Fully trained BiLSTM outperforms zero-shot and LoRA-adapted TSFMs on California wildfire PM2.5 under leave-one-incident-out evaluation, especially at hazardous AQI thresholds.
Gomez, Lukasz Kaiser, and Illia Polosukhin
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
A Transformer model generates full control filters for active noise control in an unsupervised end-to-end differentiable system, showing better noise reduction than GFANC on real noises.
Transformer and U-Net models outperform classical SVI parameterization for volatility surface reconstruction from sparse data, with soft arbitrage penalties reducing violations at modest accuracy cost.
citing papers explorer
-
Evaluating the Generalizability of Foundation Models for Extreme Environmental Events: Case Study of California Wildfire PM2.5
Fully trained BiLSTM outperforms zero-shot and LoRA-adapted TSFMs on California wildfire PM2.5 under leave-one-incident-out evaluation, especially at hazardous AQI thresholds.
-
Transformer-based End-to-End Control Filter Generation for Active Noise Control
A Transformer model generates full control filters for active noise control in an unsupervised end-to-end differentiable system, showing better noise reduction than GFANC on real noises.
-
Volatility Surface Reconstruction using Deep Learning under No-Arbitrage Constraints
Transformer and U-Net models outperform classical SVI parameterization for volatility surface reconstruction from sparse data, with soft arbitrage penalties reducing violations at modest accuracy cost.