{"total":20,"rows":[{"id":"2302.12192","title":"Aligning Text-to-Image Models using Human Feedback","created":"2023-02-23","cited_by_count":422,"area":"alignment"},{"id":"2402.04792","title":"Direct Language Model Alignment from Online AI Feedback","created":"2024-02-07","cited_by_count":260,"area":"alignment"},{"id":"2302.08215","title":"Aligning Language Models with Preferences through f-divergence Minimization","created":"2023-02-16","cited_by_count":120,"area":"alignment"},{"id":"2406.05534","title":"Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing","created":"2024-06-08","cited_by_count":39,"area":"alignment"},{"id":"2508.21066","title":"OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning","created":"2025-08-28","cited_by_count":23,"area":"alignment"},{"id":"2503.05079","title":"On a Connection Between Imitation Learning and RLHF","created":"2025-03-07","cited_by_count":13,"area":"alignment"},{"id":"2402.09872","title":"Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community","created":"2024-02-15","cited_by_count":8,"area":"alignment"},{"id":"2503.00030","title":"RSPO: Regularized Self-Play Alignment of Large Language Models","created":"2025-02-24","cited_by_count":5,"area":"alignment"},{"id":"2503.20194","title":"GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization","created":"2025-03-26","cited_by_count":4,"area":"alignment"},{"id":"2402.18284","title":"Is Crowdsourcing Breaking Your Bank? Cost-Effective Fine-Tuning of Pre-trained Language Models with Proximal Policy Optimization","created":"2024-02-28","cited_by_count":2,"area":"alignment"},{"id":"2509.26074","title":"Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis","created":"2025-09-30","cited_by_count":2,"area":"alignment"},{"id":"2605.04653","title":"Threshold-Guided Optimization for Visual Generative Models","created":"2026-05-06","cited_by_count":2,"area":"alignment"},{"id":"2506.04464","title":"Leveraging Reward Models for Guiding Code Review Comment Generation","created":"2025-06-04","cited_by_count":1,"area":"alignment"},{"id":"2509.16475","title":"Towards Universal Debiasing for Language Models-based Tabular Data Generation","created":"2025-09-20","cited_by_count":1,"area":"alignment"},{"id":"2404.06390","title":"Latent Distance Guided Alignment Training for Large Language Models","created":"2024-04-09","cited_by_count":0,"area":"alignment"},{"id":"2410.01789","title":"Investigating on RLHF methodology","created":"2024-10-02","cited_by_count":0,"area":"alignment"},{"id":"2506.13846","title":"Fake it till You Make it: Reward Modeling as Discriminative Prediction","created":"2025-06-16","cited_by_count":0,"area":"alignment"},{"id":"2607.07993","title":"Hallucination Self-Play: Bootstrapping Reinforced Detector via Evolved Generator","created":"2026-07-08","cited_by_count":0,"area":"alignment"},{"id":"2609.31855","title":"PHIRL: Aligning Learned Rewards with Task Progress for Inverse Reinforcement Learning","created":"2026-09-25","cited_by_count":0,"area":"alignment"},{"id":"2609.34673","title":"FestDPO: Few-step Generator Alignment with Direct Preference Optimization","created":"2026-09-28","cited_by_count":0,"area":"alignment"}],"next_cursor":null}