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 51–100 of 9051 papers

TitleStatusHype
Visible-Thermal Tiny Object Detection: A Benchmark Dataset and BaselinesCode3
Taiwan LLM: Bridging the Linguistic Divide with a Culturally Aligned Language ModelCode3
UniMLVG: Unified Framework for Multi-view Long Video Generation with Comprehensive Control Capabilities for Autonomous DrivingCode3
UniMERNet: A Universal Network for Real-World Mathematical Expression RecognitionCode3
UniTraj: A Unified Framework for Scalable Vehicle Trajectory PredictionCode3
Taming Diffusion Probabilistic Models for Character ControlCode3
SVIT: Scaling up Visual Instruction TuningCode3
ThemeStation: Generating Theme-Aware 3D Assets from Few ExemplarsCode3
Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking PortraitCode3
Swin3D++: Effective Multi-Source Pretraining for 3D Indoor Scene UnderstandingCode3
Self-QA: Unsupervised Knowledge Guided Language Model AlignmentCode3
SA-Med2D-20M Dataset: Segment Anything in 2D Medical Imaging with 20 Million masksCode3
Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone GenerationCode3
Results of the Big ANN: NeurIPS'23 competitionCode3
DexGrasp Anything: Towards Universal Robotic Dexterous Grasping with Physics AwarenessCode3
RT-1: Robotics Transformer for Real-World Control at ScaleCode3
Sequential Modeling Enables Scalable Learning for Large Vision ModelsCode3
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task SynthesisCode3
CRITERIA: a New Benchmarking Paradigm for Evaluating Trajectory Prediction Models for Autonomous DrivingCode3
Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language ModelsCode3
MNN: A Universal and Efficient Inference EngineCode3
Generating Long Sequences with Sparse TransformersCode3
Objaverse-XL: A Universe of 10M+ 3D ObjectsCode3
Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human SupervisionCode3
INTERS: Unlocking the Power of Large Language Models in Search with Instruction TuningCode3
Improving Text Embeddings with Large Language ModelsCode3
Zero-Shot Surgical Tool Segmentation in Monocular Video Using Segment Anything Model 2Code3
Hierarchical Text-Conditional Image Generation with CLIP LatentsCode3
Improved motif-scaffolding with SE(3) flow matchingCode3
Improving Model Evaluation using SMART Filtering of Benchmark DatasetsCode3
LongAlign: A Recipe for Long Context Alignment of Large Language ModelsCode3
MiniViT: Compressing Vision Transformers with Weight MultiplexingCode3
FRACTAL: An Ultra-Large-Scale Aerial Lidar Dataset for 3D Semantic Segmentation of Diverse LandscapesCode3
GenWarp: Single Image to Novel Views with Semantic-Preserving Generative WarpingCode3
Anything-3D: Towards Single-view Anything Reconstruction in the WildCode3
SkillMimic: Learning Basketball Interaction Skills from DemonstrationsCode3
EgoMimic: Scaling Imitation Learning via Egocentric VideoCode2
Efficient Quality Diversity Optimization of 3D Buildings through 2D Pre-optimizationCode2
Effective Data Augmentation With Diffusion ModelsCode2
AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-MakingCode2
EcomGPT: Instruction-tuning Large Language Models with Chain-of-Task Tasks for E-commerceCode2
Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty LearningCode2
DualAnoDiff: Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image GenerationCode2
EasyPortrait -- Face Parsing and Portrait Segmentation DatasetCode2
EDGE: Editable Dance Generation From MusicCode2
Diverse Preference OptimizationCode2
DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative DataCode2
DivPrune: Diversity-based Visual Token Pruning for Large Multimodal ModelsCode2
Diffusion Probabilistic Models beat GANs on Medical ImagesCode2
DiffusionPen: Towards Controlling the Style of Handwritten Text GenerationCode2
Show:102550
← PrevPage 2 of 182Next →

No leaderboard results yet.