{"total":142,"rows":[{"id":"2505.02833","title":"TWIST: Teleoperated Whole-Body Imitation System","created":"2025-05-05","cited_by_count":101,"area":null},{"id":"2510.18874","title":"Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting","created":"2025-10-21","cited_by_count":94,"area":null},{"id":"2510.08558","title":"Agent Learning via Early Experience","created":"2025-10-09","cited_by_count":85,"area":null},{"id":"2507.05386","title":"Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training","created":"2025-07-07","cited_by_count":47,"area":null},{"id":"2509.22799","title":"VideoScore2: Think before You Score in Generative Video Evaluation","created":"2025-09-26","cited_by_count":40,"area":null},{"id":"2507.14632","title":"BusterX++: Towards Unified Cross-Modal AI-Generated Content Detection and Explanation with MLLM","created":"2025-07-19","cited_by_count":29,"area":null},{"id":"2509.25760","title":"TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning","created":"2025-09-30","cited_by_count":27,"area":null},{"id":"2505.15456","title":"Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment","created":"2025-05-21","cited_by_count":24,"area":null},{"id":"2509.20758","title":"SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs","created":"2025-09-25","cited_by_count":24,"area":null},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"id":"2509.14234","title":"Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision","created":"2025-09-17","cited_by_count":18,"area":null},{"id":"2510.00526","title":"Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum","created":"2025-10-01","cited_by_count":18,"area":null},{"id":"2510.14807","title":"Beyond the Sampled Token: Preserving Candidate Support in RLVR","created":"2025-10-16","cited_by_count":18,"area":null},{"id":"2601.09195","title":"ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection","created":"2026-01-14","cited_by_count":18,"area":null},{"id":"2510.11696","title":"QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2601.02151","title":"Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting","created":"2026-01-05","cited_by_count":16,"area":null},{"id":"2509.21519","title":"Provable Scaling Laws of Feature Emergence from Learning Dynamics of Grokking","created":"2025-09-25","cited_by_count":15,"area":null},{"id":"2509.23753","title":"Anchored Supervised Fine-Tuning","created":"2025-09-28","cited_by_count":15,"area":null},{"id":"2511.20351","title":"Thinking in 360{\\deg}: Humanoid Visual Search in the Wild","created":"2025-11-25","cited_by_count":15,"area":null},{"id":"2604.07666","title":"An Imperfect Verifier is Good Enough: Learning with Noisy Rewards","created":"2026-04-09","cited_by_count":13,"area":null},{"id":"2506.13045","title":"Continual Learning for Generative AI: From LLMs to MLLMs and Beyond","created":"2025-06-16","cited_by_count":12,"area":null},{"id":"2505.23179","title":"DIP-R1: Deep Inspection and Perception with RL Looking Through and Understanding Complex Scenes","created":"2025-05-29","cited_by_count":11,"area":null},{"id":"2507.04642","title":"R1-RE: Cross-Domain Relation Extraction with RLVR","created":"2025-07-07","cited_by_count":11,"area":null},{"id":"2602.12222","title":"Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training","created":"2026-02-12","cited_by_count":11,"area":null},{"id":"2604.10701","title":"Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning","created":"2026-04-12","cited_by_count":11,"area":null},{"id":"2509.21826","title":"ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models","created":"2025-09-26","cited_by_count":10,"area":null},{"id":"2511.12596","title":"Group-Aware Reinforcement Learning for Output Diversity in Large Language Models","created":"2025-11-16","cited_by_count":10,"area":null},{"id":"2505.11614","title":"Using Reinforcement Learning to Train Large Language Models to Explain Human Decisions","created":"2025-05-16","cited_by_count":9,"area":null},{"id":"2509.21044","title":"Reinforcement Learning Fine-Tuning Enhances Activation Intensity and Diversity in the Internal Circuitry of LLMs","created":"2025-09-25","cited_by_count":9,"area":null},{"id":"2508.20697","title":"Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning","created":"2025-08-28","cited_by_count":8,"area":null},{"id":"2509.26313","title":"One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2512.01970","title":"Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies","created":"2025-12-01","cited_by_count":8,"area":null},{"id":"2512.03442","title":"PretrainZero: Reinforcement Active Pretraining","created":"2025-12-03","cited_by_count":8,"area":null},{"id":"2602.05910","title":"Chunky Post-Training: Data Driven Failures of