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 851–900 of 9051 papers

TitleStatusHype
Bridging the Fairness Gap: Enhancing Pre-trained Models with LLM-Generated Sentences—0
Deep Reinforcement Learning Optimized Intelligent Resource Allocation in Active RIS-Integrated TN-NTN Networks—0
DivTrackee versus DynTracker: Promoting Diversity in Anti-Facial Recognition against Dynamic FR StrategyCode0
Unispeaker: A Unified Approach for Multimodality-driven Speaker Generation—0
Repeat-bias-aware Optimization of Beyond-accuracy Metrics for Next Basket RecommendationCode0
Towards Iris Presentation Attack Detection with Foundation Models—0
Test-time Alignment of Diffusion Models without Reward Over-optimizationCode2
Semantic Exploration with Adaptive Gating for Efficient Problem Solving with Language Models—0
Supervision policies can shape long-term risk management in general-purpose AI modelsCode0
Ultrasound Image Synthesis Using Generative AI for Lung Ultrasound Detection—0
Poetry in Pixels: Prompt Tuning for Poem Image Generation via Diffusion ModelsCode0
Bridging Dialects: Translating Standard Bangla to Regional Variants Using Neural Models—0
Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction—0
Capability-Aware Shared Hypernetworks for Flexible Heterogeneous Multi-Robot CoordinationCode0
Seeing Sound: Assembling Sounds from Visuals for Audio-to-Image Generation—0
Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance—0
Consistent Flow Distillation for Text-to-3D Generation—0
Learning Compact and Robust Representations for Anomaly Detection—0
EquiBoost: An Equivariant Boosting Approach to Molecular Conformation GenerationCode0
Tuning-Free Long Video Generation via Global-Local Collaborative Diffusion—0
Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints—0
EpiCoder: Encompassing Diversity and Complexity in Code Generation—0
Continual Self-supervised Learning Considering Medical Domain Knowledge in Chest CT Images—0
Multi-Hypothesis Prediction for Portfolio Optimization: A Structured Ensemble Learning Approach to Risk Diversification—0
Deep Learning for Ophthalmology: The State-of-the-Art and Future Trends—0
Beyond Factual Accuracy: Evaluating Coverage of Diverse Factual Information in Long-form Text GenerationCode0
SALE-Based Offline Reinforcement Learning with Ensemble Q-Networks—0
Magic Mirror: ID-Preserved Video Generation in Video Diffusion TransformersCode2
A Diversity-Enhanced Knowledge Distillation Model for Practical Math Word Problem SolvingCode0
Evaluating Image Caption via Cycle-consistent Text-to-Image Generation—0
Finding A Voice: Evaluating African American Dialect Generation for Chatbot TechnologyCode0
The 2nd Place Solution from the 3D Semantic Segmentation Track in the 2024 Waymo Open Dataset Challenge—0
TARDiS : Text Augmentation for Refining Diversity and Separability—0
Universal Features Guided Zero-Shot Category-Level Object Pose Estimation—0
LOHA: Direct Graph Spectral Contrastive Learning Between Low-pass and High-pass Views—0
Comprehensive Pathological Image Segmentation via Teacher Aggregation for Tumor Microenvironment Analysis—0
MDP3: A Training-free Approach for List-wise Frame Selection in Video-LLMs—0
Swift Cross-Dataset Pruning: Enhancing Fine-Tuning Efficiency in Natural Language UnderstandingCode0
Citation Structural Diversity: A Novel and Concise Metric Combining Structure and Semantics for Literature Evaluation—0
Pixel-Wise Feature Selection for Perceptual Edge Detection without post-processing—0
Facial Attractiveness Prediction in Live Streaming: A New Benchmark and Multi-modal Method—0
The Application of Large Language Models in Recommendation Systems—0
CORD: Generalizable Cooperation via Role Diversity—0
ArtCrafter: Text-Image Aligning Style Transfer via Embedding Reframing—0
AR4D: Autoregressive 4D Generation from Monocular Videos—0
Sequencing Silicates in the IRS Debris Disk Catalog I: Methodology for Unsupervised Clustering—0
Large Language Model-Enhanced Symbolic Reasoning for Knowledge Base Completion—0
The Prompt Alchemist: Automated LLM-Tailored Prompt Optimization for Test Case Generation—0
Rethinking Token Reduction with Parameter-Efficient Fine-Tuning in ViT for Pixel-Level TasksCode0
Enhancing Adversarial Transferability with Checkpoints of a Single Model's Training—0
Show:102550
← PrevPage 18 of 182Next →

No leaderboard results yet.