{"list":"other","total":61,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"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":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345},{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210},{"id":"2402.14008","title":"OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems","created":"2024-02-21","cited_by_count":1136},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712},{"id":"2505.05470","title":"Flow-GRPO: Training Flow Matching Models via Online RL","created":"2025-05-08","cited_by_count":661},{"id":"2409.02813","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","created":"2024-09-04","cited_by_count":512},{"id":"2503.24290","title":"Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model","created":"2025-03-31","cited_by_count":461},{"id":"2505.07818","title":"DanceGRPO: Unleashing GRPO on Visual Generation","created":"2025-05-12","cited_by_count":413},{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384},{"id":"2105.04165","title":"Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning","created":"2021-05-10","cited_by_count":383},{"id":"2503.12937","title":"R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization","created":"2025-03-17","cited_by_count":301},{"id":"2501.09686","title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","created":"2025-01-16","cited_by_count":293},{"id":"2504.10458","title":"GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents","created":"2025-04-14","cited_by_count":244},{"id":"2412.18319","title":"Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search","created":"2024-12-24","cited_by_count":175},{"id":"2503.10460","title":"Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond","created":"2025-03-13","cited_by_count":175},{"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":"2504.01805","title":"SpaceR: Reinforcing MLLMs in Video Spatial Reasoning","created":"2025-04-02","cited_by_count":159},{"id":"2503.13377","title":"Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding","created":"2025-03-17","cited_by_count":146},{"id":"2503.13939","title":"Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models","created":"2025-03-18","cited_by_count":144},{"id":"2407.11511","title":"Multi-Step Reasoning with Large Language Models, a Survey","created":"2024-07-16","cited_by_count":143},{"id":"2502.06703","title":"Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling","created":"2025-02-10","cited_by_count":136},{"id":"2502.12025","title":"SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities","created":"2025-02-17","cited_by_count":136},{"id":"2503.05379","title":"R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning","created":"2025-03-07","cited_by_count":100},{"id":"2404.01230","title":"LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models","created":"2024-04-01","cited_by_count":99},{"id":"2503.01491","title":"What's Behind PPO's Collapse in Long-CoT? Value Optimization Holds the Secret","created":"2025-03-03","cited_by_count":98},{"id":"2503.22679","title":"Q-Insight: Understanding Image Quality via Visual Reinforcement Learning","created":"2025-03-28","cited_by_count":98},{"id":"2503.02318","title":"Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models","created":"2025-03-04","cited_by_count":95},{"id":"2502.12659","title":"The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1","created":"2025-02-18","cited_by_count":91},{"id":"2504.11455","title":"SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL","created":"2025-04-15","cited_by_count":86},{"id":"2503.11197","title":"Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering","created":"2025-03-14","cited_by_count":65},{"id":"2505.02835","title":"R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning","created":"2025-05-05","cited_by_count":65},{"id":"2502.09696","title":"ZeroBench: An Impossible Visual Benchmark for Contemporary Large Multimodal Models","created":"2025-02-13","cited_by_count":58},{"id":"2503.18470","title":"MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse","created":"2025-03-24","cited_by_count":51},{"id":"2504.00883","title":"Improved Visual-Spatial Reasoning via R1-Zero-Like Training","created":"2025-04-01","cited_by_count":51},{"id":"2503.21696","title":"Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks","created":"2025-03-27","cited_by_count":44},{"id":"2502.15806","title":"A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos","created":"2025-02-19","cited_by_count":43},{"id":"2504.12680","title":"Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning","created":"2025-04-17","cited_by_count":37},{"id":"2504.14693","title":"Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark","created":"2025-04-20","cited_by_count":37},{"id":"2504.18458","title":"Fast-Slow Thinking GRPO for Large Vision-Language Model Reasoning","created":"2025-04-25","cited_by_count":36},{"id":"2504.15900","title":"SARI: Structured Audio Reasoning via Curriculum-Guided Reinforcement Learning","created":"2025-04-22","cited_by_count":34},{"id":"2504.20930","title":"ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step Verification","created":"2025-04-29","cited_by_count":31},{"id":"2505.03981","title":"X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains","created":"2025-05-06","cited_by_count":31},{"id":"2505.00551","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","created":"2025-05-01","cited_by_count":30},{"id":"2502.00698","title":"MM-IQ: Benchmarking Human-Like Abstraction and Reasoning in Multimodal Models","created":"2025-02-02","cited_by_count":29},{"id":"2505.04623","title":"EchoInk-R1: Exploring Audio-Visual Reasoning in Multimodal LLMs via Reinforcement Learning","created":"2025-05-07","cited_by_count":29},{"id":"2502.03214","title":"iVISPAR -- An Interactive Visual-Spatial Reasoning Benchmark for VLMs","created":"2025-02-05","cited_by_count":25},{"id":"2502.10867","title":"A Tutorial on LLM Reasoning: Relevant Methods behind ChatGPT o1","created":"2025-02-15","cited_by_count":25},{"id":"2503.10814","title":"Thinking Machines: A Survey of LLM based Reasoning Strategies","created":"2025-03-13","cited_by_count":25},{"id":"2504.12597","title":"GeoSense: Evaluating Identification and Application of Geometric Principles in Multimodal Reasoning","created":"2025-04-17","cited_by_count":25},{"id":"2504.03724","title":"CrowdVLM-R1: Expanding R1 Ability to Vision Language Model for Crowd Counting using Fuzzy Group Relative Policy Reward","created":"2025-03-31","cited_by_count":15}],"next_cursor":null}