{"total":95,"rows":[{"id":"2504.15895","title":"Dynamic Early Exit in Reasoning Models","created":"2025-04-22","cited_by_count":219,"area":"lr"},{"id":"2504.09037","title":"A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems","created":"2025-04-12","cited_by_count":111,"area":"lr"},{"id":"2505.07686","title":"S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models","created":"2025-05-12","cited_by_count":87,"area":"lr"},{"id":"2407.17387","title":"PERSONA: A Reproducible Testbed for Pluralistic Alignment","created":"2024-07-24","cited_by_count":73,"area":"alignment"},{"id":"2506.08343","title":"Wait, We Don't Need to \"Wait\"! Removing Thinking Tokens Improves Reasoning Efficiency","created":"2025-06-10","cited_by_count":66,"area":"lr"},{"id":"2410.14632","title":"Diverging Preferences: When do Annotators Disagree and do Models Know?","created":"2024-10-18","cited_by_count":47,"area":"alignment"},{"id":"2504.16078","title":"LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities","created":"2025-04-22","cited_by_count":41,"area":"agents"},{"id":"2507.01663","title":"AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training","created":"2025-07-02","cited_by_count":41,"area":null},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2506.09839","title":"OctoNav: Towards Generalist Embodied Navigation","created":"2025-06-11","cited_by_count":34,"area":"lr"},{"id":"2506.20520","title":"Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards","created":"2025-06-25","cited_by_count":29,"area":"lr"},{"id":"2502.12272","title":"Learning to Reason at the Frontier of Learnability","created":"2025-02-17","cited_by_count":23,"area":"lr"},{"id":"2412.20299","title":"No Preference Left Behind: Group Distributional Preference Optimization","created":"2024-12-28","cited_by_count":21,"area":"alignment"},{"id":"2502.01930","title":"Robust LLM Alignment via Distributionally Robust Direct Preference Optimization","created":"2025-02-04","cited_by_count":18,"area":"alignment"},{"id":"2409.02795","title":"Towards a Unified View of Preference Learning for Large Language Models: A Survey","created":"2024-09-04","cited_by_count":17,"area":"alignment"},{"id":"2505.11827","title":"Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning","created":"2025-05-17","cited_by_count":16,"area":"lr"},{"id":"2502.01208","title":"On Almost Surely Safe Alignment of Large Language Models at Inference-Time","created":"2025-02-03","cited_by_count":14,"area":"alignment"},{"id":"2407.18676","title":"Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift","created":"2024-07-26","cited_by_count":13,"area":"alignment"},{"id":"2504.03784","title":"Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuning","created":"2025-04-03","cited_by_count":13,"area":"alignment"},{"id":"2601.21919","title":"Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning","created":"2026-01-29","cited_by_count":13,"area":"lr"},{"id":"2412.15538","title":"FedRLHF: A Convergence-Guaranteed Federated Framework for Privacy-Preserving and Personalized RLHF","created":"2024-12-20","cited_by_count":12,"area":"alignment"},{"id":"2503.00539","title":"Distributionally Robust Reinforcement Learning with Human Feedback","created":"2025-03-01","cited_by_count":12,"area":"alignment"},{"id":"2511.20766","title":"OpenApps: Simulating Environment Variations to Measure UI-Agent Reliability","created":"2025-11-25","cited_by_count":12,"area":null},{"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":"2412.19436","title":"Low-Rank Contextual Reinforcement Learning from Heterogeneous Human Feedback","created":"2024-12-27","cited_by_count":10,"area":"alignment"},{"id":"2507.00711","title":"Large Reasoning Models are not thinking straight: on the unreliability of thinking trajectories","created":"2025-07-01","cited_by_count":10,"area":"lr"},{"id":"2503.08796","title":"Robust Multi-Objective Controlled Decoding of Large Language Models","created":"2025-03-11","cited_by_count":9,"area":null},{"id":"2511.19413","title":"UniGame: Turning a Unified Multimodal Model Into Its Own Adversary","created":"2025-11-24","cited_by_count":9,"area":null},{"id":"2502.13173","title":"Thinking Preference Optimization","created":"2025-02-17","cited_by_count":8,"area":"lr"},{"id":"2505.00003","title":"A Review of Incorporating Psychological Theories in LLMs","created":"2025-03-28","cited_by_count":6,"area":null},{"id":"2410.01957","title":"Challenges and Future Directions of Data-Centric AI Alignment","created":"2024-10-02","cited_by_count":5,"area":"alignment"},{"id":"2503.09561","title":"Strategyproof Reinforcement Learning from Human Feedback","created":"2025-03-12","cited_by_count":5,"area":"alignment"},{"id":"2509.05381","title":"Murphys Laws of AI Alignment: Why the Gap Always