List your company

Speech Question Answering on English High School Listening Test (EHSL)

50Long Speech AccuracyUni-MoE w/ MoE-Task4 (4E) + Aux loss
-1.303212.015925.33538.6541May 18, 2024

Evaluation results

MethodLinks
Uni-MoE w/ MoE-Task4 (4E) + Aux lossModality=I,T,S,V, Training Task Strategy=MoE-Task4, Number of Experts=4, Auxiliary Balancing Loss=true2024.055054
Uni-MoE w/ MoE-Task4 (8E)Modality=I,T,S,V, Training Task Strategy=MoE-Task4, Number of Experts=82024.0548.6746
Uni-MoE w/ MoE-Task4 (4E)Modality=I,T,S,V, Training Task Strategy=MoE-Task4, Number of Experts=42024.054858.67
Uni-MoE w/ MoE-Task2 (4E)Modality=I,T,S,V, Training Task Strategy=MoE-Task2, Number of Experts=42024.054248
Uni-MoE w/ MoE-Task4 (8E) + Aux lossModality=I,T,S,V, Training Task Strategy=MoE-Task4, Number of Experts=8, Auxiliary Balancing Loss=true2024.054250
Uni-MoE w/ MoE-Task1 (4E)Modality=I,T,S, Training Task Strategy=MoE-Task1, Number of Experts=42024.0541.3336
Single-Modality-Expert-Task6Modality=I,T,S, Training Task Strategy=MoE-Task62024.0518.678
Single-Modality-Expert-Task5Modality=I,T,S, Training Task Strategy=MoE-Task52024.059.3312
Macaw-LLMModality=Image, Text, Audio, Video2024.050.672
X-InstructBLIPModality=Image, Text, Audio, Video2024.050.672