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 2901–2925 of 9051 papers

TitleStatusHype
Quantifying User Coherence: A Unified Framework for Cross-Domain Recommendation Analysis—0
Correlation and Navigation in the Vocabulary Key Representation Space of Language ModelsCode0
Stochastic Sampling from Deterministic Flow Models—0
Breaking the mold: The challenge of large scale MARL specialization—0
Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks—0
Diffusion Meets Options: Hierarchical Generative Skill Composition for Temporally-Extended Tasks—0
PersonaMath: Enhancing Math Reasoning through Persona-Driven Data Augmentation—0
CrowdCounter: A benchmark type-specific multi-target counterspeech datasetCode0
Generate then Refine: Data Augmentation for Zero-shot Intent DetectionCode0
Leveraging Large Language Models to Enhance Personalized Recommendations in E-commerce—0
Meta-TTT: A Meta-learning Minimax Framework For Test-Time Training—0
Unleashing the Power of Large Language Models in Zero-shot Relation Extraction via Self-Prompting—0
Expected Diverse Utility (EDU): Diverse Bayesian Optimization of Expensive Computer Simulators—0
Stars, Stripes, and Silicon: Unravelling the ChatGPT's All-American, Monochrome, Cis-centric Bias—0
Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging—0
Enhancing Solution Efficiency in Reinforcement Learning: Leveraging Sub-GFlowNet and Entropy Integration—0
Improved Generation of Synthetic Imaging Data Using Feature-Aligned DiffusionCode0
COLLAGE: Collaborative Human-Agent Interaction Generation using Hierarchical Latent Diffusion and Language Models—0
Teuken-7B-Base & Teuken-7B-Instruct: Towards European LLMs—0
Exploring Social Media Image Categorization Using Large Models with Different Adaptation Methods: A Case Study on Cultural Nature's Contributions to People—0
Erase, then Redraw: A Novel Data Augmentation Approach for Free Space Detection Using Diffusion Model—0
DCAST: Diverse Class-Aware Self-Training Mitigates Selection Bias for Fairer LearningCode0
Temporal Source Recovery for Time-Series Source-Free Unsupervised Domain AdaptationCode0
When Molecular GAN Meets Byte-Pair Encoding—0
Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding—0
Show:102550
← PrevPage 117 of 363Next →

No leaderboard results yet.