{"total":127,"rows":[{"id":"2601.19897","title":"Self-Distillation Enables Continual Learning","created":"2026-01-27","cited_by_count":247,"area":"offlinerl"},{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2508.11408","title":"On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting","created":"2025-08-15","cited_by_count":91,"area":"lr"},{"id":"2510.10689","title":"OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs","created":"2025-10-12","cited_by_count":59,"area":"lr"},{"id":"2511.10643","title":"Black-Box On-Policy Distillation of Large Language Models","created":"2025-11-13","cited_by_count":59,"area":"distill"},{"id":"2509.03516","title":"Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?","created":"2025-09-03","cited_by_count":34,"area":null},{"id":"2510.00553","title":"On Predictability of Reinforcement Learning Dynamics for Large Language Models","created":"2025-10-01","cited_by_count":23,"area":"lr"},{"id":"2510.10974","title":"Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning","created":"2025-10-13","cited_by_count":20,"area":"lr"},{"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":"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":"2508.17784","title":"Proximal Supervised Fine-Tuning","created":"2025-08-25","cited_by_count":16,"area":"lr"},{"id":"2510.04454","title":"Mitigating Forgetting Between Supervised and Reinforcement Learning Yields Stronger Reasoners","created":"2025-10-06","cited_by_count":16,"area":"lr"},{"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":"2509.23753","title":"Anchored Supervised Fine-Tuning","created":"2025-09-28","cited_by_count":15,"area":null},{"id":"2509.24203","title":"Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends","created":"2025-09-29","cited_by_count":15,"area":"lr"},{"id":"2511.14159","title":"MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs","created":"2025-11-18","cited_by_count":15,"area":"mllm"},{"id":"2601.14249","title":"Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment","created":"2026-01-20","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":"2509.22601","title":"Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning","created":"2025-09-26","cited_by_count":11,"area":"agents"},{"id":"2510.02295","title":"VideoNSA: Native Sparse Attention Scales Video Understanding","created":"2025-10-02","cited_by_count":11,"area":"mllm"},{"id":"2602.01058","title":"Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning","created":"2026-02-01","cited_by_count":11,"area":"lr"},{"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":"2510.01539","title":"Executable Counterfactuals: Improving LLMs' Causal Reasoning Through Code","created":"2025-10-02","cited_by_count":10,"area":"lr"},{"id":"2510.08131","title":"Real-Time Motion-Controllable Autoregressive Video Diffusion","created":"2025-10-09","cited_by_count":9,"area":"diffusion"},{"id":"2602.01745","title":"Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning","created":"2026-02-02","cited_by_count":9,"area":null},{"id":"2602.02244","title":"Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models","created":"2026-02-02","cited_by_count":9,"area":"lr"},{"id":"2509.22637","title":"Variational Reasoning for Language Models","created":"2025-09-26","cited_by_count":8,"area":"lr"},{"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":"2510.00237","title":"Debunk the Myth of SFT Generalization","created":"2025-09-30","cited_by_count":8,"area":"lr"},{"id":"2510.16720","title":"Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI","created":"2025-10-19","cited_by_count":8,"area":"agents"},{"id":"2511.06221","title":"Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B","created":"2025-11-09","cited_by_count":8,"area":"lr"},{"id":"2603.02216","title":"ATPO: Adaptive Tree Policy Optimization for Multi-Turn Medical Dialogue","created":"2026-02-10","cited_by_count":8,"area":null},{"id":"2604.07765","title":"RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMs","created":"2026-04-09","cited_by_count":8,"area":"agents"},{"id":"2607.17247","title":"Distilled Reinforcement Learning for LLM Post-training","created":"2026-07-19","cited_by_count":8,"area":"distill"},{"id":"2509.25604","title":"RFG: Test-Time Scaling for Diffusion Large Language Model Reasoning with Reward-Free Guidance","created":"2025-09-29","cited_by_count":7,"area":"lr"},{"id":"2602.07464","title":"SED-SFT: Selectively Encouraging Diversity in Supervised