{"total":85,"rows":[{"id":"2502.01456","title":"Process Reinforcement through Implicit Rewards","created":"2025-02-03","cited_by_count":504,"area":"lr"},{"id":"2405.07863","title":"RLHF Workflow: From Reward Modeling to Online RLHF","created":"2024-05-13","cited_by_count":267,"area":"lr"},{"id":"2411.10442","title":"Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization","created":"2024-11-15","cited_by_count":239,"area":"lr"},{"id":"2404.02078","title":"Advancing LLM Reasoning Generalists with Preference Trees","created":"2024-04-02","cited_by_count":192,"area":"lr"},{"id":"2503.10460","title":"Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond","created":"2025-03-13","cited_by_count":175,"area":"lr"},{"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":"2406.11839","title":"mDPO: Conditional Preference Optimization for Multimodal Large Language Models","created":"2024-06-17","cited_by_count":92,"area":"mllm"},{"id":"2406.10858","title":"Step-level Value Preference Optimization for Mathematical Reasoning","created":"2024-06-16","cited_by_count":72,"area":"lr"},{"id":"2507.08838","title":"wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models","created":"2025-07-07","cited_by_count":71,"area":"lr"},{"id":"2406.09215","title":"On Softmax Direct Preference Optimization for Recommendation","created":"2024-06-13","cited_by_count":64,"area":"alignment"},{"id":"2412.16145","title":"Offline Reinforcement Learning for LLM Multi-Step Reasoning","created":"2024-12-20","cited_by_count":54,"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":"2412.14516","title":"Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment","created":"2024-12-19","cited_by_count":51,"area":"alignment"},{"id":"2404.04656","title":"Binary Classifier Optimization for Large Language Model Alignment","created":"2024-04-06","cited_by_count":45,"area":"alignment"},{"id":"2505.18116","title":"NFT: Bridging Supervised Learning and Reinforcement Learning in Math Reasoning","created":"2025-05-23","cited_by_count":38,"area":"lr"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2406.10957","title":"Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence","created":"2024-06-16","cited_by_count":31,"area":"alignment"},{"id":"2512.16912","title":"Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward","created":"2025-12-18","cited_by_count":27,"area":"lr"},{"id":"2410.15334","title":"Modality-Fair Preference Optimization for Trustworthy MLLM Alignment","created":"2024-10-20","cited_by_count":26,"area":"mllm"},{"id":"2407.01648","title":"Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization","created":"2024-07-01","cited_by_count":25,"area":"diffusion"},{"id":"2502.00883","title":"SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters","created":"2025-02-02","cited_by_count":25,"area":"alignment"},{"id":"2507.23779","title":"Phi-Ground Tech Report: Advancing Perception in GUI Grounding","created":"2025-07-31","cited_by_count":25,"area":"lr"},{"id":"2406.07327","title":"3D-Properties: Identifying Challenges in DPO and Charting a Path Forward","created":"2024-06-11","cited_by_count":24,"area":"alignment"},{"id":"2410.21545","title":"CARMO: Dynamic Criteria Generation for Context-Aware Reward Modelling","created":"2024-10-28","cited_by_count":22,"area":"alignment"},{"id":"2410.12854","title":"TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Trees","created":"2024-10-10","cited_by_count":19,"area":"lr"},{"id":"2505.11595","title":"Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO","created":"2025-05-16","cited_by_count":19,"area":"lr"},{"id":"2502.04153","title":"UltraIF: Advancing Instruction Following from the Wild","created":"2025-02-06","cited_by_count":18,"area":null},{"id":"2501.15420","title":"Visual Generation Without Guidance","created":"2025-01-26","cited_by_count":17,"area":null},{"id":"2410.09347","title":"Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment","created":"2024-10-12","cited_by_count":14,"area":null},{"id":"2503.17928","title":"Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization","created":"2025-03-23","cited_by_count":14,"area":"mllm"},{"id":"2502.02088","title":"Dual-IPO: Dual-Iterative Preference