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 751760 of 9051 papers

TitleStatusHype
Apples to Apples: A Systematic Evaluation of Topic ModelsCode1
Context-Transformer: Tackling Object Confusion for Few-Shot DetectionCode1
Conditioned Query Generation for Task-Oriented Dialogue SystemsCode1
Conditioned Text Generation with Transfer for Closed-Domain Dialogue SystemsCode1
Content-aware Tile Generation using Exterior Boundary InpaintingCode1
Considering user agreement in learning to predict the aesthetic qualityCode1
Improving Semi-supervised Federated Learning by Reducing the Gradient Diversity of ModelsCode1
DreamDA: Generative Data Augmentation with Diffusion ModelsCode1
Contextual Diversity for Active LearningCode1
DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking TasksCode1
Show:102550
← PrevPage 76 of 906Next →

No leaderboard results yet.