Generalization","created":"2026-02-05","cited_by_count":7,"area":null},{"id":"2603.05923","title":"Learning Next Action Predictors from Human-Computer Interaction","created":"2026-03-06","cited_by_count":7,"area":null},{"id":"2504.09389","title":"Measuring LLM Novelty As The Frontier Of Original And High-Quality Output","created":"2025-04-13","cited_by_count":6,"area":null},{"id":"2507.10605","title":"RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services","created":"2025-07-13","cited_by_count":6,"area":null},{"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":"2512.16883","title":"AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning","created":"2025-12-18","cited_by_count":6,"area":null},{"id":"2601.06851","title":"A Brain-like Synergistic Core in LLMs Drives Behaviour and Learning","created":"2026-01-11","cited_by_count":6,"area":null},{"id":"2605.02572","title":"On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length","created":"2026-05-04","cited_by_count":6,"area":null},{"id":"2502.19127","title":"Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization","created":"2025-02-26","cited_by_count":4,"area":null},{"id":"2503.04969","title":"Data-Efficient Learning from Human Interventions for Mobile Robots","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2503.12167","title":"PLM: Efficient Peripheral Language Models Hardware-Co-Designed for Ubiquitous Computing","created":"2025-03-15","cited_by_count":4,"area":null},{"id":"2505.20573","title":"Collision- and Reachability-Aware Multi-Robot Control with Grounded LLM Planners","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2505.23060","title":"Self-Correcting Code Generation Using Small Language Models","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2506.22023","title":"Robust and Efficient Autoregressive Speech Synthesis with Dynamic Chunk-wise Prediction Policy","created":"2025-06-27","cited_by_count":4,"area":null},{"id":"2509.22613","title":"Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2511.05933","title":"Reinforcement Learning Improves Traversal of Parametric Knowledge in LLMs","created":"2025-11-08","cited_by_count":4,"area":null},{"id":"2601.06559","title":"ArrowGEV: Grounding Events in Video via Learning the Arrow of Time","created":"2026-01-10","cited_by_count":4,"area":null},{"id":"2601.11258","title":"Knowledge is Not Enough: Injecting RL Skills for Continual Adaptation","created":"2026-01-16","cited_by_count":4,"area":null},{"id":"2605.14967","title":"InfoSFT: Learn More and Forget Less with Information-Aware Token Weighting","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2605.15156","title":"MeMo: Memory as a Model","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2606.09932","title":"When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff","created":"2026-06-07","cited_by_count":4,"area":null},{"id":"2508.00390","title":"SA-GCS: Semantic-Aware Gaussian Curriculum Scheduling for UAV Vision-Language Navigation","created":"2025-08-01","cited_by_count":3,"area":null},{"id":"2509.17866","title":"Understanding Post-Training Structural Changes in Large Language Models","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2509.23166","title":"Test-Time Policy Adaptation for Enhanced Multi-Turn Interactions with LLMs","created":"2025-09-27","cited_by_count":3,"area":null},{"id":"2509.24923","title":"When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2510.03341","title":"OpusAnimation: Code-Based Dynamic Chart Generation","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2510.16555","title":"Urban-R1: Reinforced MLLMs Mitigate Geospatial Biases for Urban General Intelligence","created":"2025-10-18","cited_by_count":3,"area":null},{"id":"2511.14275","title":"Let the Model Distribute Its Doubt: Confidence Estimation through Verbalized Probability Distribution","created":"2025-11-18","cited_by_count":3,"area":null},{"id":"2512.08875","title":"When Tables Leak: Attacking String Memorization in LLM-Based Tabular Data Generation","created":"2025-12-09","cited_by_count":3,"area":null},{"id":"2603.13985","title":"Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models","created":"2026-03-14","cited_by_count":3,"area":null},{"id":"2607.07674","title":"Max Out GRPO Signal: Adaptive Trace Prefix Control for Hard Reasoning Problems","created":"2026-07-08","cited_by_count":3,"area":null},{"id":"2609.04061","title":"When Models Edit Too Much: On the Fidelity of Minimal Code Edits","created":"2026-09-03","cited_by_count":3,"area":null},{"id":"2507.05266","title":"User Behavior Prediction as a Generic, Robust, Scalable, and Low-Cost Evaluation Strategy for Estimating Generalization in LLMs","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2509.19770","title":"EnAnchored-X2X: English-Anchored Optimization