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 13811390 of 9051 papers

TitleStatusHype
Contrastive Losses Are Natural Criteria for Unsupervised Video SummarizationCode1
Continual Learning for Image Segmentation with Dynamic QueryCode1
An Optimistic Perspective on Offline Deep Reinforcement LearningCode1
Learning Memory-guided Normality for Anomaly DetectionCode1
Learning Semantic-Aligned Feature Representation for Text-based Person SearchCode1
Learning Semantic Latent Directions for Accurate and Controllable Human Motion PredictionCode1
Can 3D Vision-Language Models Truly Understand Natural Language?Code1
Learning to Generate Novel Scene Compositions from Single Images and VideosCode1
Learning to Imagine: Diversify Memory for Incremental Learning using Unlabeled DataCode1
ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency DistillationCode1
Show:102550
← PrevPage 139 of 906Next →

No leaderboard results yet.