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 8351–8400 of 9051 papers

TitleStatusHype
Dipper: Diversity in Prompts for Producing Large Language Model Ensembles in Reasoning tasks—0
DiRaC-I: Identifying Diverse and Rare Training Classes for Zero-Shot Learning—0
DiRe Committee : Diversity and Representation Constraints in Multiwinner Elections—0
Syntactic representation learning for neural network based TTS with syntactic parse tree traversal—0
Evaluations at Work: Measuring the Capabilities of GenAI in Use—0
Condition-Transforming Variational AutoEncoder for Conversation Response Generation—0
Direct Preference Optimization-Enhanced Multi-Guided Diffusion Model for Traffic Scenario Generation—0
Disagreement amongst counterfactual explanations: How transparency can be deceptive—0
Syntax-driven Iterative Expansion Language Models for Controllable Text Generation—0
Synth4Kws: Synthesized Speech for User Defined Keyword Spotting in Low Resource Environments—0
Conditioning Diffusion Models via Attributes and Semantic Masks for Face Generation—0
Advancing Urban Renewal: An Automated Approach to Generating Historical Arcade Facades with Stable Diffusion Models—0
Conditioned Natural Language Generation using only Unconditioned Language Model: An Exploration—0
Discovering Diverse Athletic Jumping Strategies—0
Discovering Diverse Nearly Optimal Policies with Successor Features—0
Synthesize-on-Graph: Knowledgeable Synthetic Data Generation for Continue Pre-training of Large Language Models—0
Discovering Evolutionary Stepping Stones through Behavior Domination—0
Discovering Generalizable Skills via Automated Generation of Diverse Tasks—0
VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment—0
Discovering Patterns of Definitions and Methods from Scientific Documents—0
Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality—0
Discovering Quality-Diversity Algorithms via Meta-Black-Box Optimization—0
Synthesizing Diverse Network Flow Datasets with Scalable Dynamic Multigraph Generation—0
Advancing the Arabic WordNet: Elevating Content Quality—0
Discovering Unsupervised Behaviours from Full-State Trajectories—0
Discovery data topology with the closure structure. Theoretical and practical aspects—0
Discrepancy-based Evolutionary Diversity Optimization—0
Discrete Contrastive Learning for Diffusion Policies in Autonomous Driving—0
Synthesizing Reality: Leveraging the Generative AI-Powered Platform Midjourney for Construction Worker Detection—0
Discrete Structural Planning for Generating Diverse Translations—0
Discriminative Active Learning for Domain Adaptation—0
Discriminative Representation Loss (DRL): A More Efficient Approach than Gradient Re-Projection in Continual Learning—0
Conditional Text Image Generation with Diffusion Models—0
Discursive objection strategies in online comments: Developing a classification schema and validating its training—0
Discussion of Features for Acoustic Anomaly Detection under Industrial Disturbing Noise in an End-of-Line Test of Geared Motors—0
Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring—0
Disentangled Generation Network for Enlarged License Plate Recognition and A Unified Dataset—0
Disentangled Generation with Information Bottleneck for Few-Shot Learning—0
Disentangled Motif-aware Graph Learning for Phrase Grounding—0
Advancing Non-Contact Vital Sign Measurement using Synthetic Avatars—0
Disentangled Structural and Featural Representation for Task-Agnostic Graph Valuation—0
Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification—0
Disentangling Genotype and Environment Specific Latent Features for Improved Trait Prediction using a Compositional Autoencoder—0
Disentangling Racial Phenotypes: Fine-Grained Control of Race-related Facial Phenotype Characteristics—0
Dispersal-induced instability in complex ecosystems—0
Synthesizing Training Images for Boosting Human 3D Pose Estimation—0
Distance Shrinkage and Euclidean Embedding via Regularized Kernel Estimation—0
Conditional Temporal Variational AutoEncoder for Action Video Prediction—0
Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs—0
Distilling Diversity and Control in Diffusion Models—0
Show:102550
← PrevPage 168 of 182Next →

No leaderboard results yet.