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 51–75 of 9051 papers

TitleStatusHype
Improving Model Evaluation using SMART Filtering of Benchmark DatasetsCode3
Results of the Big ANN: NeurIPS'23 competitionCode3
Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language ModelsCode3
SkillMimic: Learning Basketball Interaction Skills from DemonstrationsCode3
Zero-Shot Surgical Tool Segmentation in Monocular Video Using Segment Anything Model 2Code3
AlphaForge: A Framework to Mine and Dynamically Combine Formulaic Alpha FactorsCode3
Visible-Thermal Tiny Object Detection: A Benchmark Dataset and BaselinesCode3
Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone GenerationCode3
GenWarp: Single Image to Novel Views with Semantic-Preserving Generative WarpingCode3
FRACTAL: An Ultra-Large-Scale Aerial Lidar Dataset for 3D Semantic Segmentation of Diverse LandscapesCode3
Taming Diffusion Probabilistic Models for Character ControlCode3
UniMERNet: A Universal Network for Real-World Mathematical Expression RecognitionCode3
Addressing the Abstraction and Reasoning Corpus via Procedural Example GenerationCode3
UniTraj: A Unified Framework for Scalable Vehicle Trajectory PredictionCode3
ThemeStation: Generating Theme-Aware 3D Assets from Few ExemplarsCode3
Swin3D++: Effective Multi-Source Pretraining for 3D Indoor Scene UnderstandingCode3
LongAlign: A Recipe for Long Context Alignment of Large Language ModelsCode3
INTERS: Unlocking the Power of Large Language Models in Search with Instruction TuningCode3
Improved motif-scaffolding with SE(3) flow matchingCode3
EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture ModelingCode3
Improving Text Embeddings with Large Language ModelsCode3
Sequential Modeling Enables Scalable Learning for Large Vision ModelsCode3
Taiwan LLM: Bridging the Linguistic Divide with a Culturally Aligned Language ModelCode3
SA-Med2D-20M Dataset: Segment Anything in 2D Medical Imaging with 20 Million masksCode3
CRITERIA: a New Benchmarking Paradigm for Evaluating Trajectory Prediction Models for Autonomous DrivingCode3
Show:102550
← PrevPage 3 of 363Next →

No leaderboard results yet.