{"total":21,"rows":[{"id":"2410.20290","title":"Fast Best-of-N Decoding via Speculative Rejection","created":"2024-10-26","cited_by_count":112,"area":null},{"id":"2509.10147","title":"Virtual Agent Economies","created":"2025-09-12","cited_by_count":21,"area":null},{"id":"2510.11686","title":"Representation-Based Exploration for Language Models: From Test-Time to Post-Training","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2502.10762","title":"Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation","created":"2025-02-15","cited_by_count":14,"area":null},{"id":"2503.08796","title":"Robust Multi-Objective Controlled Decoding of Large Language Models","created":"2025-03-11","cited_by_count":9,"area":null},{"id":"2505.23829","title":"BiasFilter: An Inference-Time Debiasing Framework for Large Language Models","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2511.02966","title":"Inference-Time Personalized Alignment with a Few User Preference Queries","created":"2025-11-04","cited_by_count":6,"area":null},{"id":"2506.09085","title":"LLM-ML Teaming: Integrated Symbolic Decoding and Gradient Search for Valid and Stable Generative Feature Transformation","created":"2025-06-10","cited_by_count":5,"area":null},{"id":"2601.02535","title":"ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation","created":"2026-01-05","cited_by_count":5,"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":"2503.02368","title":"Evolutionary Guided Decoding: Iterative Value Refinement for LLMs","created":"2025-03-04","cited_by_count":3,"area":null},{"id":"2405.13984","title":"Less for More: Enhanced Feedback-aligned Mixed LLMs for Molecule Caption Generation and Fine-Grained NLI Evaluation","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2410.21027","title":"Transferable Post-training via Inverse Value Learning","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2510.27017","title":"Kad: A Framework for Proxy-based Test-time Alignment with Knapsack Approximation Deferral","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2607.27912","title":"IFHierBench: Hierarchical Instruction Following for Large Language Models","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2408.10764","title":"Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model","created":"2024-08-20","cited_by_count":0,"area":null},{"id":"2505.09082","title":"CEC-Zero: Chinese Error Correction Solution Based on LLM","created":"2025-05-14","cited_by_count":0,"area":null},{"id":"2511.21762","title":"Factors That Support Grounded Responses in LLM Conversations: A Rapid Review","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2604.16146","title":"On the Rejection Criterion for Proxy-based Test-time Alignment","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2609.30218","title":"Minimally Invasive Steering of Language Models","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.15058","title":"The Optimal Decoder is Tilted Temperature","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}