Views
No views yet
LLaVA-MORE enhances the well-known LLaVA architecture by integrating the use of LLaMA 3.1 as the language model. We are publicly releasing the checkpoints for stages one and two for the first model with 8B parameters.python -u llava/eval/run_llava.py1@article{cocchi2025llava,
2 title={{LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning}},
3 author={Cocchi, Federico and Moratelli, Nicholas and Caffagni, Davide and Sarto, Sara and Baraldi, Lorenzo and Cornia, Marcella and Cucchiara, Rita},
4 journal={arXiv preprint arXiv:2503.15621},
5 year={2025}
6}