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 301–350 of 9051 papers

TitleStatusHype
Explaining Machine Learning Classifiers through Diverse Counterfactual ExplanationsCode2
Lenia - Biology of Artificial LifeCode2
Exploring Design of Multi-Agent LLM Dialogues for Research IdeationCode1
Prompt-Free Conditional Diffusion for Multi-object Image AugmentationCode1
Inv-Entropy: A Fully Probabilistic Framework for Uncertainty Quantification in Language ModelsCode1
Diversity-Guided MLP Reduction for Efficient Large Vision TransformersCode1
Scalable and Cost-Efficient de Novo Template-Based Molecular GenerationCode1
AMPED: Adaptive Multi-objective Projection for balancing Exploration and skill DiversificationCode1
ByteMorph: Benchmarking Instruction-Guided Image Editing with Non-Rigid MotionsCode1
Foundation Molecular Grammar: Multi-Modal Foundation Models Induce Interpretable Molecular Graph LanguagesCode1
Analysis and Evaluation of Synthetic Data Generation in Speech Dysfluency DetectionCode1
MMP-2K: A Benchmark Multi-Labeled Macro Photography Image Quality Assessment DatabaseCode1
WebNovelBench: Placing LLM Novelists on the Web Novel DistributionCode1
Spectral-Spatial Self-Supervised Learning for Few-Shot Hyperspectral Image ClassificationCode1
X2C: A Dataset Featuring Nuanced Facial Expressions for Realistic Humanoid ImitationCode1
TopoDiT-3D: Topology-Aware Diffusion Transformer with Bottleneck Structure for 3D Point Cloud GenerationCode1
DRA-GRPO: Exploring Diversity-Aware Reward Adjustment for R1-Zero-Like Training of Large Language ModelsCode1
ReSurgSAM2: Referring Segment Anything in Surgical Video via Credible Long-term TrackingCode1
FLUXSynID: A Framework for Identity-Controlled Synthetic Face Generation with Document and Live ImagesCode1
Griffin: Towards a Graph-Centric Relational Database Foundation ModelCode1
TrajEvo: Designing Trajectory Prediction Heuristics via LLM-driven EvolutionCode1
Token Coordinated Prompt Attention is Needed for Visual PromptingCode1
CreoPep: A Universal Deep Learning Framework for Target-Specific Peptide Design and OptimizationCode1
Adapting Precomputed Features for Efficient Graph CondensationCode1
Instruction-Tuning Data Synthesis from Scratch via Web ReconstructionCode1
RainbowPlus: Enhancing Adversarial Prompt Generation via Evolutionary Quality-Diversity SearchCode1
TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language ModelsCode1
Parameterized Synthetic Text Generation with SimpleStoriesCode1
ID-Booth: Identity-consistent Face Generation with Diffusion ModelsCode1
CamContextI2V: Context-aware Controllable Video GenerationCode1
Advanced Codebook Design for SCMA-aided NTNs With Randomly Distributed UsersCode1
A Doubly Decoupled Network for edge detectionCode1
The Procedural Content Generation Benchmark: An Open-source Testbed for Generative Challenges in GamesCode1
Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-TrainingCode1
Unseen from Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language NavigationCode1
Unraveling the Effects of Synthetic Data on End-to-End Autonomous DrivingCode1
Probabilistic Prompt Distribution Learning for Animal Pose EstimationCode1
From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level AlignmentCode1
Modeling Thousands of Human Annotators for Generalizable Text-to-Image Person Re-identificationCode1
Oasis: One Image is All You Need for Multimodal Instruction Data SynthesisCode1
Process-Supervised LLM Recommenders via Flow-guided TuningCode1
AIM-Fair: Advancing Algorithmic Fairness via Selectively Fine-Tuning Biased Models with Contextual Synthetic DataCode1
Recent Advances on Generalizable Diffusion-generated Image DetectionCode1
Inverse Materials Design by Large Language Model-Assisted Generative FrameworkCode1
HIPPO: Enhancing the Table Understanding Capability of Large Language Models through Hybrid-Modal Preference OptimizationCode1
Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable MetricCode1
CoT-ICL Lab: A Petri Dish for Studying Chain-of-Thought Learning from In-Context DemonstrationsCode1
I-MCTS: Enhancing Agentic AutoML via Introspective Monte Carlo Tree SearchCode1
Diverse Topology Optimization using Modulated Neural FieldsCode1
FairDiverse: A Comprehensive Toolkit for Fair and Diverse Information Retrieval AlgorithmsCode1
Show:102550
← PrevPage 7 of 182Next →

No leaderboard results yet.