{"list":"other","total":61,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"2409.12122","title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","created":"2024-09-18","cited_by_count":1090},{"id":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"2007.07481","title":"Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization","created":"2020-07-15","cited_by_count":906},{"id":"1909.06335","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","created":"2019-09-13","cited_by_count":851},{"id":"2006.07242","title":"Ensemble Distillation for Robust Model Fusion in Federated Learning","created":"2020-06-12","cited_by_count":682},{"id":"2111.04263","title":"Federated Learning Based on Dynamic Regularization","created":"2021-11-08","cited_by_count":562},{"id":"2203.14371","title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","created":"2022-03-27","cited_by_count":543},{"id":"1903.02891","title":"Robust and Communication-Efficient Federated Learning from Non-IID Data","created":"2019-03-07","cited_by_count":419},{"id":"2507.17746","title":"Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains","created":"2025-07-23","cited_by_count":366},{"id":"1909.13014","title":"FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization","created":"2019-09-28","cited_by_count":356},{"id":"2406.11931","title":"DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence","created":"2024-06-17","cited_by_count":331},{"id":"2504.14945","title":"Learning to Reason under Off-Policy Guidance","created":"2025-04-21","cited_by_count":281},{"id":"2504.11456","title":"DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning","created":"2025-04-15","cited_by_count":280},{"id":"1811.11479","title":"Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data","created":"2018-11-28","cited_by_count":243},{"id":"2305.05644","title":"Towards Building the Federated GPT: Federated Instruction Tuning","created":"2023-05-09","cited_by_count":185},{"id":"2007.07682","title":"FetchSGD: Communication-Efficient Federated Learning with Sketching","created":"2020-07-15","cited_by_count":179},{"id":"2502.19634","title":"MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning","created":"2025-02-26","cited_by_count":173},{"id":"2005.05238","title":"FedSplit: An algorithmic framework for fast federated optimization","created":"2020-05-11","cited_by_count":108},{"id":"2006.03262","title":"UVeQFed: Universal Vector Quantization for Federated Learning","created":"2020-06-05","cited_by_count":107},{"id":"2504.13818","title":"Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning","created":"2025-04-18","cited_by_count":84},{"id":"2503.16252","title":"Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning","created":"2025-03-20","cited_by_count":83},{"id":"2204.12703","title":"Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning","created":"2022-04-27","cited_by_count":81},{"id":"2504.04823","title":"Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models","created":"2025-04-07","cited_by_count":73},{"id":"2301.09604","title":"FedExP: Speeding Up Federated Averaging via Extrapolation","created":"2023-01-23","cited_by_count":69},{"id":"2506.17238","title":"Training a Scientific Reasoning Model for Chemistry","created":"2025-06-04","cited_by_count":56},{"id":"2510.01161","title":"Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?","created":"2025-10-01","cited_by_count":53},{"id":"2506.08007","title":"Reinforcement Pre-Training","created":"2025-06-09","cited_by_count":40},{"id":"1910.11519","title":"Limits of Private Learning with Access to Public Data","created":"2019-10-25","cited_by_count":39},{"id":"2402.13659","title":"Privacy-Preserving Instructions for Aligning Large Language Models","created":"2024-02-21","cited_by_count":35},{"id":"2505.22257","title":"Revisiting Group Relative Policy Optimization: Insights into On-Policy and Off-Policy Training","created":"2025-05-28","cited_by_count":34},{"id":"2305.12132","title":"Can Public Large Language Models Help Private Cross-device Federated Learning?","created":"2023-05-20","cited_by_count":30},{"id":"2506.20520","title":"Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards","created":"2025-06-25","cited_by_count":29},{"id":"2509.03403","title":"Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training","created":"2025-09-03","cited_by_count":29},{"id":"2304.01731","title":"Selective Knowledge Sharing for Privacy-Preserving Federated Distillation without A Good Teacher","created":"2023-04-04","cited_by_count":25},{"id":"2504.15777","title":"Tina: Tiny Reasoning Models via LoRA","created":"2025-04-22","cited_by_count":25},{"id":"2505.07291","title":"INTELLECT-2: A Reasoning Model Trained Through Globally Decentralized Reinforcement Learning","created":"2025-05-12","cited_by_count":25},{"id":"2504.15716","title":"DianJin-R1: Evaluating and Enhancing Financial Reasoning in Large Language Models","created":"2025-04-22","cited_by_count":22},{"id":"2507.13541","title":"PrefPalette: Personalized Preference Modeling with Latent Attributes","created":"2025-07-17","cited_by_count":16},{"id":"2507.07024","title":"FlexOlmo: Open Language Models for Flexible Data Use","created":"2025-07-09","cited_by_count":15},{"id":"2504.16438","title":"POPri: Private Federated Learning using Preference-Optimized Synthetic Data","created":"2025-04-23","cited_by_count":14},{"id":"2411.05818","title":"Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives","created":"2024-11-02","cited_by_count":12},{"id":"2502.15436","title":"Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federated LoRA Fine-Tuning","created":"2025-02-21","cited_by_count":10},{"id":"2206.10032","title":"Communication-Efficient Federated Learning With Data and Client Heterogeneity","created":"2022-06-20","cited_by_count":9},{"id":"2404.09753","title":"Personalized Collaborative Fine-Tuning for On-Device Large Language Models","created":"2024-04-15","cited_by_count":9},{"id":"2506.05568","title":"Ravan: Multi-Head Low-Rank Adaptation for Federated Fine-Tuning","created":"2025-06-05","cited_by_count":9},{"id":"2402.18752","title":"Pre-training Differentially Private Models with Limited Public Data","created":"2024-02-28","cited_by_count":8},{"id":"2602.20722","title":"Buffer Matters: Unleashing the Power of Off-Policy Reinforcement Learning in Large Language Model Reasoning","created":"2026-02-24","cited_by_count":8},{"id":"2409.13931","title":"On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists","created":"2024-09-20","cited_by_count":6},{"id":"2508.17850","title":"GEPO: Group Expectation Policy Optimization for Stable Heterogeneous Reinforcement Learning","created":"2025-08-25","cited_by_count":4},{"id":"2602.00453","title":"FedMOA: Federated GRPO for Personalized Reasoning LLMs under Heterogeneous Rewards","created":"2026-01-31","cited_by_count":2}],"next_cursor":null}