多模态大模型#

学习资料#

开源项目#

• LLaVA
  • [2023.10] Improved Baselines with Visual Instruction Tuning
  • [2023.04] Visual Instruction Tuning
• minimind-v 极简vlm模型
• [2025.01] MiniMax-01: Scaling Foundation Models with Lightning Attention
  • MiniMax-AI/MiniMax-01
• [2025.04] Kimi-VL Technical Report
  • MoonshotAI/Kimi-VL

Qwen#

• Qwen-VL
  • [2023.08] Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Deepseek#

• DeepSeek-VL

核心模块#

Encoder-Decoder#

• [2021.02] Learning Transferable Visual Models From Natural Language Supervision
  • openai-clip
  • clip-vit-base-patch16