{"total":173,"rows":[{"id":"2405.20003","title":"Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities","created":"2024-05-30","cited_by_count":159,"area":null},{"id":"2407.06863","title":"Beyond Aesthetics: Cultural Competence in Text-to-Image Models","created":"2024-07-09","cited_by_count":30,"area":null},{"id":"2402.02318","title":"Diversity Measurement and Subset Selection for Instruction Tuning Datasets","created":"2024-02-04","cited_by_count":29,"area":null},{"id":"2401.00690","title":"Benchmarking Large Language Models on Controllable Generation under Diversified Instructions","created":"2024-01-01","cited_by_count":27,"area":null},{"id":"2312.03817","title":"Diffusion Illusions: Hiding Images in Plain Sight","created":"2023-12-06","cited_by_count":26,"area":null},{"id":"2407.02961","title":"Towards a Scalable Reference-Free Evaluation of Generative Models","created":"2024-07-03","cited_by_count":26,"area":null},{"id":"2407.08188","title":"Position: Measure Dataset Diversity, Don't Just Claim It","created":"2024-07-11","cited_by_count":26,"area":null},{"id":"2310.12952","title":"Cousins Of The Vendi Score: A Family Of Similarity-Based Diversity Metrics For Science And Machine Learning","created":"2023-10-19","cited_by_count":24,"area":null},{"id":"2406.04551","title":"Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidance","created":"2024-06-06","cited_by_count":24,"area":null},{"id":"2512.04562","title":"LeMat-GenBench: A Unified Evaluation Framework for Crystal Generative Models","created":"2025-12-04","cited_by_count":23,"area":null},{"id":"2408.00397","title":"In-Context Example Selection via Similarity Search Improves Low-Resource Machine Translation","created":"2024-08-01","cited_by_count":22,"area":null},{"id":"2412.17799","title":"Automating the Search for Artificial Life with Foundation Models","created":"2024-12-23","cited_by_count":20,"area":null},{"id":"2306.13840","title":"Beyond Scale: The Diversity Coefficient as a Data Quality Metric for Variability in Natural Language Data","created":"2023-06-24","cited_by_count":19,"area":null},{"id":"2212.05129","title":"Measuring Data","created":"2022-12-09","cited_by_count":18,"area":null},{"id":"2311.16054","title":"Metric Space Magnitude for Evaluating the Diversity of Latent Representations","created":"2023-11-27","cited_by_count":17,"area":null},{"id":"2402.17287","title":"An Interpretable Evaluation of Entropy-based Novelty of Generative Models","created":"2024-02-27","cited_by_count":17,"area":null},{"id":"2405.02449","title":"Quality-Weighted Vendi Scores And Their Application To Diverse Experimental Design","created":"2024-05-03","cited_by_count":17,"area":null},{"id":"2603.08561","title":"RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback","created":"2026-03-09","cited_by_count":17,"area":null},{"id":"2405.02700","title":"Unveiling Differences in Generative Models: A Scalable Differential Clustering Approach","created":"2024-05-04","cited_by_count":16,"area":null},{"id":"2405.04457","title":"Towards Geographic Inclusion in the Evaluation of Text-to-Image Models","created":"2024-05-07","cited_by_count":16,"area":null},{"id":"2408.08310","title":"ScalingFilter: Assessing Data Quality through Inverse Utilization of Scaling Laws","created":"2024-08-15","cited_by_count":15,"area":null},{"id":"2412.18645","title":"Scendi Score: Prompt-Aware Diversity Evaluation via Schur Complement of CLIP Embeddings","created":"2024-12-24","cited_by_count":15,"area":null},{"id":"2502.15208","title":"Unveiling Attractor Cycles in Large Language Models: A Dynamical Systems View of Successive Paraphrasing","created":"2025-02-21","cited_by_count":15,"area":null},{"id":"2506.08835","title":"CulturalFrames: Assessing Cultural Expectation Alignment in Text-to-Image Models and Evaluation Metrics","created":"2025-06-10","cited_by_count":15,"area":null},{"id":"2412.17622","title":"Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms","created":"2024-12-23","cited_by_count":14,"area":null},{"id":"2406.07451","title":"A Multi-Armed Bandit Approach to Online Selection and Evaluation of Generative Models","created":"2024-06-11","cited_by_count":13,"area":null},{"id":"2410.21719","title":"Do Vendi Scores Converge with Finite Samples? Truncated Vendi Score for Finite-Sample Convergence Guarantees","created":"2024-10-29","cited_by_count":12,"area":null},{"id":"2505.07175","title":"Metrics that matter: Evaluating image quality metrics for medical image generation","created":"2025-05-12","cited_by_count":12,"area":null},{"id":"2311.13028","title":"DMLR: Data-centric Machine Learning Research -- Past, Present and Future","created":"2023-11-21","cited_by_count":11,"area":null},{"id":"2403.00269","title":"Large Convolutional Model Tuning via Filter Subspace","created":"2024-03-01","cited_by_count":11,"area":null},{"id":"2604.16027","title":"Where does output diversity collapse in post-training?","created":"2026-04-17","cited_by_count":11,"area":null},{"id":"2310.11714","title":"Consistent Distributed Ranking of Generative Models via Kernel Distances","created":"2023-10-18","cited_by_count":10,"area":null},{"id":"2302.02150","title":"This Intestine