SOTAVerified

Diversity

Diversity in data sampling is crucial across various use cases, including search, recommendation systems, and more. Ensuring diverse samples means capturing a wide range of variations and perspectives, which leads to more robust, unbiased, and comprehensive models. In search use cases, for instance, diversity helps avoid redundancy, ensuring that users are exposed to a broader set of relevant information rather than repeated similar results.

Papers

Showing 18811890 of 9051 papers

TitleStatusHype
Leveraging Open Knowledge for Advancing Task Expertise in Large Language ModelsCode0
Improved Robustness Against Adaptive Attacks With Ensembles and Error-Correcting Output CodesCode0
Comparison of Diverse Decoding Methods from Conditional Language ModelsCode0
Improved Generation of Synthetic Imaging Data Using Feature-Aligned DiffusionCode0
Artificial Immune System of Secure Face Recognition Against Adversarial AttacksCode0
Improved Image Segmentation via Cost Minimization of Multiple HypothesesCode0
Improved Benthic Classification using Resolution Scaling and SymmNet Unsupervised Domain AdaptationCode0
ABD-Net: Attentive but Diverse Person Re-IdentificationCode0
Improved Generalization of Weight Space Networks via AugmentationsCode0
Improving Adversarial Robustness via Decoupled Visual Representation MaskingCode0
Show:102550
← PrevPage 189 of 906Next →

No leaderboard results yet.