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 11811190 of 9051 papers

TitleStatusHype
Improve Student's Reasoning Generalizability through Cascading Decomposed CoTs DistillationCode1
BenthicNet: A global compilation of seafloor images for deep learning applicationsCode1
2D medical image synthesis using transformer-based denoising diffusion probabilistic modelCode1
Contextual Diversity for Active LearningCode1
Continual Object Detection via Prototypical Task Correlation Guided Gating MechanismCode1
Continual Variational Autoencoder Learning via Online Cooperative MemorizationCode1
From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP ModelsCode1
Contrastive Losses Are Natural Criteria for Unsupervised Video SummarizationCode1
Contrastive Model Inversion for Data-Free Knowledge DistillationCode1
Boosting Human-Object Interaction Detection with Text-to-Image Diffusion ModelCode1
Show:102550
← PrevPage 119 of 906Next →

No leaderboard results yet.