Qingpeng Cai
Scholar

Qingpeng Cai

Google Scholar ID: uU6s1tYAAAAJ
Kuaishou Technology
Reinforcement LearningLLMRecommender SystemComputational Advertising
Citations & Impact
All-time
Citations
1,295
 
H-index
20
 
i10-index
24
 
Publications
20
 
Co-authors
11
list available
Resume (English only)
Academic Achievements
  • Awarded the 2024 Qian Weichang Prize for Chinese Information Processing Science and Technology (First Prize in Natural Sciences); Dual-track championships in the NeurIPS 2024 Auto-Bidding in Large-Scale Auctions Competition; Proposed the Generative Model for RL (G4RL) bidding paradigm, increasing the platform's revenue by more than 3%; Published multiple papers including 'TemporalExpertNet: Cross-Temporal Knowledge Reuse for Promotion-Aware CVR Prediction'.
Research Experience
  • Currently a Senior Staff Research Scientist at Kuaishou Technology, responsible for business optimization and technical management.
Education
  • Ph.D. from Institute for Interdisciplinary Information Sciences (IIIS) at Tsinghua University; B.E. from Nanjing University.
Background
  • Core research focuses on Reinforcement Learning and its applications to Large Language Models and practical domains (Recommender Systems and Advertising).
Miscellany
  • Serves as Area Chair, Organizer, and Program Committee member for top-tier machine learning conferences such as NeurIPS, ICLR, AAMAS, CIKM, ICML, WWW, and AAAI.