{"total":135,"rows":[{"id":"2404.18922","title":"DPO Meets PPO: Reinforced Token Optimization for RLHF","created":"2024-04-29","cited_by_count":127,"area":"alignment"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2410.20290","title":"Fast Best-of-N Decoding via Speculative Rejection","created":"2024-10-26","cited_by_count":112,"area":null},{"id":"2406.09136","title":"Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs","created":"2024-06-13","cited_by_count":96,"area":"lr"},{"id":"2503.02318","title":"Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models","created":"2025-03-04","cited_by_count":95,"area":"lr"},{"id":"2507.16746","title":"Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning","created":"2025-07-22","cited_by_count":84,"area":"lr"},{"id":"2411.19943","title":"Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability","created":"2024-11-29","cited_by_count":83,"area":"lr"},{"id":"2410.11287","title":"Process Reward Model with Q-Value Rankings","created":"2024-10-15","cited_by_count":80,"area":"lr"},{"id":"2405.19316","title":"Robust Preference Optimization through Reward Model Distillation","created":"2024-05-29","cited_by_count":67,"area":"alignment"},{"id":"2410.16033","title":"TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling","created":"2024-10-18","cited_by_count":61,"area":"lr"},{"id":"2504.12328","title":"A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future","created":"2025-04-12","cited_by_count":53,"area":"alignment"},{"id":"2506.08446","title":"A Survey on Large Language Models for Mathematical Reasoning","created":"2025-06-10","cited_by_count":52,"area":"lr"},{"id":"2412.14516","title":"Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment","created":"2024-12-19","cited_by_count":51,"area":"alignment"},{"id":"2504.12329","title":"Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time","created":"2025-04-12","cited_by_count":48,"area":"lr"},{"id":"2502.12671","title":"Baichuan-M1: Pushing the Medical Capability of Large Language Models","created":"2025-02-18","cited_by_count":43,"area":null},{"id":"2410.04350","title":"TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights","created":"2024-10-06","cited_by_count":42,"area":"alignment"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2506.21656","title":"Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs","created":"2025-06-26","cited_by_count":32,"area":"lr"},{"id":"2503.00897","title":"A Simple and Effective Reinforcement Learning Method for Text-to-Image Diffusion Fine-tuning","created":"2025-03-02","cited_by_count":30,"area":"diffusion"},{"id":"2410.10148","title":"AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization","created":"2024-10-14","cited_by_count":29,"area":"alignment"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2508.02298","title":"CAPO: Towards Enhancing LLM Reasoning through Generative Credit Assignment","created":"2025-08-04","cited_by_count":26,"area":"lr"},{"id":"2408.13518","title":"Selective Preference Optimization via Token-Level Reward Function Estimation","created":"2024-08-24","cited_by_count":25,"area":"lr"},{"id":"2502.10867","title":"A Tutorial on LLM Reasoning: Relevant Methods behind ChatGPT o1","created":"2025-02-15","cited_by_count":25,"area":"lr"},{"id":"2503.02846","title":"Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs","created":"2025-03-04","cited_by_count":24,"area":"alignment"},{"id":"2405.15065","title":"Direct Preference Optimization With Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences","created":"2024-05-23","cited_by_count":23,"area":"alignment"},{"id":"2510.00194","title":"GRPO-$\\lambda$: Credit Assignment improves LLM Reasoning","created":"2025-09-30","cited_by_count":23,"area":"lr"},{"id":"2502.03052","title":"Understanding and Enhancing the Transferability of Jailbreaking Attacks","created":"2025-02-05","cited_by_count":22,"area":"safety"},{"id":"2603.01162","title":"Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic","created":"2026-03-01","cited_by_count":21,"area":"lr"},{"id":"2406.00654","title":"Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback","created":"2024-06-02","cited_by_count":20,"area":"alignment"},{"id":"2410.16714","title":"Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment","created":"2024-10-22","cited_by_count":20,"area":"alignment"},{"id":"2504.13122","title":"VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models","created":"2025-04-17","cited_by_count":17,"area":"alignment"},{"id":"2505.02666","title":"A Survey on Progress in LLM Alignment from the Perspective of Reward Design","created":"2025-05-05","cited_by_count":15,"area":"alignment"},{"id":"2505.19653","title":"Token-Importance Guided Direct Preference Optimization","created":"2025-05-26","cited_by_count":14,"area":"alignment"},{"id":"2505.24445","title":"Learning Safety Constraints for Large Language Models","created":"2025-05-30","cited_by_count":13,"area":"safety"},{"id":"2406.07780","title":"A Critical Look At Tokenwise Reward-Guided Text