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 1501–1525 of 9051 papers

TitleStatusHype
APOLLO: An Optimized Training Approach for Long-form Numerical ReasoningCode1
Parea: multi-view ensemble clustering for cancer subtype discoveryCode1
CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image SteganographyCode1
Path Shadowing Monte-CarloCode1
PClean: Bayesian Data Cleaning at Scale with Domain-Specific Probabilistic ProgrammingCode1
GLAMOUR: Graph Learning over Macromolecule RepresentationsCode1
Controlling Behavioral Diversity in Multi-Agent Reinforcement LearningCode1
Automatically Generating Numerous Context-Driven SFT Data for LLMs across Diverse GranularityCode1
Personalized Federated Learning with Moreau EnvelopesCode1
Personalized Privacy Protection Mask Against Unauthorized Facial RecognitionCode1
ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet AccuracyCode1
PhenDiff: Revealing Subtle Phenotypes with Diffusion Models in Real ImagesCode1
PhraseCut: Language-based Image Segmentation in the WildCode1
Controllable Text Generation via Probability Density Estimation in the Latent SpaceCode1
A Map of Diverse Synthetic Stable Roommates InstancesCode1
Planning In Natural Language Improves LLM Search For Code GenerationCode1
Controllable Video Captioning with an Exemplar SentenceCode1
Plot and Rework: Modeling Storylines for Visual StorytellingCode1
ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based PolishingCode1
CIAGAN: Conditional Identity Anonymization Generative Adversarial NetworksCode1
Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular ValuesCode1
CIC: Contrastive Intrinsic Control for Unsupervised Skill DiscoveryCode1
PoseTrack21: A Dataset for Person Search, Multi-Object Tracking and Multi-Person Pose TrackingCode1
PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose EstimationCode1
Automated segmentation and morphological characterization of placental histology images based on a single labeled imageCode1
Show:102550
← PrevPage 61 of 363Next →

No leaderboard results yet.