Wins","created":"2025-09-04","cited_by_count":5,"area":"alignment"},{"id":"2512.23430","title":"C2PO: Diagnosing and Disentangling Bias Shortcuts in LLMs","created":"2025-12-29","cited_by_count":5,"area":null},{"id":"2601.19001","title":"FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning","created":"2026-01-26","cited_by_count":5,"area":null},{"id":"2602.01365","title":"When Domains Interact: Asymmetric and Order-Sensitive Cross-Domain Effects in Reinforcement Learning for Reasoning","created":"2026-02-01","cited_by_count":5,"area":"lr"},{"id":"2602.02033","title":"One Size, Many Fits: Aligning Diverse Group-Wise Click Preferences in Large-Scale Advertising Image Generation","created":"2026-02-02","cited_by_count":5,"area":"alignment"},{"id":"2503.19201","title":"A Shared Low-Rank Adaptation Approach to Personalized RLHF","created":"2025-03-24","cited_by_count":4,"area":"alignment"},{"id":"2505.11861","title":"Fair-PP: A Synthetic Dataset for Aligning LLM with Personalized Preferences of Social Equity","created":"2025-05-17","cited_by_count":4,"area":"alignment"},{"id":"2505.17859","title":"Scalable Valuation of Human Feedback through Provably Robust Model Alignment","created":"2025-05-23","cited_by_count":4,"area":"alignment"},{"id":"2506.05619","title":"Beyond RLHF and NLHF: Population-Proportional Alignment under an Axiomatic Framework","created":"2025-06-05","cited_by_count":4,"area":"alignment"},{"id":"2507.03051","title":"Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy Optimization","created":"2025-07-03","cited_by_count":4,"area":"lr"},{"id":"2508.11086","title":"Relative Advantage Debiasing for Watch-Time Prediction in Short-Video Recommendation","created":"2025-08-14","cited_by_count":4,"area":null},{"id":"2511.10648","title":"Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling","created":"2025-11-13","cited_by_count":4,"area":"lr"},{"id":"2410.20856","title":"Strada-LLM: Graph LLM for traffic prediction","created":"2024-10-28","cited_by_count":3,"area":null},{"id":"2507.09955","title":"DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models","created":"2025-07-14","cited_by_count":3,"area":"moe"},{"id":"2507.16679","title":"PICACO: Pluralistic In-Context Value Alignment of LLMs via Total Correlation Optimization","created":"2025-07-22","cited_by_count":3,"area":"alignment"},{"id":"2512.00709","title":"When Human Preferences Flip: An Instance-Dependent Robust Loss for RLHF","created":"2025-11-30","cited_by_count":3,"area":"alignment"},{"id":"2512.08786","title":"A Systematic Evaluation of Preference Aggregation in Federated RLHF for Pluralistic Alignment of LLMs","created":"2025-12-09","cited_by_count":3,"area":"alignment"},{"id":"2512.11844","title":"Love First, Know Later: Persona-Based Romantic Compatibility Through LLM Text World Engines","created":"2025-12-04","cited_by_count":3,"area":null},{"id":"2604.08243","title":"Self-Debias: Self-correcting for Debiasing Large Language Models","created":"2026-04-09","cited_by_count":3,"area":"lr"},{"id":"2503.08035","title":"Group Preference Alignment: Customized LLM Response Generation from In-Situ Conversations","created":"2025-03-11","cited_by_count":2,"area":"alignment"},{"id":"2504.05831","title":"Leveraging Robust Optimization for LLM Alignment under Distribution Shifts","created":"2025-04-08","cited_by_count":2,"area":"alignment"},{"id":"2504.09488","title":"Kongzi: A Historical Large Language Model with Fact Enhancement","created":"2025-04-13","cited_by_count":2,"area":null},{"id":"2505.15212","title":"Group Distributionally Robust Optimization with Flexible Sample Queries","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2505.18630","title":"DDO: Dual-Decision Optimization for LLM-Based Medical Consultation via Multi-Agent Collaboration","created":"2025-05-24","cited_by_count":2,"area":"lr"},{"id":"2505.20359","title":"Risk-aware Direct Preference Optimization under Nested Risk Measure","created":"2025-05-26","cited_by_count":2,"area":"alignment"},{"id":"2508.07970","title":"WeChat-YATT: A Scalable, Simple, Efficient, and Production Ready Training Library","created":"2025-08-11","cited_by_count":2,"area":"alignment"},{"id":"2509.03672","title":"SharedRep-RLHF: A Shared Representation Approach to RLHF with Diverse Preferences","created":"2025-09-03","cited_by_count":2,"area":"alignment"},{"id":"2510.07790","title":"GCPO: When Contrast Fails, Go Gold","created":"2025-10-09","cited_by_count":2,"area":"lr"},{"id":"2510.14620","title":"Code-driven Number Sequence Calculation: Enhancing the inductive Reasoning Abilities of Large Language Models","created":"2025-10-16","cited_by_count":2,"area":"lr"},{"id":"2601.18730","title":"Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale","created":"2026-01-26","cited_by_count":2,"area":"lr"},{"id":"2602.00886","title":"RoDiF: Robust Direct