ST-Vision-LLM reframes spatiotemporal traffic forecasting as vision-language fusion, using visual encoders on traffic grids and efficient numerical tokenization to achieve 15.6% better long-term accuracy and 30% gains in few-shot cross-domain settings.
Long Short-Term Memory
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2representative citing papers
A single-layer LSTM reports RMSE of 14.93 on FD001 and 14.20 on FD003, outperforming a prior deeper LSTM, while XGBoost reaches 13.36 on FD003 under identical preprocessing.
citing papers explorer
-
Vision-LLMs for Spatiotemporal Traffic Forecasting
ST-Vision-LLM reframes spatiotemporal traffic forecasting as vision-language fusion, using visual encoders on traffic grids and efficient numerical tokenization to achieve 15.6% better long-term accuracy and 30% gains in few-shot cross-domain settings.
-
Remaining Useful Life Estimation for Turbofan Engines: A Comparative Study of Classical, CNN, and LSTM Approaches
A single-layer LSTM reports RMSE of 14.93 on FD001 and 14.20 on FD003, outperforming a prior deeper LSTM, while XGBoost reaches 13.36 on FD003 under identical preprocessing.