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 10211030 of 9051 papers

TitleStatusHype
On the Embedding Collapse when Scaling up Recommendation ModelsCode1
On the Role of Conceptualization in Commonsense Knowledge Graph ConstructionCode1
Control, Generate, Augment: A Scalable Framework for Multi-Attribute Text GenerationCode1
Contrastive Model Inversion for Data-Free Knowledge DistillationCode1
Contrastive Losses Are Natural Criteria for Unsupervised Video SummarizationCode1
Contrastive Quantization with Code Memory for Unsupervised Image RetrievalCode1
Controllable and Guided Face Synthesis for Unconstrained Face RecognitionCode1
Continual Object Detection via Prototypical Task Correlation Guided Gating MechanismCode1
ADASR: An Adversarial Auto-Augmentation Framework for Hyperspectral and Multispectral Data FusionCode1
Continual Variational Autoencoder Learning via Online Cooperative MemorizationCode1
Show:102550
← PrevPage 103 of 906Next →

No leaderboard results yet.