Papers by Runfei Chen
SeMob: Semantic Synthesis for Dynamic Urban Mobility Prediction (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing spatiotemporal models struggle to interpret and adapt to abrupt changes caused by external events. |
| Approach: | They propose a LLM-powered semantic synthesis pipeline that extracts spatiotemporally related text from online texts and integrates it with spatio-temporal data. |
| Outcome: | The proposed framework achieves maximal reductions of 13.92% in MAE and 11.12% in RMSE compared to the spatiotemporal model. |