Visual Instruction Tuning
Abstrak
Instruction tuning large language models (LLMs) using machine-generated instruction-following data has improved zero-shot capabilities on new tasks, but the idea is less explored in the multimodal field. In this paper, we present the first attempt to use language-only GPT-4 to generate multimodal language-image instruction-following data. By instruction tuning on such generated data, we introduce LLaVA: Large Language and Vision Assistant, an end-to-end trained large multimodal model that connects a vision encoder and LLM for general-purpose visual and language understanding.Our early experiments show that LLaVA demonstrates impressive multimodel chat abilities, sometimes exhibiting the behaviors of multimodal GPT-4 on unseen images/instructions, and yields a 85.1% relative score compared with GPT-4 on a synthetic multimodal instruction-following dataset. When fine-tuned on Science QA, the synergy of LLaVA and GPT-4 achieves a new state-of-the-art accuracy of 92.53%. We make GPT-4 generated visual instruction tuning data, our model and code base publicly available.
Topik & Kata Kunci
Penulis (4)
Haotian Liu
Chunyuan Li
Qingyang Wu
Yong Jae Lee
Akses Cepat
- Tahun Terbit
- 2023
- Bahasa
- en
- Total Sitasi
- 8745×
- Sumber Database
- Semantic Scholar
- DOI
- 10.48550/arXiv.2304.08485
- Akses
- Open Access ✓