Abstract -- Ambulance emergency-call handling requires call takers to identify the emergency and record critical details under severe time pressure. In German-speaking Switzerland, this is complicated by the gap between spoken Swiss German (low-resource dialects…
Abstract -- Analyst-oriented systems for detecting threats in multilingual text must provide, besides accurate predictions, auditability and the capacity to improve as more training data becomes available. We propose a two-stage pipeline in which a…
Large Language Models (LLMs) are inducing a dual transformation in search engines: an internal transformation of search architectures and an external transformation of search traffic dynamics. As part of the internal transformation, LLMs are integrated…
We introduce a load-aware selective embedding-pruning method to be used in dense retrieval systems. Our method adapts the embedding dimensionality at inference time based on per-query deadlines and the current queue occupancy. Under light load,…
Computing-Aware Traffic Steering (CATS) optimizes the assignment of user requests to replicated service instances by jointly considering network and computing conditions.Although CATS has been widely studied for single-service scenarios, cloud--edge continuum deployments are typically multi-tenant:…