DreamLLM: Synergistic Multimodal Comprehension and Creation

Open paper
Benchmark Model Rank Results
visual-question-answering-on-mmbenchDreamLLM-7B#5GPT-3.5 score: 49.9
visual-question-answering-on-mm-vetDreamLLM-7B#131GPT-4 score: 35.9Params: 7B

Rank counts only results with a code link.