Scholar
Tao Ge
Google Scholar ID: LYbs7Q8AAAAJ
Microsoft Research
Citations & Impact
Citations
3,800
H-index
29
i10-index
41
Publications
20
Co-authors
6
list available
Publications
Resume (English only)
Academic Achievements
- - Published over 60 papers at top AI/ML conferences.
- - Technological Innovations:
- - **Speculative Decoding**: Started research in 2021, first introduced a separate drafter model to achieve lossless acceleration of Transformer decoding, and coined the term “Speculative Decoding”.
- - **Persona-Driven Synthetic Data Creation**: Proposed a novel paradigm for scaling high-quality synthetic training data generation, widely adopted in leading LLMs such as OLMo/Molmo and PixMo (AI2), Qwen (Alibaba), Hunyuan (Tencent), etc.
Research Experience
- - Microsoft, Redmond, Principal Science Lead
- - Tencent AI Lab (Seattle), Principal Researcher
- - Microsoft Research Asia (MSRA), Researcher
Education
- Ph.D. in Computer Science from Peking University.
Background
- Research Interests: GenAI/LLM. Professional Field: Computer Science. Background: Currently a Principal Science Lead at Microsoft in Redmond, leading the research and development of state-of-the-art large language models, including synthetic data creation, mid-/post-training of OpenAI models (GPT-4/5, and o3/o4-mini), and agentic approaches powering Microsoft products.
Miscellany
- Residence: Redmond, WA, USA.
