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 44814490 of 9051 papers

TitleStatusHype
Multi-Metric AutoRec for High Dimensional and Sparse User Behavior Data Prediction0
On-the-fly Denoising for Data Augmentation in Natural Language UnderstandingCode0
Efficient aggregation of face embeddings for decentralized face recognition deployments (extended version)0
A Pattern Discovery Approach to Multivariate Time Series Forecasting0
CausalDialogue: Modeling Utterance-level Causality in ConversationsCode0
Data Curation Alone Can Stabilize In-context LearningCode1
Unleashing the Power of Visual Prompting At the Pixel LevelCode0
DISCO: Distilling Counterfactuals with Large Language ModelsCode1
DimonGen: Diversified Generative Commonsense Reasoning for Explaining Concept RelationshipsCode0
Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization0
Show:102550
← PrevPage 449 of 906Next →

No leaderboard results yet.