Skip to content

Author

V. Pejović

We have 3 of 12 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Nov 2026

DynSL: Resource-Adaptive Model Training across Heterogeneous Edge Devices

Training models over data distributed across edge devices presents a trade-off: centralizing data simplifies training but raises privacy and regulatory concerns, while full local training may exceed the devices'compute and memory capacity. Split learning addresses this challenge by partitioning the model between client...

Boris Radovič, I. E. Akkus, Marco Canini et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Should SLMs be in the Driver's Seat? A Study of Local Models as Interpreters in Cloud-Written Agent Programs

An intermediate architecture is explored, in which the cloud-written program defers bounded questions over user data to a small local model through an ordinary function call, which improves the success rate of a code-only agent in all six combinations of backbone model and test partition.

Boris Radovič, Marco Canini, Veljko Pejović · 0 citations
Open access Jul 2026

Label-free dataset profiling for federated client clustering

This work introduces CoLEDS, a method for profiling unlabeled client datasets with minimal computational overhead that yields federatively trained models that are better aligned with individual data distributions and enables appropriate model assignment even for clients that do not participate in federated training.

Boris Radovič, Marco Canini, V. Pejović · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.