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 10411050 of 9051 papers

TitleStatusHype
Attracting and Dispersing: A Simple Approach for Source-free Domain AdaptationCode1
Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-SpeechCode1
Continual Object Detection via Prototypical Task Correlation Guided Gating MechanismCode1
Seed-Guided Topic Discovery with Out-of-Vocabulary SeedsCode1
RU-Net: Regularized Unrolling Network for Scene Graph GenerationCode1
Learning from Missing Relations: Contrastive Learning with Commonsense Knowledge Graphs for Commonsense InferenceCode1
RoSA: A Robust Self-Aligned Framework for Node-Node Graph Contrastive LearningCode1
User-controllable Recommendation Against Filter BubblesCode1
Where in the World is this Image? Transformer-based Geo-localization in the WildCode1
DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response GenerationCode1
Show:102550
← PrevPage 105 of 906Next →

No leaderboard results yet.