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 701–750 of 9051 papers

TitleStatusHype
Understanding the Effects of RLHF on LLM Generalisation and DiversityCode1
CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental SegmentationCode1
SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory PredictionCode1
IPMix: Label-Preserving Data Augmentation Method for Training Robust ClassifiersCode1
On the Embedding Collapse when Scaling up Recommendation ModelsCode1
Domain Randomization for Sim2real Transfer of Automatically Generated Grasping DatasetsCode1
Toward a Plug-and-Play Vision-Based Grasping Module for RoboticsCode1
Amortizing intractable inference in large language modelsCode1
Can pre-trained models assist in dataset distillation?Code1
Multimodal Question Answering for Unified Information ExtractionCode1
On the Power of Adaptive Weighted Aggregation in Heterogeneous Federated Learning and BeyondCode1
Sieve: Multimodal Dataset Pruning Using Image Captioning ModelsCode1
Strength in Diversity: Multi-Branch Representation Learning for Vehicle Re-IdentificationCode1
KERMIT: Knowledge Graph Completion of Enhanced Relation Modeling with Inverse TransformationCode1
Structure Invariant Transformation for better Adversarial TransferabilityCode1
Dual Feature Augmentation Network for Generalized Zero-shot LearningCode1
Multi-Static ISAC in Cell-Free Massive MIMO: Precoder Design and Privacy AssessmentCode1
Euler-Lagrange Analysis of Generative Adversarial NetworksCode1
Design of Chain-of-Thought in Math Problem SolvingCode1
NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource LanguagesCode1
ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency DistillationCode1
AffordPose: A Large-scale Dataset of Hand-Object Interactions with Affordance-driven Hand PoseCode1
Nucleus-aware Self-supervised Pretraining Using Unpaired Image-to-image Translation for Histopathology ImagesCode1
Masked Generative Modeling with Enhanced Sampling SchemeCode1
Large-Vocabulary 3D Diffusion Model with TransformerCode1
UnifiedGesture: A Unified Gesture Synthesis Model for Multiple SkeletonsCode1
Few-Shot Medical Image Segmentation via a Region-enhanced Prototypical TransformerCode1
Score-PA: Score-based 3D Part AssemblyCode1
AnthroNet: Conditional Generation of Humans via AnthropometricsCode1
Everyone Deserves A Reward: Learning Customized Human PreferencesCode1
SyntheWorld: A Large-Scale Synthetic Dataset for Land Cover Mapping and Building Change DetectionCode1
Probabilistic Precision and Recall Towards Reliable Evaluation of Generative ModelsCode1
dacl10k: Benchmark for Semantic Bridge Damage SegmentationCode1
Fast Diffusion EM: a diffusion model for blind inverse problems with application to deconvolutionCode1
BenchTemp: A General Benchmark for Evaluating Temporal Graph Neural NetworksCode1
Few-Shot Object Detection via Synthetic Features with Optimal TransportCode1
CALM : A Multi-task Benchmark for Comprehensive Assessment of Language Model BiasCode1
Dance with You: The Diversity Controllable Dancer Generation via Diffusion ModelsCode1
MolGrapher: Graph-based Visual Recognition of Chemical StructuresCode1
DALNet: A Rail Detection Network Based on Dynamic Anchor LineCode1
PlatoLM: Teaching LLMs in Multi-Round Dialogue via a User SimulatorCode1
Few-Shot Physically-Aware Articulated Mesh Generation via Hierarchical DeformationCode1
TransFace: Calibrating Transformer Training for Face Recognition from a Data-Centric PerspectiveCode1
MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed RecognitionCode1
Diverse Cotraining Makes Strong Semi-Supervised SegmentorCode1
LaRS: A Diverse Panoptic Maritime Obstacle Detection Dataset and BenchmarkCode1
Language-guided Human Motion Synthesis with Atomic ActionsCode1
OpenGCD: Assisting Open World Recognition with Generalized Category DiscoveryCode1
Compositional Feature Augmentation for Unbiased Scene Graph GenerationCode1
DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic DiversityCode1
Show:102550
← PrevPage 15 of 182Next →

No leaderboard results yet.