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 1276–1300 of 9051 papers

TitleStatusHype
BlendX: Complex Multi-Intent Detection with Blended PatternsCode1
GenPlot: Increasing the Scale and Diversity of Chart Derendering DataCode1
CoT-ICL Lab: A Petri Dish for Studying Chain-of-Thought Learning from In-Context DemonstrationsCode1
Curiosity-Driven Reinforcement Learning from Human FeedbackCode1
Deep Batch Active Learning by Diverse, Uncertain Gradient Lower BoundsCode1
Contrastive Losses Are Natural Criteria for Unsupervised Video SummarizationCode1
Contrastive Identity-Aware Learning for Multi-Agent Value DecompositionCode1
Goals as Reward-Producing ProgramsCode1
G-Eval: NLG Evaluation using GPT-4 with Better Human AlignmentCode1
GPT-generated Text Detection: Benchmark Dataset and Tensor-based Detection MethodCode1
Graph Meta Network for Multi-Behavior RecommendationCode1
Greedy Bayesian Posterior Approximation with Deep EnsemblesCode1
grenedalf: population genetic statistics for the next generation of pool sequencingCode1
Contrastive Model Inversion for Data-Free Knowledge DistillationCode1
BoostTree and BoostForest for Ensemble LearningCode1
Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable DiffusionCode1
GS-Blur: A 3D Scene-Based Dataset for Realistic Image DeblurringCode1
Continual Variational Autoencoder Learning via Online Cooperative MemorizationCode1
Contrastive Quantization with Code Memory for Unsupervised Image RetrievalCode1
Data Curation Alone Can Stabilize In-context LearningCode1
Harvesting Event Schemas from Large Language ModelsCode1
Heterogeneous Multi-task Learning with Expert DiversityCode1
Boosting Human-Object Interaction Detection with Text-to-Image Diffusion ModelCode1
Contextual Diversity for Active LearningCode1
Context-Transformer: Tackling Object Confusion for Few-Shot DetectionCode1
Show:102550
← PrevPage 52 of 363Next →

No leaderboard results yet.