Oscar Artur Bernd Berg

According to our database, Oscar Artur Bernd Berg authored at least 7 papers between 2025 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

CO-NAS: Joint Neural Architecture Search for Compression, Quantization, and Edge-Cloud Model Offloading.

Eiraj Saqib, Oscar Artur Bernd Berg, Isaac Sánchez Leal, Irida Shallari, Silvia Krug, Axel Jantsch, Mattias O'Nils

IEEE Access, 2026

BranchySplit: Runtime-Adaptable Partitioning and Early Exits for Accelerated Edge Inference.

Oscar Artur Bernd Berg, Eiraj Saqib, Axel Jantsch, Isaac Sánchez Leal, Irida Shallari, Silvia Krug, Mattias O'Nils

IEEE Access, 2026

2025

Quantization Compensator Network: Server-Side Feature Reconstruction in Partitioned IoT Systems.

Isaac Sánchez Leal, Oscar Artur Bernd Berg, Silvia Krug, Eiraj Saqib, Irida Shallari, Axel Jantsch, Mattias O'Nils, Tomas Nordström

IEEE Access, 2025

TCL: Time-Dependent Clustering Loss for Optimizing Post-Training Feature Map Quantization for Partitioned DNNs.

Oscar Artur Bernd Berg, Eiraj Saqib, Axel Jantsch, Irida Shallari, Silvia Krug, Isaac Sánchez Leal, Mattias O'Nils

IEEE Access, 2025

Efficient Inference of parallel partitioned hybrid-Vision Transformers.

Oscar Artur Bernd Berg, Eiraj Saqib, Axel Jantsch, Mattias O'Nils, Silvia Krug, Irida Shallari, Isaac Sánchez Leal

Proceedings of the 4th International Workshop on Real-time and IntelliGent Edge computing, 2025

Quantization-Aware Training for Autoencoder-Based Partitioning of CNNs.

Oscar Artur Bernd Berg, Eiraj Saqib, Axel Jantsch, Mattias O'Nils, Irida Shallari, Isaac Sánchez Leal, Silvia Krug

Proceedings of the IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, 2025

Efficient Edge Inference via Entropy and Magnitude-Aware Feature Map Pruning in Partitioned CNNs.

Eiraj Saqib, Oscar Artur Bernd Berg, Isaac Sánchez Leal, Irida Shallari, Silvia Krug, Axel Jantsch, Mattias O'Nils

Proceedings of the International Conference on Machine Learning and Applications, 2025