3 papers
cs.LG2026
CASA: Classification Augmented with Safety Attention for Robust Multimodal Alignment
Anurag Kumar, Raghuveer Peri, Jon Burnsky +4
Multimodal large-language models (MLLMs) often experience degraded safety alignment when harmful queries exploit cross-modal interactions. Models aligned on text alone show a highe…
eess.AS2021
Unsupervised Clustered Federated Learning in Complex Multi-source Acoustic Environments
Alexandru Nelus, Rene Glitza, Rainer Martin
In this paper we introduce a realistic and challenging, multi-source and multi-room acoustic environment and an improved algorithm for the estimation of source-dominated microphone…
eess.AS2021
Estimation of Microphone Clusters in Acoustic Sensor Networks using Unsupervised Federated Learning
Alexandru Nelus, Rene Glitza, Rainer Martin
In this paper we present a privacy-aware method for estimating source-dominated microphone clusters in the context of acoustic sensor networks (ASNs). The approach is based on clus…