60 citations · 63 across the 4 of their papers we have counts for
7 papers
Continuous Memory Machines
Ciaran Regan, Kai Arulkumaran, Luke Darlow +3
Recurrent neural networks typically compress information into a single vector-valued recurrent state, forcing short-term computation and long-term retention to share the same repre…
How Good Can Linear Models Be for Time-Series Forecasting?
Lang Huang, Jinglue Xu, Luke Darlow
Time-series forecasting research has been moving steadily toward larger architectures, from specialized transformers to general-purpose foundation models, on the assumption that ca…
Continuous Thought Machines
Luke Darlow, Ciaran Regan, Sebastian Risi +2
Biological brains demonstrate complex neural activity, where neural dynamics are critical to how brains process information. Most artificial neural networks ignore the complexity o…
Serverless Cold Starts and Where to Find Them
Artjom Joosen, Ahmed Hassan, Martin Asenov +5
This paper releases and analyzes a month-long trace of 85 billion user requests and 11.9 million cold starts from Huawei's serverless cloud platform. Our analysis spans workloads f…
DAM: Towards A Foundation Model for Time Series Forecasting
Luke Darlow, Qiwen Deng, Ahmed Hassan +5
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 c…
An Analysis of Linear Time Series Forecasting Models
William Toner, Luke Darlow
Despite their simplicity, linear models perform well at time series forecasting, even when pitted against deeper and more expensive models. A number of variations to the linear mod…
How Does It Function? Characterizing Long-term Trends in Production Serverless Workloads
Artjom Joosen, Ahmed Hassan, Martin Asenov +4
This paper releases and analyzes two new Huawei cloud serverless traces. The traces span a period of over 7 months with over 1.4 trillion function invocations combined. The first t…