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 11211130 of 9051 papers

TitleStatusHype
DebateQA: Evaluating Question Answering on Debatable KnowledgeCode1
A Flexible Framework for Designing Trainable Priors with Adaptive Smoothing and Game EncodingCode1
Analysis of diversity-accuracy tradeoff in image captioningCode1
Contrastive Model Inversion for Data-Free Knowledge DistillationCode1
Contrastive Syn-to-Real GeneralizationCode1
Device-Robust Acoustic Scene Classification via Impulse Response AugmentationCode1
A View From Somewhere: Human-Centric Face RepresentationsCode1
DGRec: Graph Neural Network for Recommendation with Diversified Embedding GenerationCode1
Accelerating Score-based Generative Models with Preconditioned Diffusion SamplingCode1
Contrastive Losses Are Natural Criteria for Unsupervised Video SummarizationCode1
Show:102550
← PrevPage 113 of 906Next →

No leaderboard results yet.