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 1326–1350 of 9051 papers

TitleStatusHype
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 54 of 363Next →

No leaderboard results yet.