Computer Science Ph.D. student at Florida State University, advised by Prof. Guang Wang. Previously B.S. in Big Data Management and Application, Peking University.
🌐 Homepage · 📄 CV · 🎓 Google Scholar · DBLP · ORCID · LinkedIn · ✉️ dahai.yu@fsu.edu
I build trustworthy machine learning systems for the physical world — models that say how much their predictions can be trusted, for spatiotemporal data and for LLM reasoning.
- Uncertainty-aware spatiotemporal prediction — graph neural networks and selective state space models that report calibrated uncertainty alongside their point predictions, for energy demand and healthcare facility visits.
- Uncertainty quantification for LLM reasoning — estimating when a fluent reasoning trace should be trusted, via answer re-elicitation, symbolic verification, and reasoning-chain consistency.
- Healthcare accessibility and resilience — fine-grained measurement of facility supply, travel burden, and disruption in rural communities, and where planners should act.
First-author papers at AAAI, IJCAI, ACM SIGKDD, and ACM SIGSPATIAL.
Full list, coauthored work included → ufodestiny.github.io/publications
Also here: POPST, a unified benchmarking framework for spatiotemporal forecasting with conformal quantile regression, and OD-ZeroCal for zero-aware calibrated origin–destination demand prediction.
Outside research I write things for games I play — EU5-Patcher (achievements outside ironman for Europa Universalis V), UFO-Bannerlord, and CK3 Smaller Map.
Always happy to talk about spatiotemporal foundation models, calibration, or urban data.