Scholar
Qingyuan Wu
Google Scholar ID: CYfMzb8AAAAJ
University of Southampton, University of Liverpool
Citations & Impact
Citations
52
H-index
4
i10-index
2
Publications
17
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Published 'Directly Forecasting Belief for Reinforcement Learning with Delays' at ICML 2025 (Poster)
- Published 'Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning' at ICML 2025 (Poster)
- Published 'Variational Delayed Policy Optimization' at NeurIPS 2024 (Spotlight)
- Published 'Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays' at ICML 2024 (Poster)
- Published 'Highway Value Iteration Networks' at ICML 2024 (Poster)
- Published 'State-wise Safe Reinforcement Learning with Pixel Observations' at L4DC 2024 (Poster)
- Preprint: 'VSC-RL: Advancing Autonomous Vision-Language Agents with Variational Subgoal-Conditioned Reinforcement Learning'
- Multiple other preprints on delayed RL, inverse RL, ensemble Q-learning, etc.
- Served as reviewer/PC member for ICML (2025), NeurIPS (2024, 2025), ICLR (2025), AAAI (2026)
Co-authors