DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learningDaya Guo, Junlong Li, Dejian Yang et al.|Nature|2025Cited by 610
Controllable construction of defect-mediated Z-scheme heterojunction for dual-functional cooperative photocatalysis of benzyl alcohol conversion and hydrogen evolutionPengyu Guo, Baining Zhang, Peng Zhang et al.|Applied Catalysis B: Environmental|2024Cited by 48