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 4151–4175 of 9051 papers

TitleStatusHype
Rethinking Robustness of Model AttributionsCode0
Unraveling Batch Normalization for Realistic Test-Time AdaptationCode0
Multiscale differential geometry learning of networks with applications to single-cell RNA sequencing dataCode0
UINav: A Practical Approach to Train On-Device Automation Agents—0
Bayesian Estimate of Mean Proper Scores for Diversity-Enhanced Active Learning—0
Text2Immersion: Generative Immersive Scene with 3D Gaussians—0
CMOSE: Comprehensive Multi-Modality Online Student Engagement Dataset with High-Quality Labels—0
ArchiGuesser -- AI Art Architecture Educational GameCode0
Planning and Rendering: Towards Product Poster Generation with Diffusion Models—0
DSS: A Diverse Sample Selection Method to Preserve Knowledge in Class-Incremental Learning—0
Adaptive parameter sharing for multi-agent reinforcement learning—0
Generalized Deepfakes Detection with Reconstructed-Blended Images and Multi-scale Feature Reconstruction Network—0
PhasePerturbation: Speech Data Augmentation via Phase Perturbation for Automatic Speech Recognition—0
GMTalker: Gaussian Mixture-based Audio-Driven Emotional Talking Video Portraits—0
DiffuVST: Narrating Fictional Scenes with Global-History-Guided Denoising Models—0
Deep Internal Learning: Deep Learning from a Single Input—0
NutritionVerse-Synth: An Open Access Synthetically Generated 2D Food Scene Dataset for Dietary Intake Estimation—0
SkyScenes: A Synthetic Dataset for Aerial Scene Understanding—0
PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization—0
Promoting Counterfactual Robustness through DiversityCode0
AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homes—0
CAD: Photorealistic 3D Generation via Adversarial Distillation—0
Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models—0
A Vision for Operationalising Diversity and Inclusion in AI—0
Singular Value Penalization and Semantic Data Augmentation for Fully Test-Time Adaptation—0
Show:102550
← PrevPage 167 of 363Next →

No leaderboard results yet.