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 25612570 of 9051 papers

TitleStatusHype
Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through OptionsCode0
Learning Diverse Options via InfoMax Termination CriticCode0
Flow Diverse and Efficient: Learning Momentum Flow Matching via Stochastic Velocity Field SamplingCode0
dhSegment: A generic deep-learning approach for document segmentationCode0
Flow-Grounded Spatial-Temporal Video Prediction from Still ImagesCode0
DGSAN: Discrete Generative Self-Adversarial NetworkCode0
Benchmarking Linguistic Diversity of Large Language ModelsCode0
Benchmarking Large Language Model Uncertainty for Prompt OptimizationCode0
FS-NCSR: Increasing Diversity of the Super-Resolution Space via Frequency Separation and Noise-Conditioned Normalizing FlowCode0
Adder Attention for Vision TransformerCode0
Show:102550
← PrevPage 257 of 906Next →

No leaderboard results yet.