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

Showing 13511360 of 9051 papers

TitleStatusHype
Building a Conversational Agent Overnight with Dialogue Self-PlayCode1
Annotation-Efficient Preference Optimization for Language Model AlignmentCode1
Neural Latents Benchmark '21: Evaluating latent variable models of neural population activityCode1
Neural Multi-Objective Combinatorial Optimization with Diversity EnhancementCode1
Neural Video Compression with Diverse ContextsCode1
BuildingsBench: A Large-Scale Dataset of 900K Buildings and Benchmark for Short-Term Load ForecastingCode1
Griffin: Towards a Graph-Centric Relational Database Foundation ModelCode1
Diverse Policy Optimization for Structured Action SpaceCode1
Graph Meta Network for Multi-Behavior RecommendationCode1
GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned ExpertsCode1
Show:102550
← PrevPage 136 of 906Next →

No leaderboard results yet.