Scholar
Pei Zhou
Google Scholar ID: 13PGDZsAAAAJ
Senior Applied Scientist, Microsoft
Citations & Impact
Citations
1,423
H-index
17
i10-index
19
Publications
20
Co-authors
5
list available
Publications
Resume (English only)
Academic Achievements
- NeurIPS 2024 paper: 'SELF-DISCOVER: Large Language Models Self-Compose Reasoning Structures' – introduces a framework enabling LLMs to self-compose task-specific reasoning structures, achieving significant gains over Chain-of-Thought and other methods
- 2023 preprint: 'How FaR Are Large Language Models From Agents with Theory-of-Mind?' – investigates theory-of-mind in LLMs
- Work featured in The Register, Science Daily, VentureBeat, Tech Xplore, etc.
- Organized a Theory-of-Mind workshop accepted at ICML 2023
- Presented a Dungeon Master-like dialogue agent with theory-of-mind and RL at ACL 2023
