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 49414950 of 9051 papers

TitleStatusHype
Reducing the Scope of Language Models0
Redundancy Aware Multi-Reference Based Gainwise Evaluation of Extractive Summarization0
Label-Based Diversity Measure Among Hidden Units of Deep Neural Networks: A Regularization Method0
ReelFramer: Human-AI Co-Creation for News-to-Video Translation0
Reference-Guided Verdict: LLMs-as-Judges in Automatic Evaluation of Free-Form Text0
Self-paced Multi-grained Cross-modal Interaction Modeling for Referring Expression Comprehension0
Regional Adversarial Training for Better Robust Generalization0
Region-level Active Detector Learning0
Regularized Attentive Capsule Network for Overlapped Relation Extraction0
Regularized directional representations for medical image registration0
Show:102550
← PrevPage 495 of 906Next →

No leaderboard results yet.