{"total":19,"rows":[{"id":"2509.02534","title":"Jointly Reinforcing Diversity and Quality in Language Model Generations","created":"2025-09-02","cited_by_count":80,"area":null},{"id":"2510.10023","title":"Skill-Targeted Adaptive Training","created":"2025-10-11","cited_by_count":6,"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":"2604.08519","title":"Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2512.05267","title":"Uncertainty Quantification and Data Efficiency in AI: An Information-Theoretic Perspective","created":"2025-12-04","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":"2608.24065","title":"Mechanistic Circuit Identification for Controllable Data Generation","created":"2026-08-25","cited_by_count":2,"area":null},{"id":"2604.14564","title":"MARS$^2$: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2605.13149","title":"AcquisitionSynthesis: Targeted Data Generation using Acquisition Functions","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2606.12385","title":"Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2509.25671","title":"The Flaw of Averages: Measuring Benchmark-Level Distributional Robustness","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2604.26170","title":"EvoSelect: Data-Efficient LLM Evolution for Targeted Task Adaptation","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.29448","title":"How Much Is a Dataset Worth? Scaling Laws, the Vendi Score, and Matrix Spectral Functions","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.01304","title":"When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.10406","title":"FOGO: Forgetting-aware Orthogonalization Optimizer","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.15216","title":"Spokes: Optimizing for Diverse Pretraining Data Selection","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2607.02423","title":"Neuron-Aware Active Few-Shot Learning for LLMs","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2610.01382","title":"Gacha Decoding: Eliciting Diverse Generations Through Instruction Following","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.12659","title":"MagicBeanStalk: Escaping the RLVR Zero Advantage Trap with Recursive Data Synthesis","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}