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 4526–4550 of 9051 papers

TitleStatusHype
Ada-adapter:Fast Few-shot Style Personlization of Diffusion Model with Pre-trained Image Encoder—0
Improving Low-Resource Sequence Labeling with Knowledge Fusion and Contextual Label Explanations—0
Improving Maximum Likelihood Training for Text Generation with Density Ratio Estimation—0
Blessing of Class Diversity in Pre-training—0
Improving Multilingual Instruction Finetuning via Linguistically Natural and Diverse Datasets—0
Improving Multimodal Joint Variational Autoencoders through Normalizing Flows and Correlation Analysis—0
Improving negation detection with negation-focused pre-training—0
Improving negation detection with negation-focused pre-training—0
TopicDiff: A Topic-enriched Diffusion Approach for Multimodal Conversational Emotion Detection—0
Topic-focused Dynamic Information Filtering in Social Media—0
Improving Neural Machine Translation Robustness via Data Augmentation: Beyond Back Translation—0
Topic Modeling as Multi-Objective Contrastive Optimization—0
Improving Neural Network Generalization via Promoting Within-Layer Diversity—0
Topic Modeling in Marathi—0
Improving NSGA-II with an Adaptive Mutation Operator—0
Black Feminist Musings on Algorithmic Oppression—0
Improving Out-of-Distribution Robustness of Classifiers Through Interpolated Generative Models—0
Improving Out-of-Distribution Robustness of Classifiers via Generative Interpolation—0
Improving performance of aircraft detection in satellite imagery while limiting the labelling effort: Hybrid active learning—0
Improving Personalized Dialogue Generation Models with Data-level Distillation and Diversification—0
Improving Personalized Explanation Generation through Visualization—0
Improving Pre-trained Language Models with Syntactic Dependency Prediction Task for Chinese Semantic Error Recognition—0
Improving Query Safety at Pinterest—0
Improving Recommendation Diversity by Highlighting the ExTrA Fabricated Experts—0
Improving Recommendation System Serendipity Through Lexicase Selection—0
Show:102550
← PrevPage 182 of 363Next →

No leaderboard results yet.