Fine-Tuning","created":"2026-02-07","cited_by_count":7,"area":null},{"id":"2602.24041","title":"Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigation","created":"2026-02-27","cited_by_count":7,"area":"mllm"},{"id":"2603.14389","title":"From $\\log \\pi$ to $\\pi$: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight","created":"2026-03-15","cited_by_count":6,"area":"lr"},{"id":"2604.07941","title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","created":"2026-04-09","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":"2510.15990","title":"Can GRPO Help LLMs Transcend Their Pretraining Origin?","created":"2025-10-14","cited_by_count":5,"area":"lr"},{"id":"2510.25801","title":"Metis-SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start","created":"2025-10-29","cited_by_count":5,"area":"mllm"},{"id":"2510.26697","title":"The End of Manual Decoding: Towards Truly End-to-End Language Models","created":"2025-10-30","cited_by_count":5,"area":null},{"id":"2601.22905","title":"FlexLoRA: Entropy-Guided Flexible Low-Rank Adaptation","created":"2026-01-30","cited_by_count":5,"area":null},{"id":"2509.20863","title":"GIFT: Guided Importance-Aware Fine-Tuning for Diffusion Language Models","created":"2025-09-25","cited_by_count":4,"area":"diffusion"},{"id":"2602.13407","title":"On-Policy Supervised Fine-Tuning for Efficient Reasoning","created":"2026-02-13","cited_by_count":4,"area":"lr"},{"id":"2604.01597","title":"Learning from the Right Rollouts: Data Attribution for PPO-based LLM Post-Training","created":"2026-04-02","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":"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":"2607.10601","title":"Agentic-DPO: From Imitation to Agentic Policy Optimization on Expert Trajectories","created":"2026-07-12","cited_by_count":4,"area":"agents"},{"id":"2508.11281","title":"ToxiFrench: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection","created":"2025-08-15","cited_by_count":3,"area":null},{"id":"2511.09222","title":"Toward Honest Language Models for Deductive Reasoning","created":"2025-11-12","cited_by_count":3,"area":"lr"},{"id":"2511.16602","title":"Bridging VLMs and Embodied Intelligence with Deliberate Practice Policy Optimization","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2511.21075","title":"Aligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning","created":"2025-11-26","cited_by_count":3,"area":null},{"id":"2601.09253","title":"RIFT: Repurposing Negative Samples via Reward-Informed Fine-Tuning","created":"2026-01-14","cited_by_count":3,"area":"alignment"},{"id":"2602.01532","title":"PRISM: Festina Lente Proactivity -- Risk-Sensitive, Uncertainty-Aware Deliberation for Proactive Agents","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2602.11424","title":"Gradients Must Earn Their Influence: Unifying SFT with Generalized Entropic Objectives","created":"2026-02-11","cited_by_count":3,"area":null},{"id":"2602.18799","title":"Rethinking Preference Alignment for Diffusion Models with Classifier-Free Guidance","created":"2026-02-21","cited_by_count":3,"area":"diffusion"},{"id":"2603.01683","title":"Surgical Post-Training: Proximal On-Policy Distillation for Reasoning with Knowledge Retention","created":"2026-03-02","cited_by_count":3,"area":"lr"},{"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":"2605.00015","title":"TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuning","created":"2026-04-18","cited_by_count":3,"area":null},{"id":"2605.10973","title":"Rotation-Preserving Supervised Fine-Tuning","created":"2026-05-08","cited_by_count":3,"area":null},{"id":"2606.01279","title":"ANDES: Agent Native Data Evolving Synthesis Tool for Autonomous Instruction Alignment","created":"2026-05-31","cited_by_count":3,"area":"agents"},{"id":"2510.18383","title":"MENTOR: Reinforcement Learning via Flexible Teacher-Optimized Rewards for Tool-Use Distillation","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2510.20519","title":"Metis-HOME: Hybrid Optimized Mixture-of-Experts for Multimodal Reasoning","created":"2025-10-23","cited_by_count":2,"area":"lr"},{"id":"2511.10254","title":"Facial-R1: Aligning Reasoning and Recognition for Facial Emotion Analysis","created":"2025-11-13","cited_by_count":2,"area":"lr"},{"id":"2602.06033","title":"Can Vision Language Models Learn Intuitive Physics from Interaction?","created":"2026-02-05","cited_by_count":2,"area":"mllm"},{"id":"2603.22094","title":"Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language