ChronusOmni: Improving Time Awareness of Omni-Modal Large Language Models
Open paper
Benchmark
Model
Rank
Results
audio-visual-question-answering-on-dailyomni
ChronusOmni
–
Accuracy: 72.3
audio-visual-question-answering-on-music-avqa
ChronusOmni
–
Acc: 66.0
audio-visual-question-answering-on-worldsense
ChronusOmni
–
Accuracy: 47.8
Rank counts only results with a code link.