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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 3651–3675 of 9051 papers

TitleStatusHype
Robust Fraud Detection via Supervised Contrastive Learning—0
Liquid Crystal-Based RIS for VLC Transmitters: Performance Analysis, Challenges, and Opportunities—0
Digital Twin-Oriented Complex Networked Systems based on Heterogeneous Node Features and Interaction Rules—0
Attesting Distributional Properties of Training Data for Machine LearningCode0
Exploring Sampling Techniques for Generating Melodies with a Transformer Language Model—0
Diverse Cotraining Makes Strong Semi-Supervised SegmentorCode1
Minimum Coverage Sets for Training Robust Ad Hoc Teamwork Agents—0
LaRS: A Diverse Panoptic Maritime Obstacle Detection Dataset and BenchmarkCode1
Language-guided Human Motion Synthesis with Atomic ActionsCode1
LesionMix: A Lesion-Level Data Augmentation Method for Medical Image SegmentationCode0
Mitigating Semantic Confusion from Hostile Neighborhood for Graph Active LearningCode0
Text-Only Training for Visual Storytelling—0
Diversifying AI: Towards Creative Chess with AlphaZero—0
Globe230k: A Benchmark Dense-Pixel Annotation Dataset for Global Land Cover Mapping—0
Flickr Africa: Examining Geo-Diversity in Large-Scale, Human-Centric Visual Data—0
Non-monotone Sequential Submodular Maximization—0
Diff-CAPTCHA: An Image-based CAPTCHA with Security Enhanced by Denoising Diffusion Model—0
Ranking-aware Uncertainty for Text-guided Image Retrieval—0
Lightweight Adaptation of Neural Language Models via Subspace EmbeddingCode0
Steering Language Generation: Harnessing Contrastive Expert Guidance and Negative Prompting for Coherent and Diverse Synthetic Data Generation—0
Learning from All Sides: Diversified Positive Augmentation via Self-distillation in Recommendation—0
Emotion Embeddings x2014 Learning Stable and Homogeneous Abstractions from Heterogeneous Affective Datasets—0
EcomGPT: Instruction-tuning Large Language Models with Chain-of-Task Tasks for E-commerceCode2
OpenGCD: Assisting Open World Recognition with Generalized Category DiscoveryCode1
Neural Categorical Priors for Physics-Based Character Control—0
Show:102550
← PrevPage 147 of 363Next →

No leaderboard results yet.