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 751775 of 9051 papers

TitleStatusHype
Apples to Apples: A Systematic Evaluation of Topic ModelsCode1
Conditioned Text Generation with Transfer for Closed-Domain Dialogue SystemsCode1
Continual Learning for Image Segmentation with Dynamic QueryCode1
Generating Smooth Pose Sequences for Diverse Human Motion PredictionCode1
Improving Semi-supervised Federated Learning by Reducing the Gradient Diversity of ModelsCode1
Contextual Diversity for Active LearningCode1
DSDL: Data Set Description Language for Bridging Modalities and Tasks in AI DataCode1
Content-aware Tile Generation using Exterior Boundary InpaintingCode1
Continual Variational Autoencoder Learning via Online Cooperative MemorizationCode1
Continual Object Detection via Prototypical Task Correlation Guided Gating MechanismCode1
Contrastive Losses Are Natural Criteria for Unsupervised Video SummarizationCode1
Contrastive Identity-Aware Learning for Multi-Agent Value DecompositionCode1
Approximating Gradients for Differentiable Quality Diversity in Reinforcement LearningCode1
Contrastive Quantization with Code Memory for Unsupervised Image RetrievalCode1
Contrastive Syn-to-Real GeneralizationCode1
Control, Generate, Augment: A Scalable Framework for Multi-Attribute Text GenerationCode1
DriveDiTFit: Fine-tuning Diffusion Transformers for Autonomous DrivingCode1
DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual LearningCode1
DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of EnsemblesCode1
DreamDA: Generative Data Augmentation with Diffusion ModelsCode1
Synth-Empathy: Towards High-Quality Synthetic Empathy DataCode1
ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet AccuracyCode1
ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based PolishingCode1
Draw Your Art Dream: Diverse Digital Art Synthesis with Multimodal Guided DiffusionCode1
DREAM: Efficient Dataset Distillation by Representative MatchingCode1
Show:102550
← PrevPage 31 of 363Next →

No leaderboard results yet.