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

New-feature

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mixture of Block Attention (MoBA) implementationNew-feature tasks
Session Duration38.7
3
Differential Transformer (Diff) implementationNew-feature tasks
Session Duration38.2
3
Showing 2 of 2 rows