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
The Paradox of Stochasticity: Limited Creativity and Computational Decoupling in Temperature-Varied LLM Outputs of Structured Fictional Data—0
Faithful, Unfaithful or Ambiguous? Multi-Agent Debate with Initial Stance for Summary EvaluationCode0
Measuring Diversity in Synthetic DatasetsCode1
GenIAS: Generator for Instantiating Anomalies in time Series—0
Classifier-Free Guidance: From High-Dimensional Analysis to Generalized Guidance Forms—0
Scaling Pre-training to One Hundred Billion Data for Vision Language Models—0
RenderBox: Expressive Performance Rendering with Text Control—0
exHarmony: Authorship and Citations for Benchmarking the Reviewer Assignment ProblemCode0
Bridging the Evaluation Gap: Leveraging Large Language Models for Topic Model EvaluationCode0
On properties driving diversity index selection—0
We Can't Understand AI Using our Existing Vocabulary—0
Unsupervised Translation of Emergent Communication—0
Extract-QD Framework: A Generic Approach for Quality-Diversity in Noisy, Stochastic or Uncertain Domains—0
Many-Task Federated Fine-Tuning via Unified Task Vectors—0
Select before Act: Spatially Decoupled Action Repetition for Continuous Control—0
Scalable and Ethical Insider Threat Detection through Data Synthesis and Analysis by LLMs—0
TANGLED: Generating 3D Hair Strands from Images with Arbitrary Styles and Viewpoints—0
Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoECode1
Universal point spread function engineering for 3D optical information processing—0
Fact-or-Fair: A Checklist for Behavioral Testing of AI Models on Fairness-Related QueriesCode0
Pencils to Pixels: A Systematic Study of Creative Drawings across Children, Adults and AICode0
Knowledge Graph-Guided Retrieval Augmented GenerationCode2
Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion—0
A Tutorial On Intersectionality in Fair Rankings—0
ELITE: Enhanced Language-Image Toxicity Evaluation for Safety—0
SeDi-Instruct: Enhancing Alignment of Language Models through Self-Directed Instruction Generation—0
Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment—0
PoI: Pixel of Interest for Novel View Synthesis Assisted Scene Coordinate Regression—0
Seasonal Station-Keeping of Short Duration High Altitude Balloons using Deep Reinforcement Learning—0
Affine Frequency Division Multiplexing: Extending OFDM for Scenario-Flexibility and Resilience—0
Leveraging Hypernetworks and Learnable Kernels for Consumer Energy Forecasting Across Diverse Consumer Types—0
CCS: Controllable and Constrained Sampling with Diffusion Models via Initial Noise Perturbation—0
Leveraging band diversity for feature selection in EO data—0
When One LLM Drools, Multi-LLM Collaboration Rules—0
Multi-Agent Reinforcement Learning with Focal Diversity OptimizationCode0
TriNER: A Series of Named Entity Recognition Models For Hindi, Bengali & Marathi—0
Single-Domain Generalized Object Detection by Balancing Domain Diversity and Invariance—0
UniForm: A Unified Multi-Task Diffusion Transformer for Audio-Video Generation—0
Augmented Conditioning Is Enough For Effective Training Image Generation—0
Pre-Optimized Irregular Arrays versus Moveable Antennas in Multi-User MIMO Systems—0
DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation—0
From Features to Transformers: Redefining Ranking for Scalable Impact—0
MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding—0
KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs—0
Proportional Selection in Networks—0
Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data—0
Controllable Satellite-to-Street-View Synthesis with Precise Pose Alignment and Zero-Shot Environmental Control—0
How Inclusively do LMs Perceive Social and Moral Norms?Code0
Position Paper: Building Trust in Synthetic Data for Clinical AI—0
Topic Modeling in Marathi—0
Show:102550
← PrevPage 15 of 182Next →

No leaderboard results yet.