{"total":17,"rows":[{"id":"2410.20290","title":"Fast Best-of-N Decoding via Speculative Rejection","created":"2024-10-26","cited_by_count":112,"area":null},{"id":"2408.16673","title":"Preserving Diversity in Supervised Fine-Tuning of Large Language Models","created":"2024-08-29","cited_by_count":70,"area":null},{"id":"2505.20674","title":"PonderLM: Pretraining Language Models to Ponder in Continuous Space","created":"2025-05-27","cited_by_count":44,"area":null},{"id":"2510.23393","title":"The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation","created":"2025-10-27","cited_by_count":16,"area":null},{"id":"2410.06084","title":"Diversity-Rewarded CFG Distillation","created":"2024-10-08","cited_by_count":9,"area":null},{"id":"2605.22817","title":"Vector Policy Optimization: Training for Diversity Improves Test-Time Search","created":"2026-05-21","cited_by_count":8,"area":null},{"id":"2505.12669","title":"Text2midi-InferAlign: Improving Symbolic Music Generation with Inference-Time Alignment","created":"2025-05-19","cited_by_count":4,"area":null},{"id":"2412.11625","title":"Fool Me, Fool Me: User Attitudes Toward LLM Falsehoods","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2604.10392","title":"Intent-aligned Formal Specification Synthesis via Traceable Refinement","created":"2026-04-12","cited_by_count":2,"area":null},{"id":"2604.20623","title":"RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-N Ranking","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2508.10030","title":"Inference-Aware Prompt Optimization for Aligning Black-Box Large Language Models","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2510.04919","title":"Do LLMs Align with My Task? Evaluating Text-to-SQL via Dataset Alignment","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2603.22017","title":"Domain Adapted Large Language Models for Additive Manufacturing","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2605.17295","title":"DISA: Offline Importance Sampling for Distribution-Matching LLM-RL","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2607.11146","title":"Rank-Conditioned Sample Reuse for the Plackett--Luce Best-of-$K$ Objective","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2609.35793","title":"Learning from the Gap Between Pass@K and Pass@1","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.17370","title":"HarnessTTT: Learn to Optimize Harness at Test-Time for Scientific Discovery","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}