Login / Signup

LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark.

Zhenfei YinJiong WangJianjian CaoZhelun ShiDingning LiuMukai LiLu ShengLei BaiXiaoshui HuangZhiyong WangJing ShaoWanli Ouyang
Published in: CoRR (2023)
Keyphrases
  • multi modal
  • cross modal
  • multi modality
  • audio visual
  • multiple modalities
  • language learning
  • machine learning
  • image segmentation
  • high level
  • feature extraction