Generation","created":"2024-06-12","cited_by_count":12,"area":"alignment"},{"id":"2411.07618","title":"Constrain Alignment with Sparse Autoencoders","created":"2024-11-12","cited_by_count":12,"area":"alignment"},{"id":"2504.04524","title":"Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning","created":"2025-04-06","cited_by_count":12,"area":"lr"},{"id":"2407.02243","title":"Robust Zero-Shot Text-to-Speech Synthesis with Reverse Inference Optimization","created":"2024-07-02","cited_by_count":11,"area":"alignment"},{"id":"2502.15145","title":"Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHF","created":"2025-02-21","cited_by_count":11,"area":"alignment"},{"id":"2512.07533","title":"VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection","created":"2025-12-08","cited_by_count":11,"area":"lr"},{"id":"2512.23126","title":"InSPO: Unlocking Intrinsic Self-Reflection for LLM Preference Optimization","created":"2025-12-29","cited_by_count":11,"area":"alignment"},{"id":"2506.08712","title":"ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization","created":"2025-06-10","cited_by_count":10,"area":"alignment"},{"id":"2410.05102","title":"SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks","created":"2024-10-07","cited_by_count":9,"area":"alignment"},{"id":"2412.04628","title":"Multi-Preference Optimization: Generalizing DPO via Set-Level Contrasts","created":"2024-12-05","cited_by_count":9,"area":"alignment"},{"id":"2505.19601","title":"Preference Optimization by Estimating the Ratio of the Data Distribution","created":"2025-05-26","cited_by_count":9,"area":"alignment"},{"id":"2510.03595","title":"Decoupling Task-Solving and Output Formatting in LLM Generation","created":"2025-10-04","cited_by_count":9,"area":"lr"},{"id":"2503.23371","title":"FeRG-LLM : Feature Engineering by Reason Generation Large Language Models","created":"2025-03-30","cited_by_count":8,"area":"lr"},{"id":"2408.03459","title":"Can DPO Learn Diverse Human Values? A Theoretical Scaling Law","created":"2024-08-06","cited_by_count":7,"area":"alignment"},{"id":"2408.07471","title":"Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization","created":"2024-08-14","cited_by_count":7,"area":"alignment"},{"id":"2410.03780","title":"Reward-RAG: Enhancing RAG with Reward Driven Supervision","created":"2024-10-03","cited_by_count":7,"area":"rag"},{"id":"2504.12083","title":"Self-alignment of Large Video Language Models with Refined Regularized Preference Optimization","created":"2025-04-16","cited_by_count":7,"area":"alignment"},{"id":"2508.04149","title":"Difficulty-Based Preference Data Selection by DPO Implicit Reward Gap","created":"2025-08-06","cited_by_count":7,"area":"alignment"},{"id":"2510.03865","title":"Unlocking Reasoning Capabilities in LLMs via Reinforcement Learning Exploration","created":"2025-10-04","cited_by_count":7,"area":"lr"},{"id":"2603.00025","title":"TAB-PO: Preference Optimization with a Token-Level Adaptive Barrier for Token-Critical Structured Generation","created":"2026-02-03","cited_by_count":7,"area":"alignment"},{"id":"2605.03327","title":"DGPO: Distribution Guided Policy Optimization for Fine Grained Credit Assignment","created":"2026-05-05","cited_by_count":7,"area":"lr"},{"id":"2504.20106","title":"Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors","created":"2025-04-27","cited_by_count":6,"area":"alignment"},{"id":"2506.06366","title":"AI Agent Behavioral Science","created":"2025-06-04","cited_by_count":6,"area":"agents"},{"id":"2510.09259","title":"Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models","created":"2025-10-10","cited_by_count":6,"area":null},{"id":"2512.22716","title":"Memento 2: Learning by Stateful Reflective Memory","created":"2025-12-27","cited_by_count":6,"area":"agents"},{"id":"2602.11455","title":"Credit Where It is Due: Cross-Modality Connectivity Drives Precise Reinforcement Learning for MLLM Reasoning","created":"2026-02-12","cited_by_count":6,"area":"lr"},{"id":"2605.00380","title":"ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning","created":"2026-05-01","cited_by_count":6,"area":"lr"},{"id":"2606.29150","title":"Flow Reasoning Models: Turning Flows Into Efficient Recurrent Reasoners","created":"2026-06-28","cited_by_count":6,"area":"lr"},{"id":"2410.01957","title":"Challenges and Future Directions of Data-Centric AI Alignment","created":"2024-10-02","cited_by_count":5,"area":"alignment"},{"id":"2410.08316","title":"COS-DPO: Conditioned One-Shot Multi-Objective Fine-Tuning Framework","created":"2024-10-10","cited_by_count":5,"area":"alignment"},{"id":"2502.18293","title":"AMPO: Active Multi-Preference Optimization for Self-play Preference Selection","created":"2025-02-25","cited_by_count":5,"area":"alignment"},{"id":"2503.04240","title":"DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models","created":"2025-03-06","cited_by_count":5,"area":"alignment"},{"id":"2505.23316","title":"Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO","created":"2025-05-29","cited_by_count":5,"area":"alignment"},{"id":"2506.14574","title":"TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization","created":"2025-06-17","cited_by_count":5,"area":"alignment"},{"id":"2512.14954","title":"Cross-Tokenizer