Omni-CLST: Error-aware Curriculum Learning with guided Selective chain-of-Thought for audio question answering
Open paper
Benchmark
Model
Rank
Results
audio-understanding-reasoning-on-mmau
Omni-CLST
#2
Accuracy (Avg, Test-mini): 73.80
audio-understanding-reasoning-on-mmau
Omni-CL-CoT
#3
Accuracy (Avg, Test-mini): 73.20
Rank counts only results with a code link.