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 11911200 of 9051 papers

TitleStatusHype
Controllable Group Choreography using Contrastive DiffusionCode1
Controllable and Guided Face Synthesis for Unconstrained Face RecognitionCode1
Controllable Multi-Interest Framework for RecommendationCode1
Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human ProgrammersCode1
Contrastive Syn-to-Real GeneralizationCode1
Efficient Facial Feature Learning with Wide Ensemble-based Convolutional Neural NetworksCode1
BLEU might be Guilty but References are not InnocentCode1
Efficient Object Detection in Autonomous Driving using Spiking Neural Networks: Performance, Energy Consumption Analysis, and Insights into Open-set Object DiscoveryCode1
Contrastive Quantization with Code Memory for Unsupervised Image RetrievalCode1
Control, Generate, Augment: A Scalable Framework for Multi-Attribute Text GenerationCode1
Show:102550
← PrevPage 120 of 906Next →

No leaderboard results yet.