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 851–875 of 9051 papers

TitleStatusHype
Agree to Disagree: Adaptive Ensemble Knowledge Distillation in Gradient SpaceCode1
Controllable Text Generation via Probability Density Estimation in the Latent SpaceCode1
Agree to Disagree: Diversity through Disagreement for Better TransferabilityCode1
Vision Transformers with Patch DiversificationCode1
Improving Contrastive Learning on Imbalanced Data via Open-World SamplingCode1
Inversion Circle Interpolation: Diffusion-based Image Augmentation for Data-scarce ClassificationCode1
Improving Generalization in Reinforcement Learning with Mixture RegularizationCode1
A Sentence Cloze Dataset for Chinese Machine Reading ComprehensionCode1
Controllable Video Captioning with an Exemplar SentenceCode1
Augmenting Sequential Recommendation with Balanced Relevance and DiversityCode1
Controllable Multi-Interest Framework for RecommendationCode1
2D medical image synthesis using transformer-based denoising diffusion probabilistic modelCode1
AbGPT: De Novo Antibody Design via Generative Language ModelingCode1
Controllable Open-ended Question Generation with A New Question Type OntologyCode1
Inducing High Energy-Latency of Large Vision-Language Models with Verbose ImagesCode1
Industrial Anomaly Detection with Domain Shift: A Real-world Dataset and Masked Multi-scale ReconstructionCode1
Controlling Behavioral Diversity in Multi-Agent Reinforcement LearningCode1
Covariance Matrix Adaptation for the Rapid Illumination of Behavior SpaceCode1
Input-Aware Dynamic Backdoor AttackCode1
InsetGAN for Full-Body Image GenerationCode1
D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data PruningCode1
Contrastive Quantization with Code Memory for Unsupervised Image RetrievalCode1
Contrastive Model Inversion for Data-Free Knowledge DistillationCode1
Instruction-Tuning Data Synthesis from Scratch via Web ReconstructionCode1
Contrastive Syn-to-Real GeneralizationCode1
Show:102550
← PrevPage 35 of 363Next →

No leaderboard results yet.