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 10761100 of 9051 papers

TitleStatusHype
Quality Controlled Paraphrase GenerationCode1
Learning Affordance Grounding from Exocentric ImagesCode1
MotionAug: Augmentation with Physical Correction for Human Motion PredictionCode1
Attribute Group Editing for Reliable Few-shot Image GenerationCode1
Complex Evolutional Pattern Learning for Temporal Knowledge Graph ReasoningCode1
InsetGAN for Full-Body Image GenerationCode1
Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph ExpertsCode1
The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of RedundancyCode1
Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label EnhancementCode1
Skating-Mixer: Long-Term Sport Audio-Visual Modeling with MLPsCode1
Towards Universal Texture Synthesis by Combining Texton Broadcasting with Noise Injection in StyleGAN-2Code1
Hierarchical Sketch Induction for Paraphrase GenerationCode1
UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translationCode1
Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular ValuesCode1
Biological Sequence Design with GFlowNetsCode1
Self-Supervised Vision Transformers Learn Visual Concepts in HistopathologyCode1
Submodlib: A Submodular Optimization LibraryCode1
VLAD-VSA: Cross-Domain Face Presentation Attack Detection with Vocabulary Separation and AdaptationCode1
Don't Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement LearningCode1
Realistic Blur Synthesis for Learning Image DeblurringCode1
RoPGen: Towards Robust Code Authorship Attribution via Automatic Coding Style TransformationCode1
Agree to Disagree: Diversity through Disagreement for Better TransferabilityCode1
Exploring Inter-Channel Correlation for Diversity-preserved KnowledgeDistillationCode1
Approximating Gradients for Differentiable Quality Diversity in Reinforcement LearningCode1
Red Teaming Language Models with Language ModelsCode1
Show:102550
← PrevPage 44 of 363Next →

No leaderboard results yet.