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 43264350 of 9051 papers

TitleStatusHype
Reanalyzing L2 Preposition Learning with Bayesian Mixed Effects and a Pretrained Language ModelCode0
Aligning Language Models with Preferences through f-divergence MinimizationCode1
Counting Carbon: A Survey of Factors Influencing the Emissions of Machine LearningCode0
Defect Transfer GAN: Diverse Defect Synthesis for Data Augmentation0
On time-consistent equilibrium stopping under aggregation of diverse discount rates0
NL2CMD: An Updated Workflow for Natural Language to Bash Commands TranslationCode1
Conversational AI-Powered Design: ChatGPT as Designer, User, and Product0
Generative Oversampling for Imbalanced Data via Majority-Guided VAE0
The Stable Entropy Hypothesis and Entropy-Aware Decoding: An Analysis and Algorithm for Robust Natural Language Generation0
A Friendly Face: Do Text-to-Image Systems Rely on Stereotypes when the Input is Under-Specified?0
Diminished Diversity-of-Thought in a Standard Large Language Model0
Large Scale Multi-Lingual Multi-Modal Summarization DatasetCode0
Evaluation of Word Embeddings for the Social Sciences0
Why Can't Discourse Parsing Generalize? A Thorough Investigation of the Impact of Data DiversityCode0
Sparse Mutation Decompositions: Fine Tuning Deep Neural Networks with Subspace Evolution0
Interpretable Diversity Analysis: Visualizing Feature Representations In Low-Cost Ensembles0
Autoselection of the Ensemble of Convolutional Neural Networks with Second-Order Cone ProgrammingCode0
MaskSketch: Unpaired Structure-guided Masked Image GenerationCode7
Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial ExamplesCode1
A Song of Ice and Fire: Analyzing Textual Autotelic Agents in ScienceWorld0
Towards Geospatial Foundation Models via Continual PretrainingCode1
Cooperative Open-ended Learning Framework for Zero-shot CoordinationCode1
Active Simultaneously Transmitting and Reflecting (STAR)-RISs: Modelling and Analysis0
Feature Likelihood Divergence: Evaluating the Generalization of Generative Models Using SamplesCode1
ERNIE-Music: Text-to-Waveform Music Generation with Diffusion Models0
Show:102550
← PrevPage 174 of 363Next →

No leaderboard results yet.