List your company

Temporal Sound Event Localization on Controlled Sound Event Sequence Benchmark

98.91Overlap (Begin)Audio Flamingo 3
17.68638.77359.8680.947Jun 9, 2026

Evaluation results

MethodLinks
Audio Flamingo 3Model=Audio Flamingo 3 (AF3), Prompting=Direct (explicit timestamp output)2026.0698.9133.467.8746.75
Audio Flamingo 3 (Window)Model=Audio Flamingo 3 (AF3), Technique=Instruction-based vector steering2026.0673.9848.3183.8768.72
Qwen2-Audio (Window)Model=Qwen2-Audio, Technique=Instruction-based vector steering2026.0636.973.3972.3260.87
Qwen2-AudioModel=Qwen2-Audio, Prompting=Direct (explicit timestamp output)2026.0636.8653.045.6131.84
RandomDescription=Places the window uniformly at random across valid positions2026.0620.8141.6120.8127.74