{"total":186,"rows":[{"id":"2304.06767","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","created":"2023-04-13","cited_by_count":686,"area":"lr"},{"id":"2406.12845","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","created":"2024-06-18","cited_by_count":376,"area":"alignment"},{"id":"2312.11456","title":"Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint","created":"2023-12-18","cited_by_count":350,"area":"alignment"},{"id":"2405.07863","title":"RLHF Workflow: From Reward Modeling to Online RLHF","created":"2024-05-13","cited_by_count":267,"area":"lr"},{"id":"2308.06394","title":"Detecting and Preventing Hallucinations in Large Vision Language Models","created":"2023-08-11","cited_by_count":256,"area":"mllm"},{"id":"2404.12358","title":"From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function","created":"2024-04-18","cited_by_count":242,"area":"alignment"},{"id":"2307.04964","title":"Secrets of RLHF in Large Language Models Part I: PPO","created":"2023-07-11","cited_by_count":229,"area":"alignment"},{"id":"2310.10505","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models","created":"2023-10-16","cited_by_count":187,"area":"alignment"},{"id":"2309.06256","title":"Mitigating the Alignment Tax of RLHF","created":"2023-09-12","cited_by_count":183,"area":"alignment"},{"id":"2402.18571","title":"Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards","created":"2024-02-28","cited_by_count":148,"area":"alignment"},{"id":"2402.07319","title":"ODIN: Disentangled Reward Mitigates Hacking in RLHF","created":"2024-02-11","cited_by_count":136,"area":"alignment"},{"id":"2101.08452","title":"Robust Reinforcement Learning on State Observations with Learned Optimal Adversary","created":"2021-01-21","cited_by_count":135,"area":null},{"id":"2404.18922","title":"DPO Meets PPO: Reinforced Token Optimization for RLHF","created":"2024-04-29","cited_by_count":127,"area":"alignment"},{"id":"2305.09836","title":"Revisiting the Minimalist Approach to Offline Reinforcement Learning","created":"2023-05-16","cited_by_count":126,"area":"offlinerl"},{"id":"2303.03982","title":"Structured State Space Models for In-Context Reinforcement Learning","created":"2023-03-07","cited_by_count":111,"area":"ssm"},{"id":"2405.16436","title":"Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer","created":"2024-05-26","cited_by_count":109,"area":"alignment"},{"id":"2110.02544","title":"Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer","created":"2021-10-06","cited_by_count":108,"area":null},{"id":"2402.14740","title":"Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs","created":"2024-02-22","cited_by_count":108,"area":"alignment"},{"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":"2503.16252","title":"Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning","created":"2025-03-20","cited_by_count":83,"area":"lr"},{"id":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78,"area":"deeprl"},{"id":"2409.13156","title":"RRM: Robust Reward Model Training Mitigates Reward Hacking","created":"2024-09-20","cited_by_count":76,"area":"alignment"},{"id":"2404.04626","title":"Towards Analyzing and Understanding the Limitations of DPO: A Theoretical Perspective","created":"2024-04-06","cited_by_count":69,"area":"alignment"},{"id":"2404.16767","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","created":"2024-04-25","cited_by_count":69,"area":"alignment"},{"id":"2102.03479","title":"Rethinking the Implementation Tricks and Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learning","created":"2021-02-06","cited_by_count":68,"area":null},{"id":"2409.02392","title":"Building Math Agents with Multi-Turn Iterative Preference Learning","created":"2024-09-04","cited_by_count":66,"area":"lr"},{"id":"2306.12420","title":"LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models","created":"2023-06-21","cited_by_count":60,"area":null},{"id":"2310.00212","title":"Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment","created":"2023-09-30","cited_by_count":57,"area":"alignment"},{"id":"2508.08221","title":"Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning","created":"2025-08-11","cited_by_count":56,"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":"2209.10485","title":"Towards a Standardised Performance Evaluation Protocol for Cooperative MARL","created":"2022-09-21","cited_by_count":49,"area":null},{"id":"2409.11704","title":"From Lists to Emojis: How Format Bias Affects Model Alignment","created":"2024-09-18","cited_by_count":49,"area":"alignment"},{"id":"2309.00754","title":"Efficient RLHF: Reducing the Memory Usage of PPO","created":"2023-09-01","cited_by_count":40,"area":"alignment"},{"id":"2409.07253","title":"Alignment of Diffusion Models: Fundamentals, Challenges, and