An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models
Research paper by Yadong Lu and collaborators. Published 2023-09-18. Topics: LLaVA, MiniGPT-4, parameter-efficient training methods, LoRA, QLoRA.
Resource information
- Authors
- Yadong Lu, Chunyuan Li, Haotian Liu, Jianwei Yang, Yelong Shen
- Research topics
- LLaVA, MiniGPT-4, parameter-efficient training methods, LoRA, QLoRA, full-model fine-tuning, image resolution, data mixing, multi-modal capabilities, language capabilities, real-world tasks
- Publication date
- 2023-09-18
- Publication
- arXiv
- Last record update
- Nov 3, 2026