Ruisong Zhang
DeepSeek (China)
1 paper in the Anchorcite directory, published in 2025, cited 16,737 times in total.
ORCID profileResearch topics
- AI-based Problem Solving and Planning · 1 paper
- Natural Language Processing Techniques · 1 paper
- Topic Modeling · 1 paper
Frequent co-authors
- Daya Guo · 1 paper
- Haowei Zhang · 1 paper
- Junxiao Song · 1 paper
- Peiyi Wang · 1 paper
- Qihao Zhu · 1 paper
- Runxin Xu · 1 paper
- Ruoyu Zhang · 1 paper
- Shirong Ma · 1 paper
Papers
- DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learningNature · 2025 · 16,737 citations
Abstract General reasoning represents a long-standing and formidable challenge in artificial intelligence (AI). Recent breakthroughs, exemplified by large language models (LLMs) 1,2 and chain-of-thought (CoT) prompting 3 , have achieved considerable success on foundational reasoning tasks. However, this success is…
Metadata from OpenAlex (CC0).