Search Results for author:
Found 2 papers, 2 papers with code
Multi-modal preference alignment remedies regression of visual instruction tuning on language model
In conclusion, we propose a distillation-based multi-modal alignment model with fine-grained annotations on a small dataset that reconciles the textual and visual performance of MLLMs, restoring and boosting language capability after visual instruction tuning.
SciGraphQA: A Large-Scale Synthetic Multi-Turn Question-Answering Dataset for Scientific Graphs
We asked GPT-4 to assess the matching quality of our question-answer turns given the paper's context, obtaining an average rating of 8. 7/10 on our 3K test set.
Ranked #1 on
Visual Question Answering (VQA)
on SciGraphQA
Cannot find the paper you are looking for? You can
Submit a new open access paper.
