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 576–600 of 9051 papers

TitleStatusHype
TartanAviation: Image, Speech, and ADS-B Trajectory Datasets for Terminal Airspace OperationsCode1
Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual FidelityCode1
Language and Speech Technology for Central Kurdish VarietiesCode1
Standardizing the Measurement of Text Diversity: A Tool and a Comparative Analysis of ScoresCode1
Teaching Large Language Models an Unseen Language on the FlyCode1
Improving Open-Ended Text Generation via Adaptive DecodingCode1
MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-TuningCode1
Taming the Tail in Class-Conditional GANs: Knowledge Sharing via Unconditional Training at Lower ResolutionsCode1
NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated DataCode1
Mirror: A Multiple-perspective Self-Reflection Method for Knowledge-rich ReasoningCode1
Visual Hallucinations of Multi-modal Large Language ModelsCode1
MerRec: A Large-scale Multipurpose Mercari Dataset for Consumer-to-Consumer Recommendation SystemsCode1
LongWanjuan: Towards Systematic Measurement for Long Text QualityCode1
Class-Aware Mask-Guided Feature Refinement for Scene Text RecognitionCode1
DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual LearningCode1
A Multimodal In-Context Tuning Approach for E-Commerce Product Description GenerationCode1
wmh_seg: Transformer based U-Net for Robust and Automatic White Matter Hyperintensity Segmentation across 1.5T, 3T and 7TCode1
MGF: Mixed Gaussian Flow for Diverse Trajectory PredictionCode1
PreAct: Prediction Enhances Agent's Planning AbilityCode1
Semi-supervised Medical Image Segmentation Method Based on Cross-pseudo Labeling Leveraging Strong and Weak Data Augmentation StrategiesCode1
ReViT: Enhancing Vision Transformers Feature Diversity with Attention Residual ConnectionsCode1
Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language ModelsCode1
OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language ModelsCode1
QGFN: Controllable Greediness with Action ValuesCode1
INSIDE: LLMs' Internal States Retain the Power of Hallucination DetectionCode1
Show:102550
← PrevPage 24 of 363Next →

No leaderboard results yet.