Optimization for Text-to-Video Generation","created":"2025-02-04","cited_by_count":13,"area":"diffusion"},{"id":"2505.05465","title":"ComPO: Preference Alignment via Comparison Oracles","created":"2025-05-08","cited_by_count":13,"area":"alignment"},{"id":"2407.09024","title":"Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control","created":"2024-07-12","cited_by_count":12,"area":"diffusion"},{"id":"2503.17726","title":"A Survey on Mathematical Reasoning and Optimization with Large Language Models","created":"2025-03-22","cited_by_count":12,"area":"lr"},{"id":"2507.04832","title":"Discrete Diffusion Trajectory Alignment via Stepwise Decomposition","created":"2025-07-07","cited_by_count":12,"area":"diffusion"},{"id":"2410.08067","title":"Reward-Augmented Data Enhances Direct Preference Alignment of LLMs","created":"2024-10-10","cited_by_count":10,"area":"alignment"},{"id":"2503.02783","title":"Teaching Your Models to Understand Code via Focal Preference Alignment","created":"2025-03-04","cited_by_count":10,"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":"2412.13862","title":"Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model","created":"2024-12-18","cited_by_count":9,"area":"alignment"},{"id":"2505.12225","title":"Mining Intrinsic Rewards from LLM Hidden States for Efficient Best-of-N Sampling","created":"2025-05-18","cited_by_count":9,"area":"alignment"},{"id":"2409.06411","title":"Length Desensitization in Direct Preference Optimization","created":"2024-09-10","cited_by_count":8,"area":"alignment"},{"id":"2504.09802","title":"Enhancing Reasoning Abilities of Small LLMs with Cognitive Alignment","created":"2025-04-14","cited_by_count":7,"area":"lr"},{"id":"2505.08507","title":"InfoPO: On Mutual Information Maximization for Large Language Model Alignment","created":"2025-05-13","cited_by_count":7,"area":"alignment"},{"id":"2505.12843","title":"Bias Fitting to Mitigate Length Bias of Reward Model in RLHF","created":"2025-05-19","cited_by_count":7,"area":"alignment"},{"id":"2505.18720","title":"Optimal Transport-Based Token Weighting scheme for Enhanced Preference Optimization","created":"2025-05-24","cited_by_count":7,"area":"alignment"},{"id":"2508.14904","title":"Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training","created":"2025-08-12","cited_by_count":7,"area":"alignment"},{"id":"2512.07175","title":"SPACE: Noise Contrastive Estimation Stabilizes Self-Play Fine-Tuning for Large Language Models","created":"2025-12-08","cited_by_count":7,"area":"synth"},{"id":"2502.00814","title":"Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling","created":"2025-02-02","cited_by_count":6,"area":"alignment"},{"id":"2502.13723","title":"Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values","created":"2025-02-19","cited_by_count":6,"area":"lr"},{"id":"2506.00297","title":"Improving Protein Sequence Design through Designability Preference Optimization","created":"2025-05-30","cited_by_count":6,"area":null},{"id":"2409.07772","title":"Alignment with Preference Optimization Is All You Need for LLM Safety","created":"2024-09-12","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":"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":"2506.22578","title":"The Hidden Link Between RLHF and Contrastive Learning","created":"2025-06-27","cited_by_count":5,"area":"alignment"},{"id":"2603.14128","title":"Diffusion Reinforcement Learning via Centered Reward Distillation","created":"2026-03-14","cited_by_count":5,"area":"diffusion"},{"id":"2505.12358","title":"AbFlowNet: Optimizing Antibody-Antigen Binding Energy via Diffusion-GFlowNet Fusion","created":"2025-05-18","cited_by_count":4,"area":"diffusion"},{"id":"2409.18170","title":"Evaluation of Large Language Models for Summarization Tasks in the Medical Domain: A Narrative Review","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2502.01237","title":"The Differences Between Direct Alignment Algorithms are a Blur","created":"2025-02-03","cited_by_count":3,"area":"alignment"},{"id":"2505.12435","title":"SGDPO: Self-Guided Direct Preference Optimization for Language Model Alignment","created":"2025-05-18","cited_by_count":3,"area":"alignment"},{"id":"2505.23634","title":"MCP