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 13711380 of 9051 papers

TitleStatusHype
Contrastive Model Inversion for Data-Free Knowledge DistillationCode1
Latent Denoising Diffusion GAN: Faster sampling, Higher image qualityCode1
Lattice CNNs for Matching Based Chinese Question AnsweringCode1
Calliar: An Online Handwritten Dataset for Arabic CalligraphyCode1
CALM : A Multi-task Benchmark for Comprehensive Assessment of Language Model BiasCode1
Advancing Fine-Grained Classification by Structure and Subject Preserving AugmentationCode1
Learning Diverse Risk Preferences in Population-based Self-playCode1
CamContextI2V: Context-aware Controllable Video GenerationCode1
Contrastive Quantization with Code Memory for Unsupervised Image RetrievalCode1
Controllable Group Choreography using Contrastive DiffusionCode1
Show:102550
← PrevPage 138 of 906Next →

No leaderboard results yet.