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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 6126–6150 of 9051 papers

TitleStatusHype
Correcting Exposure Bias for Link RecommendationCode0
Post-hoc loss-calibration for Bayesian neural networks—0
LENAS: Learning-based Neural Architecture Search and Ensemble for 3D Radiotherapy Dose PredictionCode0
Modeling Language Usage and Listener Engagement in Podcasts—0
Topology-Preserved Human Reconstruction with DetailsCode0
Deep Probabilistic Koopman: Long-term time-series forecasting under periodic uncertainties—0
Learning distinct features helps, provably—0
Overcoming Difficulty in Obtaining Dark-skinned Subjects for Remote-PPG by Synthetic Augmentation—0
Unsupervised Behaviour Discovery with Quality-Diversity OptimisationCode1
Learning to See by Looking at NoiseCode1
Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games—0
Energy-Based Models for Code Generation under Compilability ConstraintsCode1
Ex uno plures: Splitting One Model into an Ensemble of Subnetworks—0
Taxonomy of Machine Learning Safety: A Survey and Primer—0
Loss function based second-order Jensen inequality and its application to particle variational inference—0
UniKeyphrase: A Unified Extraction and Generation Framework for Keyphrase PredictionCode1
Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer—0
Progressive Open-Domain Response Generation with Multiple Controllable Attributes—0
EventDrop: data augmentation for event-based learningCode0
Generating Relevant and Coherent Dialogue Responses using Self-separated Conditional Variational AutoEncoders—0
Differentiable Quality DiversityCode1
PcDGAN: A Continuous Conditional Diverse Generative Adversarial Network For Inverse DesignCode1
GTM: A Generative Triple-Wise Model for Conversational Question Generation—0
Refiner: Refining Self-attention for Vision TransformersCode1
Diversity driven Query Rewriting in Search Advertising—0
Show:102550
← PrevPage 246 of 363Next →

No leaderboard results yet.