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 201–250 of 9051 papers

TitleStatusHype
EasyPortrait -- Face Parsing and Portrait Segmentation DatasetCode2
Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty LearningCode2
EcomGPT: Instruction-tuning Large Language Models with Chain-of-Task Tasks for E-commerceCode2
DreamMix: Decoupling Object Attributes for Enhanced Editability in Customized Image InpaintingCode2
DualAnoDiff: Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image GenerationCode2
Mammo-CLIP: A Vision Language Foundation Model to Enhance Data Efficiency and Robustness in MammographyCode2
EDGE: Editable Dance Generation From MusicCode2
Ambiguous Medical Image Segmentation using Diffusion ModelsCode2
BigBIO: A Framework for Data-Centric Biomedical Natural Language ProcessingCode2
MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based AgentsCode2
DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative DataCode2
Diverse Preference OptimizationCode2
Diffusion Probabilistic Models beat GANs on Medical ImagesCode2
MiniPLM: Knowledge Distillation for Pre-Training Language ModelsCode2
Modifying Large Language Model Post-Training for Diverse Creative WritingCode2
Mono-ViFI: A Unified Learning Framework for Self-supervised Single- and Multi-frame Monocular Depth EstimationCode2
Boosting Latent Diffusion with Flow MatchingCode2
Multi-Space Alignments Towards Universal LiDAR SegmentationCode2
DivPrune: Diversity-based Visual Token Pruning for Large Multimodal ModelsCode2
Diffusion Models Beat GANs on Image SynthesisCode2
DiffusionLight: Light Probes for Free by Painting a Chrome BallCode2
Omni3D: A Large Benchmark and Model for 3D Object Detection in the WildCode2
Diffusion Models for Molecules: A Survey of Methods and TasksCode2
Palette: Image-to-Image Diffusion ModelsCode2
PerAct2: Benchmarking and Learning for Robotic Bimanual Manipulation TasksCode2
Person Image Synthesis via Denoising Diffusion ModelCode2
Test-time Alignment of Diffusion Models without Reward Over-optimizationCode2
Can Go AIs be adversarially robust?Code2
DiffusionPen: Towards Controlling the Style of Handwritten Text GenerationCode2
Pretraining a Neural Network before Knowing Its ArchitectureCode2
CDFormer: When Degradation Prediction Embraces Diffusion Model for Blind Image Super-ResolutionCode2
AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-MakingCode2
CDFormer:When Degradation Prediction Embraces Diffusion Model for Blind Image Super-ResolutionCode2
ProtComposer: Compositional Protein Structure Generation with 3D EllipsoidsCode2
DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-TrainingCode2
Diff-BGM: A Diffusion Model for Video Background Music GenerationCode2
AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based PoliciesCode2
ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot CoordinationCode2
DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AICode2
DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Iterative Diffusion-Based RefinementCode2
DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image ClassificationCode2
AD-AGENT: A Multi-agent Framework for End-to-end Anomaly DetectionCode2
CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language ModelsCode2
Dialectal Coverage And Generalization in Arabic Speech RecognitionCode2
DiffTF++: 3D-aware Diffusion Transformer for Large-Vocabulary 3D GenerationCode2
Classifier-Free Diffusion GuidanceCode2
Depth Field Networks for Generalizable Multi-view Scene RepresentationCode2
Dereflection Any Image with Diffusion Priors and Diversified DataCode2
Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality EstimationCode2
A Generalizable Anomaly Detection Method in Dynamic GraphsCode2
Show:102550
← PrevPage 5 of 182Next →

No leaderboard results yet.