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 10311040 of 9051 papers

TitleStatusHype
Rethinking Fano's Inequality in Ensemble LearningCode1
GeoMLAMA: Geo-Diverse Commonsense Probing on Multilingual Pre-Trained Language ModelsCode1
KERPLE: Kernelized Relative Positional Embedding for Length ExtrapolationCode1
UCC: Uncertainty guided Cross-head Co-training for Semi-Supervised Semantic SegmentationCode1
Diverse Weight Averaging for Out-of-Distribution GeneralizationCode1
Self-supervised Assisted Active Learning for Skin Lesion SegmentationCode1
DendroMap: Visual Exploration of Large-Scale Image Datasets for Machine Learning with TreemapsCode1
TreeMix: Compositional Constituency-based Data Augmentation for Natural Language UnderstandingCode1
What's in a Caption? Dataset-Specific Linguistic Diversity and Its Effect on Visual Description Models and MetricsCode1
M3ED: Multi-modal Multi-scene Multi-label Emotional Dialogue DatabaseCode1
Show:102550
← PrevPage 104 of 906Next →

No leaderboard results yet.