for Many-to-Many Translation","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2509.20321","title":"Conversational Speech Reveals Structural Robustness Failures in SpeechLLM Backbones","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2509.24961","title":"SemanticShield: LLM-Powered Audits Expose Shilling Attacks in Recommender Systems","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2601.18129","title":"Typhoon-S: Minimal Open Post-Training for Sovereign Large Language Models","created":"2026-01-26","cited_by_count":2,"area":null},{"id":"2602.00513","title":"Minerva: Reinforcement Learning with Verifiable Rewards for Cyber Threat Intelligence LLMs","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2603.01993","title":"Cultivating Forensic Reasoning for Generalizable Multimodal Manipulation Detection","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2603.15011","title":"Molecular Identifier Visual Prompt and Verifiable Reinforcement Learning for Chemical Reaction Diagram Parsing","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2605.24432","title":"Found in Conversation: LLMs Teach Themselves to Close the Multi-Turn Gap","created":"2026-05-23","cited_by_count":2,"area":null},{"id":"2607.04332","title":"On the effectiveness of reward functions in reinforcement learning for confidence calibration of large language models","created":"2026-07-05","cited_by_count":2,"area":null},{"id":"2607.07646","title":"RL Post-Training Builds Compositional Reasoning Strategies","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2607.22039","title":"Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs","created":"2026-07-24","cited_by_count":2,"area":null},{"id":"2608.20350","title":"How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel","created":"2026-06-16","cited_by_count":2,"area":null},{"id":"2506.21895","title":"Exploring Task-Solving Paradigm for Generalized Cross-Domain Face Anti-Spoofing via Reinforcement Fine-Tuning","created":"2025-06-27","cited_by_count":1,"area":null},{"id":"2507.06056","title":"Data Compressibility Quantifies LLM Memorization","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2507.12911","title":"LaViPlan : Language-Guided Visual Path Planning with RLVR","created":"2025-07-17","cited_by_count":1,"area":null},{"id":"2509.15927","title":"Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2509.22621","title":"IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2511.07413","title":"DigiData: Training and Evaluating General-Purpose Mobile Control Agents","created":"2025-11-10","cited_by_count":1,"area":null},{"id":"2602.03542","title":"Can Large Language Models Generalize Procedures Across Representations?","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2602.15849","title":"IntelliAsk: Learning to Ask High-Quality Research Questions via RLVR","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2602.16488","title":"Learning to Learn from Language Feedback with Social Meta-Learning","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2603.00938","title":"Seeing Beyond 8bits: Subjective and Objective Quality Assessment of HDR-UGC Videos","created":"2026-03-01","cited_by_count":1,"area":null},{"id":"2604.14258","title":"GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2605.00610","title":"Decouple before Integration: Test-time Synthesis of SFT and RLVR Task Vectors","created":"2026-05-01","cited_by_count":1,"area":null},{"id":"2605.22240","title":"Unlocking Proactivity in Task-Oriented Dialogue","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2605.29303","title":"Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.00251","title":"Capability Self-Assessment in Large Language Models","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.04272","title":"RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.18487","title":"SFT Overtraining Predicts Rank Inversion via Entropy Collapse Under RLVR","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2607.02755","title":"Out-of-Distribution Generalization of Risk Aversion in Language Models","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.21351","title":"How Much Can a LoRA Adapter Memorize? Measuring Adapter Capacity in Bits","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2608.05224","title":"Small Foundation Models of Human Cognition and Behaviour","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2608.08010","title":"Ground-Truth Neighborhood Regularization for Reinforcement Learning Post-Training of Time Series Foundation Models","created":"2026-08-08","cited_by_count":1,"area":null},{"id":"2608.11426","title":"Is Convergence Inevitable? Tracing Output Homogeneity Back to Base Models","created":"2026-08-11","cited_by_count":1,"area":null}],"next_cursor":"100"}