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 901–925 of 9051 papers

TitleStatusHype
StyleGene: Crossover and Mutation of Region-Level Facial Genes for Kinship Face SynthesisCode1
Progressive Spatio-Temporal Prototype Matching for Text-Video RetrievalCode1
Boosting Single Image Super-Resolution via Partial Channel ShiftingCode1
Optimizing Readability Using Genetic AlgorithmsCode1
Zero-Shot Point Cloud Segmentation by Semantic-Visual Aware SynthesisCode1
DISCO: Distilling Counterfactuals with Large Language ModelsCode1
Data Curation Alone Can Stabilize In-context LearningCode1
DAG: Depth-Aware Guidance with Denoising Diffusion Probabilistic ModelsCode1
Controllable Text Generation via Probability Density Estimation in the Latent SpaceCode1
APOLLO: An Optimized Training Approach for Long-form Numerical ReasoningCode1
DialogCC: An Automated Pipeline for Creating High-Quality Multi-Modal Dialogue DatasetCode1
Self-Supervised Correspondence Estimation via Multiview RegistrationCode1
On the effectiveness of partial variance reduction in federated learning with heterogeneous dataCode1
UDE: A Unified Driving Engine for Human Motion GenerationCode1
VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph CaptioningCode1
Rethinking Data Augmentation for Single-source Domain Generalization in Medical Image SegmentationCode1
BeLFusion: Latent Diffusion for Behavior-Driven Human Motion PredictionCode1
Generative Modeling in Structural-Hankel Domain for Color Image InpaintingCode1
Contrastive Identity-Aware Learning for Multi-Agent Value DecompositionCode1
SciRepEval: A Multi-Format Benchmark for Scientific Document RepresentationsCode1
The Euclidean Space is Evil: Hyperbolic Attribute Editing for Few-shot Image GenerationCode1
Plug and Play Active Learning for Object DetectionCode1
SinFusion: Training Diffusion Models on a Single Image or VideoCode1
Automating Rigid Origami DesignCode1
An Empirical Study On Contrastive Search And Contrastive Decoding For Open-ended Text GenerationCode1
Show:102550
← PrevPage 37 of 363Next →

No leaderboard results yet.