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 2651–2675 of 9051 papers

TitleStatusHype
Mix from Failure: Confusion-Pairing Mixup for Long-Tailed Recognition—0
Study on Inter and Intra Speaker Variability in Speaker Recognition—0
Top-nσ: Not All Logits Are You Need—0
Gini Coefficient as a Unified Metric for Evaluating Many-versus-Many Similarity in Vector Spaces—0
Multi-Objective Algorithms for Learning Open-Ended Robotic Problems—0
Exploring Variational Autoencoders for Medical Image Generation: A Comprehensive Study—0
Imitation from Diverse Behaviors: Wasserstein Quality Diversity Imitation Learning with Single-Step Archive Exploration—0
A comprehensive representation of selection at loci with multiple alleles that allows complex forms of genotypic fitnessCode0
PLM-Based Discrete Diffusion Language Models with Entropy-Adaptive Gibbs Sampling—0
Deep Active Learning in the Open World—0
Diversity and Inclusion in AI for Recruitment: Lessons from Industry Workshop—0
Quasi-random Multi-Sample Inference for Large Language Models—0
ViTOC: Vision Transformer and Object-aware Captioner—0
MOANA: Multi-Objective Ant Nesting Algorithm for Optimization Problems—0
Bridging the Gap between Learning and Inference for Diffusion-Based Molecule GenerationCode0
STARS: Sensor-agnostic Transformer Architecture for Remote Sensing—0
A Bayesian Mixture Model of Temporal Point Processes with Determinantal Point Process Prior—0
Discretized Gaussian Representation for Tomographic Reconstruction—0
Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting DiversityCode0
PASSION for Dermatology: Bridging the Diversity Gap with Pigmented Skin Images from Sub-Saharan Africa—0
One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversityCode0
Efficient Symmetry-Aware Materials Generation via Hierarchical Generative Flow Networks—0
Hiring as Exploration—0
No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 LanguagesCode0
Diversity Helps Jailbreak Large Language Models—0
Show:102550
← PrevPage 107 of 363Next →

No leaderboard results yet.