🧑🔬 Dejian Yang — papers of 2025 — 3 papers, the most cited first3 papers · all years of Dejian YangDeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement LearningNatureDeepSeek-AI, Daya Guo, Dejian Yang, et al.2025 · 4,728 citationsDeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal DecompositionarXiv:2504.21801Z. Z. Ren, Zhihong Shao, Junxiao Song, et al.2025 · 122 citationsCodeI/O: Condensing Reasoning Patterns via Code Input-Output PredictionarXiv:2502.07316Junlong Li, Daya Guo, Dejian Yang, et al.2025 · 21 citationsThis page in Markdown → https://md.research.elamur.ai/free/en/authors/dejian-yang/year/2025/