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 601–650 of 9051 papers

TitleStatusHype
INSIDE: LLMs' Internal States Retain the Power of Hallucination DetectionCode1
BehAVE: Behaviour Alignment of Video Game EncodingsCode1
IMUGPT 2.0: Language-Based Cross Modality Transfer for Sensor-Based Human Activity RecognitionCode1
LLM Voting: Human Choices and AI Collective Decision MakingCode1
Revisiting Active Learning in the Era of Vision Foundation ModelsCode1
On the Affinity, Rationality, and Diversity of Hierarchical Topic ModelingCode1
ARGS: Alignment as Reward-Guided SearchCode1
Inducing High Energy-Latency of Large Vision-Language Models with Verbose ImagesCode1
Learning High-Quality and General-Purpose Phrase RepresentationsCode1
UOEP: User-Oriented Exploration Policy for Enhancing Long-Term User Experiences in Recommender SystemsCode1
Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human ProgrammersCode1
TIGER: Time-Varying Denoising Model for 3D Point Cloud Generation with Diffusion ProcessCode1
Online Task-Free Continual Generative and Discriminative Learning via Dynamic Cluster MemoryCode1
Ensemble Diversity Facilitates Adversarial TransferabilityCode1
Distribution-aware Knowledge Prototyping for Non-exemplar Lifelong Person Re-identificationCode1
HomoFormer: Homogenized Transformer for Image Shadow RemovalCode1
ODAQ: Open Dataset of Audio QualityCode1
HyKGE: A Hypothesis Knowledge Graph Enhanced Framework for Accurate and Reliable Medical LLMs ResponsesCode1
HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3DCode1
A Multi-Modal Contrastive Diffusion Model for Therapeutic Peptide GenerationCode1
Quality-Diversity Generative Sampling for Learning with Synthetic DataCode1
Cross-Covariate Gait Recognition: A BenchmarkCode1
Q-SENN: Quantized Self-Explaining Neural NetworksCode1
De novo Drug Design using Reinforcement Learning with Multiple GPT AgentsCode1
Diffusion Reward: Learning Rewards via Conditional Video DiffusionCode1
Point Cloud Part Editing: Segmentation, Generation, Assembly, and SelectionCode1
CETN: Contrast-enhanced Through Network for CTR PredictionCode1
SoloPose: One-Shot Kinematic 3D Human Pose Estimation with Video Data AugmentationCode1
How Does It Function? Characterizing Long-term Trends in Production Serverless WorkloadsCode1
Modality Plug-and-Play: Elastic Modality Adaptation in Multimodal LLMs for Embodied AICode1
PhenDiff: Revealing Subtle Phenotypes with Diffusion Models in Real ImagesCode1
Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-ExpertsCode1
Toward Robustness in Multi-label Classification: A Data Augmentation Strategy against Imbalance and NoiseCode1
Efficient Object Detection in Autonomous Driving using Spiking Neural Networks: Performance, Energy Consumption Analysis, and Insights into Open-set Object DiscoveryCode1
Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose EstimationCode1
The Journey, Not the Destination: How Data Guides Diffusion ModelsCode1
3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D DetectionCode1
GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned ExpertsCode1
Mitigating Open-Vocabulary Caption HallucinationsCode1
On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation ParadigmCode1
WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene GenerationCode1
Diversified in-domain synthesis with efficient fine-tuning for few-shot classificationCode1
Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain ShiftsCode1
Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic SegmentationCode1
Dynamic Inertial Poser (DynaIP): Part-Based Motion Dynamics Learning for Enhanced Human Pose Estimation with Sparse Inertial SensorsCode1
Toward Improving Robustness of Object Detectors Against Domain ShiftCode1
W-HMR: Monocular Human Mesh Recovery in World Space with Weak-Supervised CalibrationCode1
Continual Learning for Image Segmentation with Dynamic QueryCode1
DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Diffusion ModelCode1
DEU-Net: Dual-Encoder U-Net for Automated Skin Lesion SegmentationCode1
Show:102550
← PrevPage 13 of 182Next →

No leaderboard results yet.