{"list":"other","total":52,"rows":[{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2403.20330","title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","created":"2024-03-29","cited_by_count":914},{"id":"2403.14624","title":"MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?","created":"2024-03-21","cited_by_count":586},{"id":"2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","created":"2025-06-02","cited_by_count":559},{"id":"2402.14804","title":"Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset","created":"2024-02-22","cited_by_count":526},{"id":"2504.07615","title":"VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model","created":"2025-04-10","cited_by_count":526},{"id":"2503.01785","title":"Visual-RFT: Visual Reinforcement Fine-Tuning","created":"2025-03-03","cited_by_count":513},{"id":"2409.02813","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","created":"2024-09-04","cited_by_count":512},{"id":"2502.03387","title":"LIMO: Less is More for Reasoning","created":"2025-02-05","cited_by_count":498},{"id":"2505.22617","title":"The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models","created":"2025-05-28","cited_by_count":485},{"id":"2411.10440","title":"LLaVA-CoT: Let Vision Language Models Reason Step-by-Step","created":"2024-11-15","cited_by_count":454},{"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":"2209.14610","title":"Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning","created":"2022-09-29","cited_by_count":350},{"id":"2504.08837","title":"VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning","created":"2025-04-10","cited_by_count":323},{"id":"1710.07300","title":"FigureQA: An Annotated Figure Dataset for Visual Reasoning","created":"2017-10-19","cited_by_count":319},{"id":"2506.04178","title":"OpenThoughts: Data Recipes for Reasoning Models","created":"2025-06-04","cited_by_count":304},{"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":"2407.01284","title":"We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?","created":"2024-07-01","cited_by_count":286},{"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":"2110.13214","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","created":"2021-10-25","cited_by_count":267},{"id":"2503.07536","title":"LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL","created":"2025-03-10","cited_by_count":248},{"id":"2502.04463","title":"Training Language Models to Reason Efficiently","created":"2025-02-06","cited_by_count":247},{"id":"2407.04973","title":"LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts","created":"2024-07-06","cited_by_count":245},{"id":"2503.06520","title":"Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement","created":"2025-03-09","cited_by_count":239},{"id":"2406.18521","title":"CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs","created":"2024-06-26","cited_by_count":234},{"id":"2105.14517","title":"GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning","created":"2021-05-30","cited_by_count":228},{"id":"2504.11468","title":"SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models","created":"2025-04-10","cited_by_count":212},{"id":"2504.16891","title":"AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset","created":"2025-04-23","cited_by_count":174},{"id":"1704.06440","title":"Equivalence Between Policy Gradients and Soft Q-Learning","created":"2017-04-21","cited_by_count":173},{"id":"2402.14830","title":"Orca-Math: Unlocking the potential of SLMs in Grade School Math","created":"2024-02-16","cited_by_count":151},{"id":"2411.00836","title":"DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models","created":"2024-10-29","cited_by_count":146},{"id":"2504.07934","title":"SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement","created":"2025-04-10","cited_by_count":145},{"id":"2212.02746","title":"UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression","created":"2022-12-06","cited_by_count":137},{"id":"2502.19187","title":"BIG-Bench Extra Hard","created":"2025-02-26","cited_by_count":125},{"id":"2502.17387","title":"Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models","created":"2025-02-24","cited_by_count":109},{"id":"2212.00259","title":"Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning","created":"2022-12-01","cited_by_count":92},{"id":"2507.16812","title":"MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning","created":"2025-07-22","cited_by_count":59},{"id":"2506.04207","title":"Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning","created":"2025-06-04","cited_by_count":53},{"id":"2509.03493","title":"On Entropy Control in LLM-RL Algorithms","created":"2025-09-03","cited_by_count":40},{"id":"2412.11006","title":"Entropy-Regularized Process Reward Model","created":"2024-12-15","cited_by_count":38},{"id":"2504.18458","title":"Fast-Slow Thinking GRPO for Large Vision-Language Model Reasoning","created":"2025-04-25","cited_by_count":36},{"id":"2505.08311","title":"AM-Thinking-v1: Advancing the Frontier of Reasoning at 32B Scale","created":"2025-05-13","cited_by_count":29},{"id":"2508.12680","title":"Vision-G1: Towards General Vision Language Reasoning with Multi-Domain Data Curation","created":"2025-08-18","cited_by_count":13},{"id":"2507.03483","title":"BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset","created":"2025-07-04","cited_by_count":12},{"id":"2310.02671","title":"Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods","created":"2023-10-04","cited_by_count":9},{"id":"2404.11129","title":"Fact :Teaching MLLMs with Faithful, Concise and Transferable Rationales","created":"2024-04-17","cited_by_count":7},{"id":"2506.01676","title":"K12Vista: Exploring the Boundaries of MLLMs in K-12 Education","created":"2025-06-02","cited_by_count":6}],"next_cursor":null}