Does Not Exist: Multiscale Residual Variational Autoencoder for Realistic Wireless Capsule Endoscopy Image Generation","created":"2023-02-04","cited_by_count":9,"area":null},{"id":"2308.06198","title":"DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity","created":"2023-08-11","cited_by_count":9,"area":null},{"id":"2410.01322","title":"Forte : Finding Outliers with Representation Typicality Estimation","created":"2024-10-02","cited_by_count":9,"area":null},{"id":"2410.06084","title":"Diversity-Rewarded CFG Distillation","created":"2024-10-08","cited_by_count":9,"area":null},{"id":"2412.06235","title":"VariFace: Fair and Diverse Synthetic Dataset Generation for Face Recognition","created":"2024-12-09","cited_by_count":8,"area":null},{"id":"2506.08071","title":"CuRe: Cultural Gaps in the Long Tail of Text-to-Image Systems","created":"2025-06-09","cited_by_count":8,"area":null},{"id":"2511.05650","title":"Optimizing Diversity and Quality through Base-Aligned Model Collaboration","created":"2025-11-07","cited_by_count":8,"area":null},{"id":"2606.26448","title":"Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist","created":"2026-06-24","cited_by_count":8,"area":null},{"id":"2410.06851","title":"Understanding Model Ensemble in Transferable Adversarial Attack","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2506.24106","title":"On the Predictive Power of Representation Dispersion in Language Models","created":"2025-06-30","cited_by_count":7,"area":null},{"id":"2508.09654","title":"Improving Diversity in Language Models: When Temperature Fails, Change the Loss","created":"2025-08-13","cited_by_count":7,"area":null},{"id":"2304.11961","title":"Towards Mode Balancing of Generative Models via Diversity Weights","created":"2023-04-24","cited_by_count":6,"area":null},{"id":"2310.16499","title":"Data Optimization in Deep Learning: A Survey","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2409.18859","title":"Challenges of Generating Structurally Diverse Graphs","created":"2024-09-27","cited_by_count":6,"area":null},{"id":"2410.14556","title":"Measuring Diversity: Axioms and Challenges","created":"2024-10-18","cited_by_count":6,"area":null},{"id":"2411.02817","title":"Conditional Vendi Score: Prompt-Aware Diversity Evaluation for Generative AI Models and LLMs","created":"2024-11-05","cited_by_count":6,"area":null},{"id":"2411.08127","title":"TIPO: Text to Image with Text Presampling for Prompt Optimization","created":"2024-11-12","cited_by_count":6,"area":null},{"id":"2508.10631","title":"Increasing the Utility of Synthetic Images through Chamfer Guidance","created":"2025-08-14","cited_by_count":6,"area":null},{"id":"2510.19557","title":"The Intricate Dance of Prompt Complexity, Quality, Diversity, and Consistency in T2I Models","created":"2025-10-22","cited_by_count":6,"area":null},{"id":"2603.13300","title":"Safety-Guided Flow (SGF): A Unified Framework for Negative Guidance in Safe Generation","created":"2026-03-02","cited_by_count":6,"area":null},{"id":"2604.13977","title":"How Can We Synthesize High-Quality Pretraining Data? A Systematic Study of Prompt Design, Generator Model, and Source Data","created":"2026-04-15","cited_by_count":6,"area":null},{"id":"2410.22592","title":"GRADE: Quantifying Sample Diversity in Text-to-Image Models","created":"2024-10-29","cited_by_count":5,"area":null},{"id":"2502.10828","title":"The Vendiscope: An Algorithmic Microscope For Data Collections","created":"2025-02-15","cited_by_count":5,"area":null},{"id":"2511.22150","title":"From Topology to Retrieval: Decoding Embedding Spaces with Unified Signatures","created":"2025-11-27","cited_by_count":5,"area":null},{"id":"2406.11143","title":"Scorecards for Synthetic Medical Data Evaluation and Reporting","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2409.09469","title":"Hyperedge Representations with Hypergraph Wavelets: Applications to Spatial Transcriptomics","created":"2024-09-14","cited_by_count":4,"area":null},{"id":"2410.14602","title":"Data Diversity as Implicit Regularization: How Does Diversity Shape the Weight Space of Deep Neural Networks?","created":"2024-10-18","cited_by_count":4,"area":null},{"id":"2411.00588","title":"$\\alpha$-TCVAE: On the relationship between Disentanglement and Diversity","created":"2024-11-01","cited_by_count":4,"area":null},{"id":"2506.05108","title":"DIMCIM: A Quantitative Evaluation Framework for Default-mode Diversity and Generalization in Text-to-Image Generative Models","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2603.18348","title":"Epistemic Generative Adversarial Networks","created":"2026-03-18","cited_by_count":4,"area":null},{"id":"2607.26811","title":"DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation","created":"2026-07-29","cited_by_count":4,"area":null},{"id":"2409.19436","title":"Introducing SDICE: An Index for Assessing Diversity of Synthetic Medical Datasets","created":"2024-09-28","cited_by_count":3,"area":null},{"id":"2410.21553","title":"Exploring the Design Space of Diffusion Bridge Models","created":"2024-10-28","cited_by_count":3,"area":null},{"id":"2502.03393","title":"Pre-training Epidemic Time Series Forecasters