STIC
STIC copied to clipboard
Enhancing Large Vision Language Models with Self-Training on Image Comprehension.
### Question  When I downloaded the corresponding data and ran run/dpo_finetune.sh, this error occurred.
### Question Great job! But I have a question, why are the results in the paper different from the official results of llava? The results officially reported by LLaVA-1.6 will...
### Describe the issue Hi there. A nice work! When I tried to reproduce the result of STIC, I did not see the improvement of STIC-stage1-preference optimization. The training setting...