Future","created":"2024-09-11","cited_by_count":35,"area":"diffusion"},{"id":"2201.02373","title":"Mirror Learning: A Unifying Framework of Policy Optimisation","created":"2022-01-07","cited_by_count":31,"area":null},{"id":"2101.09207","title":"Differentiable Trust Region Layers for Deep Reinforcement Learning","created":"2021-01-22","cited_by_count":25,"area":null},{"id":"2410.14606","title":"Streaming Deep Reinforcement Learning Finally Works","created":"2024-10-18","cited_by_count":25,"area":"deeprl"},{"id":"2502.00883","title":"SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters","created":"2025-02-02","cited_by_count":25,"area":"alignment"},{"id":"2408.01420","title":"Mission Impossible: A Statistical Perspective on Jailbreaking LLMs","created":"2024-08-02","cited_by_count":24,"area":"alignment"},{"id":"2411.04832","title":"Plasticity Loss in Deep Reinforcement Learning: A Survey","created":"2024-11-07","cited_by_count":24,"area":"deeprl"},{"id":"2406.17523","title":"On the consistency of hyper-parameter selection in value-based deep reinforcement learning","created":"2024-06-25","cited_by_count":21,"area":"deeprl"},{"id":"2210.09622","title":"Deep Black-Box Reinforcement Learning with Movement Primitives","created":"2022-10-18","cited_by_count":20,"area":null},{"id":"2106.01151","title":"Towards Deeper Deep Reinforcement Learning with Spectral Normalization","created":"2021-06-02","cited_by_count":19,"area":null},{"id":"2202.00079","title":"You May Not Need Ratio Clipping in PPO","created":"2022-01-31","cited_by_count":19,"area":null},{"id":"2105.12034","title":"Hyperparameter Selection for Imitation Learning","created":"2021-05-25","cited_by_count":17,"area":"offlinerl"},{"id":"2509.25174","title":"XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning","created":"2025-09-29","cited_by_count":17,"area":"deeprl"},{"id":"2203.04272","title":"Policy-Based Bayesian Experimental Design for Non-Differentiable Implicit Models","created":"2022-03-08","cited_by_count":16,"area":null},{"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":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2403.06966","title":"Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts","created":"2024-03-11","cited_by_count":14,"area":"moe"},{"id":"2403.16442","title":"If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions","created":"2024-03-25","cited_by_count":14,"area":"mllm"},{"id":"2410.10093","title":"How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspective","created":"2024-10-14","cited_by_count":14,"area":"alignment"},{"id":"2105.02730","title":"Solve routing problems with a residual edge-graph attention neural network","created":"2021-05-06","cited_by_count":13,"area":null},{"id":"2407.03038","title":"Towards Federated RLHF with Aggregated Client Preference for LLMs","created":"2024-07-03","cited_by_count":13,"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":"2203.04735","title":"A Survey on Reinforcement Learning Methods in Character Animation","created":"2022-03-07","cited_by_count":12,"area":null},{"id":"2208.01682","title":"Heterogeneous-Agent Mirror Learning: A Continuum of Solutions to Cooperative MARL","created":"2022-08-02","cited_by_count":12,"area":null},{"id":"2212.02721","title":"A Novel Deep Reinforcement Learning Based Automated Stock Trading System Using Cascaded LSTM Networks","created":"2022-12-06","cited_by_count":12,"area":null},{"id":"2412.17113","title":"Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps","created":"2024-12-22","cited_by_count":11,"area":"deeprl"},{"id":"2501.13075","title":"Evolution and The Knightian Blindspot of Machine Learning","created":"2025-01-22","cited_by_count":11,"area":null},{"id":"2602.01750","title":"Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking","created":"2026-02-02","cited_by_count":11,"area":"alignment"},{"id":"2210.08607","title":"The Impact of Task Underspecification in Evaluating Deep Reinforcement Learning","created":"2022-10-16","cited_by_count":10,"area":null},{"id":"2306.01460","title":"ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages","created":"2023-06-02","cited_by_count":10,"area":null},{"id":"2405.19548","title":"RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learning","created":"2024-05-29","cited_by_count":10,"area":"deeprl"},{"id":"2503.15354","title":"Optimizing Decomposition for Optimal Claim Verification","created":"2025-03-19","cited_by_count":10,"area":null},{"id":"2601.20789","title":"SERA: Soft-Verified Efficient Repository Agents","created":"2026-01-28","cited_by_count":10,"area":"agents"},{"id":"2108.01867","title":"A Pragmatic Look at Deep Imitation Learning","created":"2021-08-04","cited_by_count":9,"area":"offlinerl"},{"id":"2408.15332","title":"What makes math problems hard for reinforcement learning: a case