{"total":60,"rows":[{"id":"2510.26788","title":"Defeating the Training-Inference Mismatch via FP16","created":"2025-10-30","cited_by_count":66,"area":null},{"id":"2508.15884","title":"Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search","created":"2025-08-21","cited_by_count":41,"area":null},{"id":"2509.04419","title":"Towards a Unified View of Large Language Model Post-Training","created":"2025-09-04","cited_by_count":36,"area":null},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2602.13035","title":"Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL","created":"2026-02-13","cited_by_count":27,"area":null},{"id":"2510.06062","title":"When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL","created":"2025-10-07","cited_by_count":21,"area":null},{"id":"2510.06826","title":"Mid-Training of Large Language Models: A Survey","created":"2025-10-08","cited_by_count":21,"area":null},{"id":"2507.16577","title":"Scaling Linear Attention with Sparse State Expansion","created":"2025-07-22","cited_by_count":13,"area":null},{"id":"2509.20241","title":"Energy Use of AI Inference, Efficiency Pathways, and Test-Time Scaling","created":"2025-09-24","cited_by_count":13,"area":null},{"id":"2511.21016","title":"Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression","created":"2025-11-26","cited_by_count":11,"area":null},{"id":"2510.19338","title":"Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning","created":"2025-10-22","cited_by_count":10,"area":null},{"id":"2602.08064","title":"SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm","created":"2026-02-08","cited_by_count":10,"area":null},{"id":"2602.01826","title":"Beyond Precision: Training-Inference Mismatch is an Optimization Problem and Simple LR Scheduling Fixes It","created":"2026-02-02","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":"2603.09652","title":"MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants","created":"2026-03-10","cited_by_count":8,"area":null},{"id":"2605.14220","title":"Diagnosing Training Inference Mismatch in LLM Reinforcement Learning via a Zero-Mismatch Reference","created":"2026-05-14","cited_by_count":7,"area":null},{"id":"2602.12036","title":"Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models","created":"2026-02-12","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":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2603.16140","title":"Noisy Data is Destructive to Reinforcement Learning with Verifiable Rewards","created":"2026-03-17","cited_by_count":5,"area":null},{"id":"2605.08301","title":"Priming: Hybrid State Space Models From Pre-trained Transformers","created":"2026-05-08","cited_by_count":5,"area":null},{"id":"2507.01652","title":"Autoregressive Image Generation with Linear Complexity: A Spatial-Aware Decay Perspective","created":"2025-07-02","cited_by_count":4,"area":null},{"id":"2602.06391","title":"POINTS-GUI-G: GUI-Grounding Journey","created":"2026-02-06","cited_by_count":4,"area":null},{"id":"2605.02944","title":"Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation","created":"2026-05-01","cited_by_count":4,"area":null},{"id":"2605.15417","title":"$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2607.05863","title":"Strategic Bargaining in Multi-Buyer Markets: Reinforcement Learning from Verifiable Rewards for LLM Negotiations","created":"2026-07-07","cited_by_count":4,"area":null},{"id":"2510.25441","title":"Grounded in Reality: Learning and Deploying Proactive LLM from Offline Logs","created":"2025-10-29","cited_by_count":3,"area":null},{"id":"2602.04296","title":"ProxyWar: Dynamic Assessment of LLM Code Generation in Game Arenas","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2604.06111","title":"AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2604.21718","title":"Building a Precise Video Language with Human-AI Oversight","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2607.16850","title":"Group Entropy-Controlled Policy Optimization","created":"2026-07-18","cited_by_count":3,"area":null},{"id":"2607.20785","title":"Robostral Navigate","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2511.07148","title":"TCM-Eval: An Expert-Level Dynamic and Extensible Benchmark for Traditional Chinese Medicine","created":"2025-11-10","cited_by_count":2,"area":null},{"id":"2605.28751","title":"Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2606.30562","title":"Morphing into Hybrid Attention Models","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2508.09525","title":"Learning Spatial Decay for Vision Transformers","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2509.18600","title":"OraPO: Oracle-educated Reinforcement Learning for Data-efficient and Factual Radiology Report Generation","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2512.03847","title":"DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2601.06911","title":"Distributional Clarity: The Hidden Driver of RL-Friendliness in Large Language Models","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2602.13033","title":"Buy versus Build an LLM: A Decision Framework for Governments","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2602.21196","title":"Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2603.00963","title":"Stabilizing Policy Optimization via Logits Convexity","created":"2026-03-01","cited_by_count":1,"area":null},{"id":"2604.28020","title":"Cost-Aware Learning","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2607.01567","title":"Scaling Trends for Lie Detector Oversight in Preference Learning","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2609.05141","title":"SciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2508.00450","title":"When Relevance Meets Novelty: Dual-Stable Periodic Optimization for Serendipitous Recommendation","created":"2025-08-01","cited_by_count":0,"area":null},{"id":"2601.06867","title":"U-MASK: User-adaptive Spatio-Temporal Masking for Personalized Mobile AI Applications","created":"2026-01-11","cited_by_count":0,"area":null},{"id":"2602.05933","title":"Approximation of Log-Partition Function in Policy Mirror Descent Induces Implicit Regularization for LLM Post-Training","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2605.11235","title":"Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.12265","title":"How Useful Is Cross-Domain Generalization for Training LLM Monitors?","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.04023","title":"CodegenBench: Can LLMs Write Efficient Code Across Architectures?","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.11431","title":"Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2607.00724","title":"MSQA: A Natively Sourced Multilingual and Multicultural SimpleQA Benchmark","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.10848","title":"Predictive Divergence Masks for LLM RL","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2608.06933","title":"Ask-E: An Environment for Calibrated Question Generation","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2609.00734","title":"Online Self-Weighted Fine-Tuning","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.12419","title":"MInTRL: Off-policy Intervention can boost On-policy RL","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.36830","title":"Where Does Staleness Accumulate? Pool Aware Effective Staleness Control for Asynchronous RL in LLM Post-Training","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39247","title":"Trust the Critic More","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39661","title":"The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}