Profiles2023-2026
Qingpeng Cai
Kuaishou Technology
15Papers
0Last author
49Unique co-authors
1First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers15
- Hierarchical Residual Policy Optimization for Generative RecommendationsAuthor 8 of 9KDD 2026
- LBM: Hierarchical Large Auto-Bidding Model via Reasoning and ActingAuthor 4 of 6WWW 2026
- LLM-Powered User Simulator for Recommender SystemAuthor 5 of 9AAAI 2025 · 11 citations
- Generative Auto-Bidding with Value-Guided ExplorationsAuthor 7 of 11SIGIR 2025 · 7 citations
- AURO: Reinforcement Learning for Adaptive User Retention Optimization in Recommender SystemsAuthor 2 of 6WWW 2025 · 6 citations
- Value Function Decomposition in Markov Recommendation ProcessAuthor 3 of 7WWW 2025 · 4 citations
- M3oE: Multi-Domain Multi-Task Mixture-of Experts Recommendation FrameworkAuthor 4 of 12SIGIR 2024 · 27 citations
- Sequential Recommendation for Optimizing Both Immediate Feedback and Long-term RetentionAuthor 4 of 9SIGIR 2024 · 23 citations
- Two-Stage Constrained Actor-Critic for Short Video RecommendationAuthor 1 of 12WWW 2023 · 60 citations
- Multi-Task Recommendations with Reinforcement LearningAuthor 3 of 11WWW 2023 · 57 citations
- Exploration and Regularization of the Latent Action Space in RecommendationAuthor 2 of 11WWW 2023 · 54 citations
- State Regularized Policy Optimization on Data with Dynamics ShiftAuthor 2 of 7NeurIPS 2023 · 30 citations
- PrefRec: Recommender Systems with Human Preferences for Reinforcing Long-term User EngagementAuthor 2 of 9KDD 2023 · 24 citations
- Generative Flow Network for Listwise RecommendationAuthor 2 of 8KDD 2023 · 15 citations
- ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual ActorAuthor 2 of 7ICLR 2023 · 6 citations
