https://tiger-ai-lab.github.io/Mantis/

Official code for Paper "Mantis: Multi-Image Instruction Tuning" [TMLR2024]
https://tiger-ai-lab.github.io/Mantis/

fuyu language llava-llama3 lmm mantis mllm multi-image-understanding multimodal video vision vlm

Last synced: about 2 months ago
JSON representation

Official code for Paper "Mantis: Multi-Image Instruction Tuning" [TMLR2024]

• Host: GitHub
• URL: https://tiger-ai-lab.github.io/Mantis/
• Owner: TIGER-AI-Lab
• License: apache-2.0
• Created: 2024-04-12T05:28:40.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2025-03-23T23:37:51.000Z (2 months ago)
• Last Synced: 2025-04-02T19:46:01.764Z (about 2 months ago)
• Topics: fuyu, language, llava-llama3, lmm, mantis, mllm, multi-image-understanding, multimodal, video, vision, vlm
• Language: Python
• Homepage: https://tiger-ai-lab.github.io/Mantis/
• Size: 83.6 MB
• Stars: 210
• Watchers: 9
• Forks: 20
• Open Issues: 4
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-LLMs-finetuning - Project - AI-Lab/Mantis) (4. Fine-Tuning / Papers)