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 801–825 of 9051 papers

TitleStatusHype
Rethinking Masked Language Modeling for Chinese Spelling CorrectionCode1
Whitening-based Contrastive Learning of Sentence EmbeddingsCode1
Exploiting Abstract Meaning Representation for Open-Domain Question AnsweringCode1
CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image SteganographyCode1
Diversify Your Vision Datasets with Automatic Diffusion-Based AugmentationCode1
CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph DiffusionCode1
Self-aware and Cross-sample Prototypical Learning for Semi-supervised Medical Image SegmentationCode1
Optimized Custom Dataset for Efficient Detection of Underwater TrashCode1
ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score DistillationCode1
GUARD: A Safe Reinforcement Learning BenchmarkCode1
CodeInstruct: Empowering Language Models to Edit CodeCode1
ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability AssessmentCode1
MvP: Multi-view Prompting Improves Aspect Sentiment Tuple PredictionCode1
CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion DiffusionCode1
Boosting Human-Object Interaction Detection with Text-to-Image Diffusion ModelCode1
Learning Diverse Risk Preferences in Population-based Self-playCode1
Learning In-context Learning for Named Entity RecognitionCode1
MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer TasksCode1
CLIP-VG: Self-paced Curriculum Adapting of CLIP for Visual GroundingCode1
From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP ModelsCode1
DATED: Guidelines for Creating Synthetic Datasets for Engineering Design ApplicationsCode1
Harvesting Event Schemas from Large Language ModelsCode1
Device-Robust Acoustic Scene Classification via Impulse Response AugmentationCode1
HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution EstimationCode1
Multi-Robot Coordination and Layout Design for Automated WarehousingCode1
Show:102550
← PrevPage 33 of 363Next →

No leaderboard results yet.