Safety Training: Learning to Refuse Falsely Benign MCP Exploits using Improved Preference Alignment","created":"2025-05-29","cited_by_count":3,"area":"agents"},{"id":"2510.13022","title":"On the Role of Preference Variance in Preference Optimization","created":"2025-10-14","cited_by_count":3,"area":"alignment"},{"id":"2603.00526","title":"Mesh-Pro: Asynchronous Advantage-guided Ranking Preference Optimization for Artist-style Quadrilateral Mesh Generation","created":"2026-02-28","cited_by_count":3,"area":"alignment"},{"id":"2502.14400","title":"HPS: Hard Preference Sampling for Human Preference Alignment","created":"2025-02-20","cited_by_count":2,"area":"alignment"},{"id":"2510.03283","title":"MACE: A Hybrid LLM Serving System with Colocated SLO-aware Continuous Retraining Alignment","created":"2025-09-28","cited_by_count":2,"area":"inference"},{"id":"2602.00603","title":"Direct Preference Optimization with Rating Information: Practical Algorithms and Provable Gains","created":"2026-01-31","cited_by_count":2,"area":"alignment"},{"id":"2406.16377","title":"On the Transformations across Reward Model, Parameter Update, and In-Context Prompt","created":"2024-06-24","cited_by_count":1,"area":"alignment"},{"id":"2502.18679","title":"Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference Data","created":"2025-02-25","cited_by_count":1,"area":"alignment"},{"id":"2505.23761","title":"Differential Information Distribution: A Bayesian Perspective on Direct Preference Optimization","created":"2025-05-29","cited_by_count":1,"area":"alignment"},{"id":"2601.22432","title":"ReNCE: Learning to Reason by Noise Contrastive Estimation","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2607.16240","title":"Normalized Rewards for Preference Optimization","created":"2026-06-26","cited_by_count":1,"area":"alignment"},{"id":"2405.13386","title":"360Zhinao Technical Report","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2412.16378","title":"REFA: Reference Free Alignment for multi-preference optimization","created":"2024-12-20","cited_by_count":0,"area":"alignment"},{"id":"2505.12845","title":"Multi-Level Aware Preference Learning: Enhancing RLHF for Complex Multi-Instruction Tasks","created":"2025-05-19","cited_by_count":0,"area":"alignment"},{"id":"2505.21893","title":"SIPO: Stabilized and Improved Preference Optimization for Aligning Diffusion Models","created":"2025-05-28","cited_by_count":0,"area":"diffusion"},{"id":"2512.04513","title":"BiTAgent: A Task-Aware Modular Framework for Bidirectional Coupling between Multimodal Large Language Models and World Models","created":"2025-12-04","cited_by_count":0,"area":"wm"},{"id":"2602.01207","title":"Not All Preferences Deserve Gradients: Understanding Gradient Utility in Offline Reasoning Alignment","created":"2026-02-01","cited_by_count":0,"area":"lr"},{"id":"2604.24536","title":"Generating Place-Based Compromises Between Two Points of View","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.11217","title":"Training-Free Refusal of MCP Exploits via Retrieval-Augmented Generation","created":"2026-05-11","cited_by_count":0,"area":"rag"},{"id":"2605.13284","title":"Learning Perturbations to Extrapolate Your LLM","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.23740","title":"Weight-Space Geometry of Offline Reasoning Training","created":"2026-06-21","cited_by_count":0,"area":"lr"},{"id":"2606.24937","title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2607.16431","title":"RIMS: Preference Optimization via Smoothed Multi-pair Aggregation for Small-Scale LLM Retrieval-Augmented Generation","created":"2026-07-17","cited_by_count":0,"area":"rag"},{"id":"2609.06893","title":"Towards Bridging the Gap Between Offline and Iterative Alignment via Preference Distillation","created":"2026-09-07","cited_by_count":0,"area":"alignment"},{"id":"2609.16340","title":"StalePO: Anchored Token-Level Preference Optimization using Legacy Post-Edits in Machine Translation","created":"2026-09-14","cited_by_count":0,"area":"alignment"},{"id":"2609.19144","title":"A Zeroth-Order Paradigm for LLM Preference Alignment","created":"2026-09-16","cited_by_count":0,"area":"alignment"}],"next_cursor":null}