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 426450 of 9051 papers

TitleStatusHype
Agree to Disagree: Diversity through Disagreement for Better TransferabilityCode1
AffordPose: A Large-scale Dataset of Hand-Object Interactions with Affordance-driven Hand PoseCode1
Deep Sketch-Based Modeling: Tips and TricksCode1
Calliar: An Online Handwritten Dataset for Arabic CalligraphyCode1
Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human ProgrammersCode1
BiRT: Bio-inspired Replay in Vision Transformers for Continual LearningCode1
Deep Time Series Forecasting with Shape and Temporal CriteriaCode1
Automating Rigid Origami DesignCode1
Synth-Empathy: Towards High-Quality Synthetic Empathy DataCode1
Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity RecognitionCode1
Diffusion Reward: Learning Rewards via Conditional Video DiffusionCode1
DiffWave: A Versatile Diffusion Model for Audio SynthesisCode1
Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech EnhancementCode1
Active learning for medical image segmentation with stochastic batchesCode1
Beyond Trivial Counterfactual Explanations with Diverse Valuable ExplanationsCode1
Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text GenerationCode1
DisCup: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text GenerationCode1
Distribution-aware Knowledge Prototyping for Non-exemplar Lifelong Person Re-identificationCode1
Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problemCode1
Biological Sequence Design with GFlowNetsCode1
Bilingual Mutual Information Based Adaptive Training for Neural Machine TranslationCode1
A Hierarchical Probabilistic U-Net for Modeling Multi-Scale AmbiguitiesCode1
AutoMix: Automatically Mixing Language ModelsCode1
Benchmarking Algorithms for Federated Domain GeneralizationCode1
DEFN: Dual-Encoder Fourier Group Harmonics Network for Three-Dimensional Indistinct-Boundary Object SegmentationCode1
Show:102550
← PrevPage 18 of 363Next →

No leaderboard results yet.