Anders Larsen
YOU?
Author Swipe
View article: Apple Intelligence Foundation Language Models: Tech Report 2025
Apple Intelligence Foundation Language Models: Tech Report 2025 Open
We introduce two multilingual, multimodal foundation language models that power Apple Intelligence features across Apple devices and services: i a 3B-parameter on-device model optimized for Apple silicon through architectural innovations s…
View article: Language Models Improve When Pretraining Data Matches Target Tasks
Language Models Improve When Pretraining Data Matches Target Tasks Open
Every data selection method inherently has a target. In practice, these targets often emerge implicitly through benchmark-driven iteration: researchers develop selection strategies, train models, measure benchmark performance, then refine …
View article: Principles of gas sampling: TOS with critical challenges
Principles of gas sampling: TOS with critical challenges Open
Sampling and analysis of materials in the gas phase is not covered in general sampling standards and guides, due to the complex nature of the subject matter. Most gas-phase materials exist in the region from ambient temperatures (~300 K) t…
View article: Semi‐supervised covariate shift modelling of spectroscopic data
Semi‐supervised covariate shift modelling of spectroscopic data Open
Utilizing the full potential of spectroscopic calibrations in changing environments typically requires large amounts of maintenance and/or model updates as the presence of new sources of variation makes the calibration insufficient. In thi…
View article: Autoencoding beyond pixels using a learned similarity metric
Autoencoding beyond pixels using a learned similarity metric Open
We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder (VAE) with a generative adversarial network (GAN) we can use learned feature representati…
View article: Autoencoding beyond pixels using a learned similarity metric
Autoencoding beyond pixels using a learned similarity metric Open
We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder with a generative adversarial network we can use learned feature representations in the G…
View article: Dreaming More Data: Class-dependent Distributions over Diffeomorphisms for Learned Data Augmentation
Dreaming More Data: Class-dependent Distributions over Diffeomorphisms for Learned Data Augmentation Open
Data augmentation is a key element in training high-dimensional models. In this approach, one synthesizes new observations by applying pre-specified transformations to the original training data; e.g.~new images are formed by rotating old …