Likelihood Scoring Algorithms for Language Model Distillation","created":"2025-12-16","cited_by_count":5,"area":"distill"},{"id":"2409.17169","title":"REAL: Response Embedding-based Alignment for LLMs","created":"2024-09-17","cited_by_count":4,"area":"alignment"},{"id":"2411.07595","title":"Entropy Controllable Direct Preference Optimization","created":"2024-11-12","cited_by_count":4,"area":"alignment"},{"id":"2411.14797","title":"Continual SFT Matches Multimodal RLHF with Negative Supervision","created":"2024-11-22","cited_by_count":4,"area":"mllm"},{"id":"2508.04329","title":"Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning","created":"2025-08-06","cited_by_count":4,"area":null},{"id":"2510.13170","title":"Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism","created":"2025-10-15","cited_by_count":4,"area":"lr"},{"id":"2606.20008","title":"VIMPO: Value-Implicit Policy Optimization for LLMs","created":"2026-06-18","cited_by_count":4,"area":"lr"},{"id":"2502.12678","title":"Multi-Step Alignment as Markov Games: An Optimistic Online Gradient Descent Approach with Convergence Guarantees","created":"2025-02-18","cited_by_count":3,"area":"alignment"},{"id":"2509.01181","title":"FocusDPO: Dynamic Preference Optimization for Multi-Subject Personalized Image Generation via Adaptive Focus","created":"2025-09-01","cited_by_count":3,"area":"alignment"},{"id":"2510.01458","title":"How Well Can Preference Optimization Generalize Under Noisy Feedback?","created":"2025-10-01","cited_by_count":3,"area":"alignment"},{"id":"2510.04773","title":"Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning","created":"2025-10-06","cited_by_count":3,"area":"alignment"},{"id":"2504.16272","title":"Learning Explainable Dense Reward Shapes via Bayesian Optimization","created":"2025-04-22","cited_by_count":2,"area":"alignment"},{"id":"2505.06273","title":"Policy-labeled Preference Learning: Is Preference Enough for RLHF?","created":"2025-05-06","cited_by_count":2,"area":"alignment"},{"id":"2505.20359","title":"Risk-aware Direct Preference Optimization under Nested Risk Measure","created":"2025-05-26","cited_by_count":2,"area":"alignment"},{"id":"2505.23540","title":"Probability-Consistent Preference Optimization for Enhanced LLM Reasoning","created":"2025-05-29","cited_by_count":2,"area":"lr"},{"id":"2507.05179","title":"From Fragments to Facts: A Curriculum-Driven DPO Approach for Generating Hindi News Veracity Explanations","created":"2025-07-07","cited_by_count":2,"area":"alignment"},{"id":"2509.23564","title":"Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment","created":"2025-09-28","cited_by_count":2,"area":"alignment"},{"id":"2510.03269","title":"General Exploratory Bonus for Optimistic Exploration in RLHF","created":"2025-09-27","cited_by_count":2,"area":"alignment"},{"id":"2510.08256","title":"Mix- and MoE-DPO: A Variational Inference Approach to Direct Preference Optimization","created":"2025-10-09","cited_by_count":2,"area":"alignment"},{"id":"2601.21969","title":"Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decoding","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2604.18239","title":"Towards Disentangled Preference Optimization Dynamics: Suppress the Loser, Preserve the Winner","created":"2026-04-20","cited_by_count":2,"area":"alignment"},{"id":"2412.17572","title":"Empathetic Response in Audio-Visual Conversations Using Emotion Preference Optimization and MambaCompressor","created":"2024-12-23","cited_by_count":1,"area":"alignment"},{"id":"2502.05773","title":"PIPA: Preference Alignment as Prior-Informed Statistical Estimation","created":"2025-02-09","cited_by_count":1,"area":"alignment"},{"id":"2502.18532","title":"CuDIP: Enhancing Theorem Proving in LLMs via Curriculum Learning-based Direct Preference Optimization","created":"2025-02-25","cited_by_count":1,"area":"lr"},{"id":"2505.19743","title":"Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models","created":"2025-05-26","cited_by_count":1,"area":"alignment"},{"id":"2508.04047","title":"LaPA$^2$: Length-Aware Prefix and Prompt Attention Augmentation for Long-Form Controllable Text Generation","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2510.15716","title":"Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences","created":"2025-10-17","cited_by_count":1,"area":"alignment"},{"id":"2602.01068","title":"From Utterance to Vividity: Training Expressive Subtitle Translation LLM via Adaptive Local Preference Optimization","created":"2026-02-01","cited_by_count":1,"area":"alignment"},{"id":"2602.07832","title":"rePIRL: Learn PRM with Inverse RL for LLM Reasoning","created":"2026-02-08","cited_by_count":1,"area":"lr"},{"id":"2602.09533","title":"Autoregressive Direct Preference Optimization","created":"2026-02-10","cited_by_count":1,"area":"alignment"},{"id":"2602.11902","title":"Mitigating Mismatch within Reference-based Preference Optimization","created":"2026-02-12","cited_by_count":1,"area":"alignment"}],"next_cursor":"100"}