Fine-Tuning of Diffusion Policies with Corrupted Human Feedback","created":"2026-01-31","cited_by_count":2,"area":"diffusion"},{"id":"2603.17305","title":"Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2506.06215","title":"Corrector Sampling in Language Models","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2508.07126","title":"Pref-GUIDE: Continual Policy Learning from Real-Time Human Feedback via Preference-Based Learning","created":"2025-08-10","cited_by_count":1,"area":"alignment"},{"id":"2509.25966","title":"MUVLA: Learning to Explore Object Navigation via Map Understanding","created":"2025-09-30","cited_by_count":1,"area":"vla"},{"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":"2601.12091","title":"Mitigating Cultural Bias in LLMs via Multi-Agent Cultural Debate","created":"2026-01-17","cited_by_count":1,"area":"agents"},{"id":"2601.16419","title":"Learning Domain Knowledge in Multimodal Large Language Models through Reinforcement Fine-Tuning","created":"2026-01-23","cited_by_count":1,"area":"mllm"},{"id":"2602.20457","title":"Oracle-Robust Online Alignment for Large Language Models","created":"2026-02-24","cited_by_count":1,"area":"alignment"},{"id":"2604.00200","title":"Offline Constrained RLHF with Multiple Preference Oracles","created":"2026-03-31","cited_by_count":1,"area":"alignment"},{"id":"2604.04261","title":"APPA: Adaptive Preference Pluralistic Alignment for Fair Federated RLHF of LLMs","created":"2026-04-05","cited_by_count":1,"area":"alignment"},{"id":"2604.17299","title":"Cat-DPO: Category-Adaptive Safety Alignment","created":"2026-04-19","cited_by_count":1,"area":"alignment"},{"id":"2605.12138","title":"Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.26442","title":"Alignment Tuning for Large Language Models: A Data-Centric Lens on Alignment Data Pipelines","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2606.18606","title":"Steerable Cultural Preference Optimization of Reward Models","created":"2026-06-17","cited_by_count":1,"area":"alignment"},{"id":"2505.02433","title":"FairPO: Robust Preference Optimization for Fair Multi-Label Learning","created":"2025-05-05","cited_by_count":0,"area":"alignment"},{"id":"2507.03487","title":"ObjectRL: An Object-Oriented Reinforcement Learning Codebase","created":"2025-07-04","cited_by_count":0,"area":"deeprl"},{"id":"2507.07855","title":"DPO Unchained: Your Training Algorithm is Secretly Disentangled in Human Choice Theory (and its Loss' Convexity is Dispensable)","created":"2025-07-10","cited_by_count":0,"area":"alignment"},{"id":"2510.21345","title":"$\\alpha$-LoRA: Effective Fine-Tuning via Base Model Rescaling","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2510.26301","title":"Offline Clustering of Preference Learning with Active-data Augmentation","created":"2025-10-30","cited_by_count":0,"area":"alignment"},{"id":"2511.05286","title":"Reflective Personalization Optimization: A Post-hoc Rewriting Framework for Black-Box Large Language Models","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2512.24263","title":"Constrained Language Model Policy Optimization via Risk-aware Stepwise Alignment","created":"2025-12-30","cited_by_count":0,"area":"alignment"},{"id":"2602.00485","title":"Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models","created":"2026-01-31","cited_by_count":0,"area":"mllm"},{"id":"2602.19041","title":"Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2603.08145","title":"DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding","created":"2026-03-09","cited_by_count":0,"area":"alignment"},{"id":"2604.08577","title":"Distributionally Robust Token Optimization in RLHF","created":"2026-03-27","cited_by_count":0,"area":"alignment"},{"id":"2604.25895","title":"Three Models of RLHF Annotation: Extension, Evidence, and Authority","created":"2026-04-28","cited_by_count":0,"area":"alignment"},{"id":"2605.03426","title":"Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models","created":"2026-05-05","cited_by_count":0,"area":"mllm"},{"id":"2606.07988","title":"PAFO: Pareto Fairness Optimization for Personalized Reward Modeling","created":"2026-06-06","cited_by_count":0,"area":"alignment"},{"id":"2607.08572","title":"Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learning","created":"2026-07-09","cited_by_count":0,"area":"lr"},{"id":"2608.11528","title":"Group Alignment-Induced Sycophancy: A Two-Sided Evaluation of Steerable Pluralistic Alignment","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.27910","title":"AI Alignment through a Game-theoretic Lens: A Survey","created":"2026-08-28","cited_by_count":0,"area":"alignment"},{"id":"2610.05450","title":"Groupwise Distortion Guarantees for Preference-Based Alignment","created":"2026-10-04","cited_by_count":0,"area":"alignment"}],"next_cursor":null}