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

Various

Benchmarks

Task NameDataset NameSOTA ResultTrend
Audio ReconstructionVarious (test)
PESQ3.27
11
Network Intrusion DetectionVarious
F1 Score89.1
1
Long-context compression and memory managementVarious SCM, HotpotQA, MS-MARCO, SQuAD, LongBench, Ruler, InfiniteBench, LOCOMO, LOCCO
Execution Time Reduction21.45
1
Device-Directed Speech DetectionVarious Comparison of published systems
Metric-
0
Showing 4 of 4 rows