model, and code publicly available. [S1]

## Claims
- id: C1
  claim: 'LLaVA connects a vision encoder and an LLM for visual and language understanding.'
  source: S1
  evidence: "connects a vision encoder and an LLM"
- id: C2
  claim: 'They collect 158K unique language-image instruction-following samples in total.'
  source: S1
  evidence: "158K unique language-image instruction-following samples in total"
- id: C3
  claim: 'When fine-tuned on Science QA, LLaVA plus GPT-4 reaches 92.53% accuracy.'
  source: S1
  evidence: "the synergy of LLaVA and GPT-4 achieves a new state-of-the-art accuracy of 92.53%"

## Verification
- Code available: Paper points to https://llava-vl.github.io, which returned HTTP 200 on 2026-11-11. The HTML also names the anonymized GitHub repo LLaVA-Annonymous/LLaVA (HTTP 200). The public code repo https://github.com/haotian-liu/LLaVA also returned HTTP 200. Code not run.
- Reproduced: not reproduced (2026-11-11). Code not run.
- Related work: Live notes [ao-evals-multimodal-agents](https://iinventedlight.com/library/notes/ao-evals-multimodal-agents/). This batch also has pointer notes for CLIP and Flamingo, which this recipe builds on.
- Limits: The authors discuss chatbot failures on the in-the-wild bench, including cases that need high-resolution images, wide knowledge coverage, or multilingual reading. Appendix A also flags hallucination, biases, and evaluation complexities.
- License: CC BY 4.0 on the abs page (2026-11-11; icon by-4.0.png; http://creativecommons.org/licenses/by/4.0/). Submitted 17 Apr 2023 (v1); last revised 11 Dec 2023 (v2). Comments: NeurIPS 2023 Oral. Sources: [S1] https://arxiv.org/abs/2304.08485, v2 (11 Dec 2023). checked_on: 2026-11-11.

## When to apply
Use when asking how an open vision-language assistant was built by connecting a frozen CLIP encoder to a chat LLM with a linear projector and visual instruction data.

## Facts
- id: F1
  claim: 'LLaVA connects the CLIP ViT-L/14 vision encoder to Vicuna with a simple linear layer.'
  confidence: medium
  date: 2026-11-11
  sources: [S1]
  license: CC BY 4.0
- id: F2
  claim: 'The authors collect 158K unique language-image instruction-following samples in total.'
  confidence: medium
  date: 2026-11-11
  sources: [S1]
  license: CC BY 4.0
- id: F3
  claim: 'Fine-tuned on Science QA, the synergy of LLaVA and GPT-4 reaches 92.53% accuracy.'
  confidence: medium
  date: 2026-11-11
  sources: [S1]
  license: CC BY 4.0

## Sources
- [S1] arXiv 2304.08485, https://arxiv.org/abs/2304.08485. License: CC BY 4.0. v2 (11 Dec 2023). Accessed 2026-11-11.

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Summary by iinventedlight (AI-assisted). Paper is CC BY 4.0.

---

Agents: [/agents.md](/agents.md) | [/.well-known/agent-library.json](/.well-known/agent-library.json).