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 701710 of 9051 papers

TitleStatusHype
Exploiting Abstract Meaning Representation for Open-Domain Question AnsweringCode1
Explore-Instruct: Enhancing Domain-Specific Instruction Coverage through Active ExplorationCode1
An Empirical Study of Vehicle Re-Identification on the AI City ChallengeCode1
Improving Semi-supervised Federated Learning by Reducing the Gradient Diversity of ModelsCode1
Diversity-based Trajectory and Goal Selection with Hindsight Experience ReplayCode1
Diversity Enhanced Active Learning with Strictly Proper Scoring RulesCode1
Diversity-Guided MLP Reduction for Efficient Large Vision TransformersCode1
Diversify Your Vision Datasets with Automatic Diffusion-Based AugmentationCode1
CityPersons: A Diverse Dataset for Pedestrian DetectionCode1
Diversify Question Generation with Retrieval-Augmented Style TransferCode1
Show:102550
← PrevPage 71 of 906Next →

No leaderboard results yet.