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 1301–1350 of 9051 papers

TitleStatusHype
Celebrating Diversity in Shared Multi-Agent Reinforcement LearningCode1
AMPED: Adaptive Multi-objective Projection for balancing Exploration and skill DiversificationCode1
HandBooster: Boosting 3D Hand-Mesh Reconstruction by Conditional Synthesis and Sampling of Hand-Object InteractionsCode1
Amortizing intractable inference in large language modelsCode1
AutoMix: Automatically Mixing Language ModelsCode1
Automating Rigid Origami DesignCode1
Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial TrajectoryCode1
Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable DiffusionCode1
CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich AnnotationsCode1
GLAMOUR: Graph Learning over Macromolecule RepresentationsCode1
HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3DCode1
HomoFormer: Homogenized Transformer for Image Shadow RemovalCode1
Group-wise Contrastive Learning for Neural Dialogue GenerationCode1
DiffuSum: Generation Enhanced Extractive Summarization with DiffusionCode1
Group-wise Inhibition based Feature Regularization for Robust ClassificationCode1
Griffin: Towards a Graph-Centric Relational Database Foundation ModelCode1
An Informative Tracking BenchmarkCode1
MMPD: Multi-Domain Mobile Video Physiology DatasetCode1
DISCO: Distilling Counterfactuals with Large Language ModelsCode1
Modality Plug-and-Play: Elastic Modality Adaptation in Multimodal LLMs for Embodied AICode1
DirectMultiStep: Direct Route Generation for Multi-Step RetrosynthesisCode1
Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word ExclusionCode1
Grounded Affordance from Exocentric ViewCode1
GS-Blur: A 3D Scene-Based Dataset for Realistic Image DeblurringCode1
MOFDiff: Coarse-grained Diffusion for Metal-Organic Framework DesignCode1
MolGrapher: Graph-based Visual Recognition of Chemical StructuresCode1
DisCup: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text GenerationCode1
Data Curation Alone Can Stabilize In-context LearningCode1
Mosaic-IT: Free Compositional Data Augmentation Improves Instruction TuningCode1
MotionAug: Augmentation with Physical Correction for Human Motion PredictionCode1
Multi-head Attention-based Deep Multiple Instance LearningCode1
Learning to Discover Multi-Class Attentional Regions for Multi-Label Image RecognitionCode1
Distributed speech separation in spatially unconstrained microphone arraysCode1
Greedy Bayesian Posterior Approximation with Deep EnsemblesCode1
Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problemCode1
GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned ExpertsCode1
Multimodal Multi-objective Optimization: Comparative Study of the State-of-the-ArtCode1
Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language ModelsCode1
DivClust: Controlling Diversity in Deep ClusteringCode1
DivAug: Plug-in Automated Data Augmentation with Explicit Diversity MaximizationCode1
Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealingCode1
DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial NetworkCode1
Diverse and Admissible Trajectory Prediction through Multimodal Context UnderstandingCode1
Diverse and Admissible Trajectory Forecasting through Multimodal Context UnderstandingCode1
Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior InferenceCode1
Diverse and Specific Clarification Question Generation with KeywordsCode1
Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline GenerationCode1
Diverse Cotraining Makes Strong Semi-Supervised SegmentorCode1
Diverse Generative Perturbations on Attention Space for Transferable Adversarial AttacksCode1
Graph Neural PDE Solvers with Conservation and Similarity-EquivarianceCode1
Show:102550
← PrevPage 27 of 182Next →

No leaderboard results yet.