{"total":103,"rows":[{"id":"2504.16084","title":"TTRL: Test-Time Reinforcement Learning","created":"2025-04-22","cited_by_count":275,"area":"lr"},{"id":"2410.20290","title":"Fast Best-of-N Decoding via Speculative Rejection","created":"2024-10-26","cited_by_count":112,"area":null},{"id":"2503.21878","title":"Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment","created":"2025-03-27","cited_by_count":97,"area":"alignment"},{"id":"2501.05803","title":"Test-time Alignment of Diffusion Models without Reward Over-optimization","created":"2025-01-10","cited_by_count":93,"area":"diffusion"},{"id":"2501.09685","title":"Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Review","created":"2025-01-16","cited_by_count":88,"area":"diffusion"},{"id":"2406.05954","title":"Aligning Large Language Models with Representation Editing: A Control Perspective","created":"2024-06-10","cited_by_count":64,"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":"2410.04070","title":"PAD: Personalized Alignment of LLMs at Decoding-Time","created":"2024-10-05","cited_by_count":60,"area":"alignment"},{"id":"2410.06625","title":"ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time","created":"2024-10-09","cited_by_count":60,"area":"mllm"},{"id":"2402.06147","title":"DeAL: Decoding-time Alignment for Large Language Models","created":"2024-02-05","cited_by_count":55,"area":"alignment"},{"id":"2410.08193","title":"GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment","created":"2024-10-10","cited_by_count":54,"area":"alignment"},{"id":"2411.18688","title":"Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment","created":"2024-11-27","cited_by_count":44,"area":"lr"},{"id":"2503.17003","title":"A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications","created":"2025-03-21","cited_by_count":42,"area":"alignment"},{"id":"2501.12895","title":"Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback","created":"2025-01-22","cited_by_count":41,"area":"alignment"},{"id":"2503.18942","title":"Video-T1: Test-Time Scaling for Video Generation","created":"2025-03-24","cited_by_count":40,"area":"lr"},{"id":"2406.16306","title":"Cascade Reward Sampling for Efficient Decoding-Time Alignment","created":"2024-06-24","cited_by_count":39,"area":"alignment"},{"id":"2502.12668","title":"Evaluation of Best-of-N Sampling Strategies for Language Model Alignment","created":"2025-02-18","cited_by_count":39,"area":"alignment"},{"id":"2502.09457","title":"A Survey of Multilingual Reasoning in Language Models","created":"2025-02-13","cited_by_count":33,"area":"lr"},{"id":"2503.06358","title":"Language Model Personalization via Reward Factorization","created":"2025-03-08","cited_by_count":31,"area":"alignment"},{"id":"2505.13031","title":"MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO","created":"2025-05-19","cited_by_count":30,"area":"lr"},{"id":"2504.07070","title":"A Survey on Personalized and Pluralistic Preference Alignment in Large Language Models","created":"2025-04-09","cited_by_count":27,"area":"alignment"},{"id":"2509.10147","title":"Virtual Agent Economies","created":"2025-09-12","cited_by_count":21,"area":null},{"id":"2510.11686","title":"Representation-Based Exploration for Language Models: From Test-Time to Post-Training","created":"2025-10-13","cited_by_count":16,"area":null},{"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":"2502.10762","title":"Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation","created":"2025-02-15","cited_by_count":14,"area":null},{"id":"2411.08733","title":"Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models","created":"2024-11-13","cited_by_count":13,"area":"alignment"},{"id":"2502.14289","title":"Drift: Decoding-time Personalized Alignments with Implicit User Preferences","created":"2025-02-20","cited_by_count":13,"area":"alignment"},{"id":"2505.20640","title":"IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarios","created":"2025-05-27","cited_by_count":13,"area":"lr"},{"id":"2505.20925","title":"Multi-objective Large Language Model Alignment with Hierarchical Experts","created":"2025-05-27","cited_by_count":13,"area":"alignment"},{"id":"2603.22117","title":"On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation","created":"2026-03-23","cited_by_count":13,"area":"lr"},{"id":"2511.17938","title":"SPINE: Token-Selective Test-Time Reinforcement Learning with Entropy-Band Regularization","created":"2025-11-22","cited_by_count":12,"area":"lr"},{"id":"2504.12663","title":"Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgment","created":"2025-04-17","cited_by_count":11,"area":"alignment"},{"id":"2507.07375","title":"Bradley-Terry and Multi-Objective Reward Modeling Are Complementary","created":"2025-07-10","cited_by_count":11,"area":"alignment"},{"id":"2408.10668","title":"Probing the Safety Response Boundary of Large Language Models via Unsafe Decoding Path Generation","created":"2024-08-20","cited_by_count":10,"area":"safety"},{"id":"2411.08302","title":"RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution","created":"2024-11-13","cited_by_count":10,"area":"alignment"},{"id":"2503.14495","title":"Temporal