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 491500 of 9051 papers

TitleStatusHype
Optimal Kernel Orchestration for Tensor Programs with KorchCode1
MMRel: A Relation Understanding Benchmark in the MLLM EraCode1
REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic EntropyCode1
Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-TrainingCode1
MoPS: Modular Story Premise Synthesis for Open-Ended Automatic Story GenerationCode1
Bootstrapping Referring Multi-Object TrackingCode1
Diversified Batch Selection for Training AccelerationCode1
The ULS23 Challenge: a Baseline Model and Benchmark Dataset for 3D Universal Lesion Segmentation in Computed TomographyCode1
CLoG: Benchmarking Continual Learning of Image Generation ModelsCode1
Improving Geo-diversity of Generated Images with Contextualized Vendi Score GuidanceCode1
Show:102550
← PrevPage 50 of 906Next →

No leaderboard results yet.