2 papers
cs.LG2026
Activation- and Influence-Aware Ranks (AIR): Function-Preserving SVD Compression for LLMs
Nico Harder, Daniel Becking, Karsten Mueller +1
We present Activation- and Influence-Aware Ranks (AIR), an SVD-based LLM compression framework that guides each weight matrix's low-rank approximation with a backward-signal influe…
cs.LG2025
Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction
Daniel Becking, Ingo Friese, Karsten Müller +4
In telecommunications, Autonomous Networks (ANs) automatically adjust configurations based on specific requirements (e.g., bandwidth) and available resources. These networks rely o…