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 26312640 of 9051 papers

TitleStatusHype
Behind Recommender Systems: the Geography of the ACM RecSys CommunityCode0
Fine-Grained Spatiotemporal Motion Alignment for Contrastive Video Representation LearningCode0
ADS-Cap: A Framework for Accurate and Diverse Stylized Captioning with Unpaired Stylistic CorporaCode0
FireFly A Synthetic Dataset for Ember Detection in WildfireCode0
Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and FlatnessCode0
From Bytes to Borsch: Fine-Tuning Gemma and Mistral for the Ukrainian Language RepresentationCode0
Bottleneck Analysis of Dynamic Graph Neural Network Inference on CPU and GPUCode0
Improving Transferability of Adversarial Examples with Input DiversityCode0
DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation FusionCode0
FG-RAG: Enhancing Query-Focused Summarization with Context-Aware Fine-Grained Graph RAGCode0
Show:102550
← PrevPage 264 of 906Next →

No leaderboard results yet.