Consistency for LLM Reasoning Process Error Identification","created":"2025-03-18","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":"2505.12050","title":"AdaBoN: Adaptive Best-of-N Alignment","created":"2025-05-17","cited_by_count":9,"area":"alignment"},{"id":"2505.23729","title":"Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time","created":"2025-05-29","cited_by_count":9,"area":"alignment"},{"id":"2506.12446","title":"From Outcomes to Processes: Guiding PRM Learning from ORM for Inference-Time Alignment","created":"2025-06-14","cited_by_count":9,"area":"alignment"},{"id":"2604.19018","title":"Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control","created":"2026-04-21","cited_by_count":9,"area":"alignment"},{"id":"2510.05040","title":"Test-Time Scaling in Diffusion LLMs via Hidden Semi-Autoregressive Experts","created":"2025-10-06","cited_by_count":8,"area":"lr"},{"id":"2410.11584","title":"DeformPAM: Data-Efficient Learning for Long-horizon Deformable Object Manipulation via Preference-based Action Alignment","created":"2024-10-15","cited_by_count":7,"area":"alignment"},{"id":"2506.07434","title":"Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding","created":"2025-06-09","cited_by_count":7,"area":"alignment"},{"id":"2507.13158","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","created":"2025-07-17","cited_by_count":7,"area":"alignment"},{"id":"2509.24696","title":"T-POP: Test-Time Personalization with Online Preference Feedback","created":"2025-09-29","cited_by_count":7,"area":"alignment"},{"id":"2505.23829","title":"BiasFilter: An Inference-Time Debiasing Framework for Large Language Models","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2506.00166","title":"Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment","created":"2025-05-30","cited_by_count":6,"area":"alignment"},{"id":"2506.16502","title":"Relic: Enhancing Reward Model Generalization for Low-Resource Indic Languages with Few-Shot Examples","created":"2025-06-19","cited_by_count":6,"area":"alignment"},{"id":"2506.17124","title":"When Can Model-Free Reinforcement Learning be Enough for Thinking?","created":"2025-06-20","cited_by_count":6,"area":"lr"},{"id":"2509.06982","title":"CARE: Decoding Time Safety Alignment via Rollback and Introspection Intervention","created":"2025-09-01","cited_by_count":6,"area":"alignment"},{"id":"2510.01167","title":"Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards","created":"2025-10-01","cited_by_count":6,"area":"alignment"},{"id":"2511.02966","title":"Inference-Time Personalized Alignment with a Few User Preference Queries","created":"2025-11-04","cited_by_count":6,"area":null},{"id":"2410.14184","title":"MetaAlign: Align Large Language Models with Diverse Preferences during Inference Time","created":"2024-10-18","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":"2506.09085","title":"LLM-ML Teaming: Integrated Symbolic Decoding and Gradient Search for Valid and Stable Generative Feature Transformation","created":"2025-06-10","cited_by_count":5,"area":null},{"id":"2601.02535","title":"ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation","created":"2026-01-05","cited_by_count":5,"area":null},{"id":"2603.04948","title":"$\\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space","created":"2026-03-05","cited_by_count":5,"area":"lr"},{"id":"2406.03642","title":"Is Free Self-Alignment Possible?","created":"2024-06-05","cited_by_count":4,"area":"alignment"},{"id":"2412.13471","title":"Gradual Vigilance and Interval Communication: Enhancing Value Alignment in Multi-Agent Debates","created":"2024-12-18","cited_by_count":4,"area":"agents"},{"id":"2505.12669","title":"Text2midi-InferAlign: Improving Symbolic Music Generation with Inference-Time Alignment","created":"2025-05-19","cited_by_count":4,"area":null},{"id":"2508.15044","title":"Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner","created":"2025-08-20","cited_by_count":4,"area":"alignment"},{"id":"2604.12479","title":"Meet Dynamic Individual Preferences: Resolving Conflicting Human Value with Paired Fine-Tuning","created":"2026-04-14","cited_by_count":4,"area":"alignment"},{"id":"2605.21851","title":"OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning","created":"2026-05-21","cited_by_count":4,"area":"lr"},{"id":"2503.02368","title":"Evolutionary Guided Decoding: Iterative Value Refinement for LLMs","created":"2025-03-04","cited_by_count":3,"area":null},{"id":"2512.23067","title":"The Reward Model Selection Crisis in Personalized Alignment","created":"2025-12-28","cited_by_count":3,"area":"alignment"},{"id":"2606.04775","title":"Activation Steering of Video Generation Models via Reduced-Order Linear Optimal Control","created":"2026-06-03","cited_by_count":3,"area":"mechinterp"},{"id":"2606.08454","title":"Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior","created":"2026-06-07","cited_by_count":3,"area":"mechinterp"},{"id":"2502.17173","title":"Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch","created":"2025-02-24","cited_by_count":2,"area":"alignment"},{"id":"2502.20795","title":"Test-Time