Rajkarn Singh — accepted AI-conference papers

2025

Lightweight Online Adaption for Time Series Foundation Model Forecasts

Thomas L Lee, William Toner, Rajkarn Singh, Artjom Joosen, Martin Asenov

ICML 2025poster

Foundation models (FMs) have emerged as a promising approach for time series forecasting. While effective, FMs typically remain fixed during deployment due to the high computational costs of learning them online. Consequently, deployed FMs fail to adapt their forecasts to current data characteristic…

Cited by 1 Source ↗PDF ↗Scholar ↗

2024

DAM: Towards a Foundation Model for Forecasting

Luke Nicholas Darlow, Qiwen Deng, Ahmed Hassan, Martin Asenov, Rajkarn Singh, Artjom Joosen +2

ICLR 2024poster

It is challenging to scale time series forecasting models such that they forecast accurately for multiple distinct domains and datasets, all with potentially different underlying collection procedures (e.g., sample resolution), patterns (e.g., periodicity), and prediction requirements (e.g., reconst…

Cited by 0 Source ↗PDF ↗Scholar ↗