study","created":"2024-08-27","cited_by_count":9,"area":"deeprl"},{"id":"2410.20749","title":"Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs","created":"2024-10-28","cited_by_count":9,"area":null},{"id":"2411.13611","title":"DSTC: Direct Preference Learning with Only Self-Generated Tests and Code to Improve Code LMs","created":"2024-11-20","cited_by_count":9,"area":"alignment"},{"id":"2306.12729","title":"MP3: Movement Primitive-Based (Re-)Planning Policy","created":"2023-06-22","cited_by_count":8,"area":null},{"id":"2502.00666","title":"Avoiding $\\mathbf{exp(R_{max})}$ scaling in RLHF through Preference-based Exploration","created":"2025-02-02","cited_by_count":8,"area":"alignment"},{"id":"2402.03590","title":"Assessing the Impact of Distribution Shift on Reinforcement Learning Performance","created":"2024-02-05","cited_by_count":7,"area":"deeprl"},{"id":"2410.23726","title":"Towards Reliable Alignment: Uncertainty-aware RLHF","created":"2024-10-31","cited_by_count":7,"area":"alignment"},{"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":"2505.20081","title":"Inference-time Alignment in Continuous Space","created":"2025-05-26","cited_by_count":7,"area":"alignment"},{"id":"2510.03817","title":"TROLL: Trust Regions improve Reinforcement Learning for Large Language Models","created":"2025-10-04","cited_by_count":7,"area":null},{"id":"2307.12798","title":"RRAML: Reinforced Retrieval Augmented Machine Learning","created":"2023-07-24","cited_by_count":6,"area":"rag"},{"id":"2308.01674","title":"End-to-End Reinforcement Learning of Koopman Models for Economic Nonlinear Model Predictive Control","created":"2023-08-03","cited_by_count":6,"area":null},{"id":"2012.13682","title":"POPO: Pessimistic Offline Policy Optimization","created":"2020-12-26","cited_by_count":5,"area":"offlinerl"},{"id":"2110.04698","title":"A Closer Look at Advantage-Filtered Behavioral Cloning in High-Noise Datasets","created":"2021-10-10","cited_by_count":5,"area":"offlinerl"},{"id":"2111.01100","title":"Investigation of Independent Reinforcement Learning Algorithms in Multi-Agent Environments","created":"2021-11-01","cited_by_count":5,"area":null},{"id":"2112.04123","title":"ShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectives","created":"2021-12-08","cited_by_count":5,"area":null},{"id":"2207.12185","title":"Post-processing Networks: Method for Optimizing Pipeline Task-oriented Dialogue Systems using Reinforcement Learning","created":"2022-07-25","cited_by_count":5,"area":null},{"id":"2211.12956","title":"Reinforcement learning for traffic signal control in hybrid action space","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","cited_by_count":5,"area":null},{"id":"2505.17122","title":"Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data?","created":"2025-05-21","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":"2602.19416","title":"IR$^3$: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking","created":"2026-02-23","cited_by_count":5,"area":"alignment"},{"id":"2106.02681","title":"SpikePropamine: Differentiable Plasticity in Spiking Neural Networks","created":"2021-06-04","cited_by_count":4,"area":null},{"id":"2202.11452","title":"Deep Learning Reproducibility and Explainable AI (XAI)","created":"2022-02-23","cited_by_count":4,"area":null},{"id":"2203.06250","title":"Combining imitation and deep reinforcement learning to accomplish human-level performance on a virtual foraging task","created":"2022-03-11","cited_by_count":4,"area":null},{"id":"2212.13472","title":"Optimal scheduling of island integrated energy systems considering multi-uncertainties and hydrothermal simultaneous transmission: A deep reinforcement learning approach","created":"2022-12-27","cited_by_count":4,"area":null},{"id":"2409.03740","title":"Differentiable Discrete Event Simulation for Queuing Network Control","created":"2024-09-05","cited_by_count":4,"area":"deeprl"},{"id":"2510.04072","title":"Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning","created":"2025-10-05","cited_by_count":4,"area":"lr"},{"id":"2102.13565","title":"Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision","created":"2021-02-26","cited_by_count":3,"area":null},{"id":"2104.02372","title":"The Fragility of Noise Estimation in Kalman Filter: Optimization Can Handle Model-Misspecification","created":"2021-04-06","cited_by_count":3,"area":null},{"id":"2306.10882","title":"AdaStop: adaptive statistical testing for sound comparisons of Deep RL agents","created":"2023-06-19","cited_by_count":3,"area":null},{"id":"2411.00666","title":"Beyond the Boundaries of Proximal Policy Optimization","created":"2024-11-01","cited_by_count":3,"area":"deeprl"},{"id":"2508.08550","title":"Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference Optimization","created":"2025-08-12","cited_by_count":3,"area":"alignment"}],"next_cursor":"100"}