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 701750 of 9051 papers

TitleStatusHype
CityPersons: A Diverse Dataset for Pedestrian DetectionCode1
Dual-stage Hyperspectral Image Classification Model with Spectral SupertokenCode1
Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity RecognitionCode1
An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language ModelsCode1
Cold-Start Data Selection for Few-shot Language Model Fine-tuning: A Prompt-Based Uncertainty Propagation ApproachCode1
CLoG: Benchmarking Continual Learning of Image Generation ModelsCode1
CloudEval-YAML: A Practical Benchmark for Cloud Configuration GenerationCode1
Clotho: An Audio Captioning DatasetCode1
Few-Shot Medical Image Segmentation via a Region-enhanced Prototypical TransformerCode1
Few-Shot Object Detection via Synthetic Features with Optimal TransportCode1
DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of EnsemblesCode1
CMoralEval: A Moral Evaluation Benchmark for Chinese Large Language ModelsCode1
FHDe²Net: Full High Definition Demoireing NetworkCode1
COAST: COntrollable Arbitrary-Sampling NeTwork for Compressive SensingCode1
CodeInstruct: Empowering Language Models to Edit CodeCode1
CoFE-RAG: A Comprehensive Full-chain Evaluation Framework for Retrieval-Augmented Generation with Enhanced Data DiversityCode1
An Empirical Study On Contrastive Search And Contrastive Decoding For Open-ended Text GenerationCode1
CoDEPS: Online Continual Learning for Depth Estimation and Panoptic SegmentationCode1
An Empirical Study of Vehicle Re-Identification on the AI City ChallengeCode1
COM Kitchens: An Unedited Overhead-view Video Dataset as a Vision-Language BenchmarkCode1
DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual LearningCode1
New Protocols and Negative Results for Textual Entailment Data CollectionCode1
DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking TasksCode1
Florence-2: Advancing a Unified Representation for a Variety of Vision TasksCode1
DSDL: Data Set Description Language for Bridging Modalities and Tasks in AI DataCode1
Color Space Learning for Cross-Color Person Re-IdentificationCode1
Co-Mixup: Saliency Guided Joint Mixup with Supermodular DiversityCode1
COMETA: A Corpus for Medical Entity Linking in the Social MediaCode1
CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph DiffusionCode1
Complex Evolutional Pattern Learning for Temporal Knowledge Graph ReasoningCode1
Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human ProgrammersCode1
Forecasting Future World Events with Neural NetworksCode1
DRIT++: Diverse Image-to-Image Translation via Disentangled RepresentationsCode1
Any-Play: An Intrinsic Augmentation for Zero-Shot CoordinationCode1
An Empirical Investigation of Pre-Trained Transformer Language Models for Open-Domain Dialogue GenerationCode1
DriveDiTFit: Fine-tuning Diffusion Transformers for Autonomous DrivingCode1
Dual Feature Augmentation Network for Generalized Zero-shot LearningCode1
Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code ContributionsCode1
Compositional Feature Augmentation for Unbiased Scene Graph GenerationCode1
Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence LearningCode1
BenchTemp: A General Benchmark for Evaluating Temporal Graph Neural NetworksCode1
BenthicNet: A global compilation of seafloor images for deep learning applicationsCode1
Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual ConceptsCode1
Ape210K: A Large-Scale and Template-Rich Dataset of Math Word ProblemsCode1
Improving Semi-supervised Federated Learning by Reducing the Gradient Diversity of ModelsCode1
Don't Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement LearningCode1
A Picture is Worth a Thousand Words: A Unified System for Diverse Captions and Rich Images GenerationCode1
Unconstrained Face-Mask & Face-Hand Datasets: Building a Computer Vision System to Help Prevent the Transmission of COVID-19Code1
DRA-GRPO: Exploring Diversity-Aware Reward Adjustment for R1-Zero-Like Training of Large Language ModelsCode1
Domain-specific ChatBots for Science using EmbeddingsCode1
Show:102550
← PrevPage 15 of 182Next →

No leaderboard results yet.