Models","created":"2026-03-23","cited_by_count":2,"area":"mllm"},{"id":"2606.09396","title":"PriFT: Prior-Support Guided Supervised Fine-Tuning","created":"2026-06-08","cited_by_count":2,"area":"lr"},{"id":"2607.04364","title":"RL Forgets! Towards Continual Policy Optimization","created":"2026-07-05","cited_by_count":2,"area":"mllm"},{"id":"2608.12764","title":"Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents","created":"2026-08-13","cited_by_count":2,"area":"lr"},{"id":"2510.14459","title":"Holdout-Loss-Based Data Selection for LLM Finetuning via In-Context Learning","created":"2025-10-16","cited_by_count":1,"area":"alignment"},{"id":"2512.22955","title":"Diversity or Precision? A Deep Dive into Next Token Prediction","created":"2025-12-28","cited_by_count":1,"area":"lr"},{"id":"2601.21476","title":"Thinking Seeds: Leveraging Historical Diversity for Position-Aware RL in LLMs","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2603.05969","title":"Imagine How To Change: Explicit Procedure Modeling for Change Captioning","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2603.07659","title":"Scaling Test-Time Robustness of Vision-Language Models via Self-Critical Inference Framework","created":"2026-03-08","cited_by_count":1,"area":"mllm"},{"id":"2603.27185","title":"MotionRFT: Unified Reinforcement Fine-Tuning for Text-to-Motion Generation","created":"2026-03-28","cited_by_count":1,"area":null},{"id":"2604.08926","title":"Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning","created":"2026-04-10","cited_by_count":1,"area":"lr"},{"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":"2605.01256","title":"GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models","created":"2026-05-02","cited_by_count":1,"area":null},{"id":"2605.02469","title":"Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2605.04468","title":"Stabilizing LLM Supervised Fine-Tuning via Explicit Distributional Control","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2605.11505","title":"Selective Off-Policy Reference Tuning with Plan Guidance","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2605.20005","title":"Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2606.16231","title":"From Tokens to Regions: CUDA-Sensitive Instruction Tuning for GPU Kernel Generation","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2606.24064","title":"Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning","created":"2026-06-23","cited_by_count":1,"area":"lr"},{"id":"2607.04733","title":"LP-SFT: Keeping Plausible Alternatives Alive in Supervised Fine-Tuning","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2608.30158","title":"CPR for LLMs: Critical-Point Routing against Catastrophic Forgetting in Domain Adaptation","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2509.25455","title":"PIPer: On-Device Environment Setup via Online Reinforcement Learning","created":"2025-09-29","cited_by_count":0,"area":"lr"},{"id":"2510.12560","title":"CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving","created":"2025-10-14","cited_by_count":0,"area":"wm"},{"id":"2510.17519","title":"MUG-V 10B: High-efficiency Training Pipeline for Large Video Generation Models","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2510.27462","title":"VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision","created":"2025-10-31","cited_by_count":0,"area":"lr"},{"id":"2511.09571","title":"General Intelligence-based Fragmentation (GIF): A framework for peak-labeled spectra simulation","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2601.01580","title":"The Two-Stage Decision-Sampling Hypothesis: Understanding the Emergence of Self-Reflection in RL-Trained LLMs","created":"2026-01-04","cited_by_count":0,"area":null},{"id":"2602.01227","title":"Supervised Fine-Tuning Needs to Unlock the Potential of Token Priority","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.02708","title":"BinaryPPO: Efficient Policy Optimization for Binary Classification","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2603.12875","title":"Test-time RL alignment exposes task familiarity artifacts in LLM benchmarks","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.14463","title":"An Industrial-Scale Insurance LLM Achieving Verifiable Domain Mastery and Hallucination Control without Competence Trade-offs","created":"2026-03-15","cited_by_count":0,"area":null}],"next_cursor":"100"}