Assistant Professor in AI & ML at The University of Glasgow

Glasgow, Scotland
Joined October 2013
Can your NAS pipeline handle datasets it has never seen before? We’re officially inviting the ML community to the NAS Unseen Data Competition. Website: nascompetition.com/ Winners will be celebrated at the AutoML 2026 conference in Ljubljana! @automl_conf
1
1
111
Linus Ericsson retweeted
Check out our new work on NAS search spaces! We have created einspace, a new expressive search space that unifies many architectural families, including convnets, transformers and mlp-only architectures. paper: arxiv.org/abs/2405.20838 project page: linusericsson.github.io/eins…
1
19
2
42
7,532
This work was done at the University of Edinburgh with collaborators Miguel Espinosa, @CYang51746374, @AntreasAntonio, @AmosStorkey, Shay B. Cohen, @steve_mcdonagh and Elliot J. Crowley. @SchoolOfEng_UoE , @InfAtEd
Check out our new work on NAS search spaces! We have created einspace, a new expressive search space that unifies many architectural families, including convnets, transformers and mlp-only architectures. paper: arxiv.org/abs/2405.20838 project page: linusericsson.github.io/eins…
1
2
13
761
Thanks to Elliot, Steven and Antreas in particular for forming the early stages of the idea and Shay for help formulating the CFG!
2
63
Our space is based on a parameterised probabilistic context-free grammar. Through its recursively defined production rules, it's able to generate architectures that are arbitrarily wide and deep, containing branching and routing operations in addition to parameterised layers.
1
4
181
In our experiments we find new cool architectures as well as improvements on existing ones across a range of diverse datasets from the Unseen NAS suite. Here is an example of the wild (and high-performing) things einspace can generate. code: github.com/linusericsson/ein…
3
135
Check out our new work on NAS search spaces! We have created einspace, a new expressive search space that unifies many architectural families, including convnets, transformers and mlp-only architectures. paper: arxiv.org/abs/2405.20838 project page: linusericsson.github.io/eins…
1
19
2
42
7,532
Linus Ericsson retweeted
🚨 MemControl: Mitigating Memorization in Medical Diffusion Models via Automated Parameter Selection A new strategy to mitigate memorization in Diffusion models Arxiv: arxiv.org/abs/2405.19458 Work done with @SnchzPedro_ @OBohdal @STsaftaris @tmh31 @BioMedAI_CDT 🧵👇
1
7
1
19
2,156