with Compartmental Prototypes","created":"2025-02-05","cited_by_count":3,"area":null},{"id":"2505.01225","title":"Core-Set Selection for Data-efficient Land Cover Segmentation","created":"2025-05-02","cited_by_count":3,"area":null},{"id":"2505.22813","title":"X-Factor: Quality Is a Dataset-Intrinsic Property","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2506.05634","title":"AutoQD: Automatic Discovery of Diverse Behaviors with Quality-Diversity Optimization","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2510.10715","title":"VLM-Guided Adaptive Negative Prompting for Creative Generation","created":"2025-10-12","cited_by_count":3,"area":null},{"id":"2602.02117","title":"The Maximum von Neumann Entropy Principle: Theory and Applications in Machine Learning","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2602.03183","title":"Privasis: Synthesizing the Largest \"Public\" Private Dataset from Scratch","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2606.08802","title":"Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules","created":"2026-06-07","cited_by_count":3,"area":null},{"id":"2404.10419","title":"MAD Speech: Measures of Acoustic Diversity of Speech","created":"2024-04-16","cited_by_count":2,"area":null},{"id":"2406.04257","title":"Data Measurements for Decentralized Data Markets","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2412.17684","title":"COBRA: COmBinatorial Retrieval Augmentation for Few-Shot Adaptation","created":"2024-12-23","cited_by_count":2,"area":null},{"id":"2503.18337","title":"Coeff-Tuning: A Graph Filter Subspace View for Tuning Attention-Based Large Models","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2505.11314","title":"CROC: Evaluating and Training T2I Metrics with Pseudo- and Human-Labeled Contrastive Robustness Checks","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2505.20264","title":"We Need to Measure Data Diversity in NLP -- Better and Broader","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2506.14568","title":"QUEST: Quality-aware Semi-supervised Table Extraction for Business Documents","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2507.06654","title":"MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrieval","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2509.14436","title":"When Content is Goliath and Algorithm is David: The Style and Semantic Effects of Generative Search Engine","created":"2025-09-17","cited_by_count":2,"area":null},{"id":"2510.22107","title":"Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generation","created":"2025-10-25","cited_by_count":2,"area":null},{"id":"2512.23601","title":"Enhancing Diversity of LLM-Generated Educational Tasks","created":"2025-12-29","cited_by_count":2,"area":null},{"id":"2601.06116","title":"The Homogenization Problem in LLMs: Towards Meaningful Diversity in AI Safety","created":"2026-01-03","cited_by_count":2,"area":null},{"id":"2602.07633","title":"Flow-Based Conformal Predictive Distributions","created":"2026-02-07","cited_by_count":2,"area":null},{"id":"2602.11089","title":"DataChef: Cooking Up Optimal Data Recipes for LLM Adaptation via Reinforcement Learning","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2602.14682","title":"Exposing Diversity Bias in Deep Generative Models: Statistical Origins and Correction of Diversity Error","created":"2026-02-16","cited_by_count":2,"area":null},{"id":"2603.23140","title":"DAK-UCB: Diversity-Aware Prompt Routing for LLMs and Generative Models","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2603.24480","title":"Positive-First Most Ambiguous: A Simple Active Learning Criterion for Interactive Retrieval of Rare Categories","created":"2026-03-25","cited_by_count":2,"area":null},{"id":"2608.21784","title":"DefaultShift: Auditing Semantic Default Shift in Accelerated Text-to-Image Models","created":"2026-08-22","cited_by_count":2,"area":null},{"id":"2507.10855","title":"Sparse Fine-Tuning of Transformers for Generative Tasks","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2508.08680","title":"TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2510.15828","title":"GENESIS: A Generative Model of Episodic-Semantic Interaction","created":"2025-10-17","cited_by_count":1,"area":null},{"id":"2510.24037","title":"Kernelized Sparse Fine-Tuning with Bi-level Parameter Competition for Vision Models","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2511.20251","title":"Diversifying Long Prompt Image Generation through Structured Prompt Embedding Space Sampling","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2512.00810","title":"Soft Quality-Diversity Optimization","created":"2025-11-30","cited_by_count":1,"area":null},{"id":"2512.13083","title":"DiRe: Diversity-promoting Regularization for Dataset Condensation","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2602.09775","title":"Where Do Images Come From? Analyzing Captions to Geographically Profile Datasets","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2602.10062","title":"Vendi Novelty Scores for Out-of-Distribution Detection","created":"2026-02-10","cited_by_count":1,"area":null}],"next_cursor":"100"}