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 751800 of 9051 papers

TitleStatusHype
Curiosity-Driven Reinforcement Learning from Human FeedbackCode1
DART: Articulated Hand Model with Diverse Accessories and Rich TexturesCode1
Explicit Syntactic Guidance for Neural Text GenerationCode1
Exploiting Abstract Meaning Representation for Open-Domain Question AnsweringCode1
DEFN: Dual-Encoder Fourier Group Harmonics Network for Three-Dimensional Indistinct-Boundary Object SegmentationCode1
Exploring Empty Spaces: Human-in-the-Loop Data AugmentationCode1
Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code ContributionsCode1
Exploring Semantic Consistency and Style Diversity for Domain Generalized Semantic SegmentationCode1
Cooperative Open-ended Learning Framework for Zero-shot CoordinationCode1
Extraction of instantaneous frequencies and amplitudes in nonstationary time-series dataCode1
Coralai: Intrinsic Evolution of Embodied Neural Cellular Automata EcosystemsCode1
FacialGAN: Style Transfer and Attribute Manipulation on Synthetic FacesCode1
Approximating Gradients for Differentiable Quality Diversity in Reinforcement LearningCode1
FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMsCode1
ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet AccuracyCode1
FALL-E: A Foley Sound Synthesis Model and StrategiesCode1
Controlling Behavioral Diversity in Multi-Agent Reinforcement LearningCode1
ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based PolishingCode1
Few-shot Image Generation via Cross-domain CorrespondenceCode1
Few-Shot Medical Image Segmentation via a Region-enhanced Prototypical TransformerCode1
Synth-Empathy: Towards High-Quality Synthetic Empathy DataCode1
Few-Shot Video Object DetectionCode1
CoT-ICL Lab: A Petri Dish for Studying Chain-of-Thought Learning from In-Context DemonstrationsCode1
Fibottention: Inceptive Visual Representation Learning with Diverse Attention Across HeadsCode1
Controllable Open-ended Question Generation with A New Question Type OntologyCode1
Fine-Grained VR Sketching: Dataset and InsightsCode1
ARGS: Alignment as Reward-Guided SearchCode1
FLAIR: a Country-Scale Land Cover Semantic Segmentation Dataset From Multi-Source Optical ImageryCode1
Controllable Text Generation via Probability Density Estimation in the Latent SpaceCode1
Controllable Group Choreography using Contrastive DiffusionCode1
AffordPose: A Large-scale Dataset of Hand-Object Interactions with Affordance-driven Hand PoseCode1
ARBERT & MARBERT: Deep Bidirectional Transformers for ArabicCode1
Forecasting Future World Events with Neural NetworksCode1
Fork or Fail: Cycle-Consistent Training with Many-to-One MappingsCode1
Argumentative Large Language Models for Explainable and Contestable Claim VerificationCode1
Controllable Multi-Interest Framework for RecommendationCode1
Controllable Video Captioning with an Exemplar SentenceCode1
FreEformer: Frequency Enhanced Transformer for Multivariate Time Series ForecastingCode1
Cousins Of The Vendi Score: A Family Of Similarity-Based Diversity Metrics For Science And Machine LearningCode1
Contrastive Quantization with Code Memory for Unsupervised Image RetrievalCode1
Contrastive Model Inversion for Data-Free Knowledge DistillationCode1
FS6D: Few-Shot 6D Pose Estimation of Novel ObjectsCode1
Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text GenerationCode1
Contrastive Syn-to-Real GeneralizationCode1
Contrastive Identity-Aware Learning for Multi-Agent Value DecompositionCode1
AcroFOD: An Adaptive Method for Cross-domain Few-shot Object DetectionCode1
G-DIG: Towards Gradient-based Diverse and High-quality Instruction Data Selection for Machine TranslationCode1
GenAug: Data Augmentation for Finetuning Text GeneratorsCode1
Addressing the Elephant in the Room: Robust Animal Re-Identification with Unsupervised Part-Based Feature AlignmentCode1
Contrastive Losses Are Natural Criteria for Unsupervised Video SummarizationCode1
Show:102550
← PrevPage 16 of 182Next →

No leaderboard results yet.