Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Narratives

Benchmarks

Task NameDataset NameSOTA ResultTrend
cross-subject fMRI-to-text decodingNarratives
BLEU-127.8
9
3-class classificationNarratives 54 narratives, 48,640 samples (held-out)
Aligned Accuracy57.8
4
Showing 2 of 2 rows