Alignment for Large Language Models via Textual Model Predictive Control","created":"2025-02-28","cited_by_count":2,"area":"alignment"},{"id":"2503.03122","title":"The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models","created":"2025-03-05","cited_by_count":2,"area":"alignment"},{"id":"2504.06659","title":"Leveraging Machine Unlearning for Cost-Efficient Preference Alignment","created":"2025-04-09","cited_by_count":2,"area":"alignment"},{"id":"2508.09016","title":"A Survey on Training-free Alignment of Large Language Models","created":"2025-08-12","cited_by_count":2,"area":"alignment"},{"id":"2508.11616","title":"Controlling Multimodal LLMs via Reward-guided Decoding","created":"2025-08-15","cited_by_count":2,"area":"mllm"},{"id":"2602.02572","title":"Reward Shaping for (Inference-Time) Alignment: A Stackelberg Game Perspective","created":"2026-01-31","cited_by_count":2,"area":"alignment"},{"id":"2405.13984","title":"Less for More: Enhanced Feedback-aligned Mixed LLMs for Molecule Caption Generation and Fine-Grained NLI Evaluation","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2410.21027","title":"Transferable Post-training via Inverse Value Learning","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2505.13257","title":"Is Active Persona Inference Necessary for Aligning Small Models to Personal Preferences?","created":"2025-05-19","cited_by_count":1,"area":"alignment"},{"id":"2506.17828","title":"Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach","created":"2025-06-21","cited_by_count":1,"area":"alignment"},{"id":"2510.23334","title":"Adaptive Blockwise Search: Inference-Time Alignment for Large Language Models","created":"2025-10-27","cited_by_count":1,"area":"alignment"},{"id":"2510.27017","title":"Kad: A Framework for Proxy-based Test-time Alignment with Knapsack Approximation Deferral","created":"2025-10-30","cited_by_count":1,"area":null},{"id":"2601.10416","title":"LLMdoctor: Token-Level Flow-Guided Preference Optimization for Efficient Test-Time Alignment of Large Language Models","created":"2026-01-15","cited_by_count":1,"area":"alignment"},{"id":"2603.18411","title":"TARo: Token-level Adaptive Routing for LLM Test-time Alignment","created":"2026-03-19","cited_by_count":1,"area":"lr"},{"id":"2605.20408","title":"Spectral Souping: A Unified Framework for Online Preference Alignment","created":"2026-05-19","cited_by_count":1,"area":"alignment"},{"id":"2607.02781","title":"Safe Inference-Time Alignment via Lagrangian Reward Augmentation","created":"2026-07-02","cited_by_count":1,"area":"alignment"},{"id":"2607.27912","title":"IFHierBench: Hierarchical Instruction Following for Large Language Models","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2408.10764","title":"Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model","created":"2024-08-20","cited_by_count":0,"area":null},{"id":"2505.09082","title":"CEC-Zero: Chinese Error Correction Solution Based on LLM","created":"2025-05-14","cited_by_count":0,"area":null},{"id":"2511.21762","title":"Factors That Support Grounded Responses in LLM Conversations: A Rapid Review","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2604.16146","title":"On the Rejection Criterion for Proxy-based Test-time Alignment","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2604.23543","title":"Pref-CTRL: Preference Driven LLM Alignment using Representation Editing","created":"2026-04-26","cited_by_count":0,"area":"alignment"},{"id":"2605.10843","title":"Training-Free Cultural Alignment of Large Language Models via Persona Disagreement","created":"2026-05-11","cited_by_count":0,"area":"alignment"},{"id":"2607.03453","title":"Best-of-Better-$N$: Generating Pre-Aligned Responses with In-Context Learning","created":"2026-07-03","cited_by_count":0,"area":"alignment"},{"id":"2608.30395","title":"When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2609.00624","title":"Trust Your Guide Only When Certain: Uncertainty-Aware Sparse Alignment at Inference Time","created":"2026-09-01","cited_by_count":0,"area":"alignment"},{"id":"2609.08082","title":"Inference-Time Nash Alignment","created":"2026-09-08","cited_by_count":0,"area":"alignment"},{"id":"2609.21231","title":"Beyond Reference-Based Evaluation: Reward Models for Meta-Evaluation of Grammatical Error Correction","created":"2026-09-18","cited_by_count":0,"area":"alignment"},{"id":"2609.30218","title":"Minimally Invasive Steering of Language Models","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.35695","title":"Rethinking Personalized Generation: Test-Time Alignment via Factorized Ranking Models","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2609.37041","title":"Beam Search as Test-Time Self-Distillation via Counterfactual Contexts","created":"2026-09-29","cited_by_count":0,"area":"distill"}],"next_cursor":"100"}