19 papers
SE-MoLoRA: Shared-Expert LoRA Adapters for Domain-Specific Photographic Assessment
Bishwash Khanal, Anlan Zhang, Sasu Tarkoma +2
Vision-language models can describe images fluently, but they often fail to provide actionable photographic critique because semantic content and aesthetic judgment remain entangle…
UrbanWell: Benchmarking Multimodal Large Language Models for Spatio-Temporal Urban Wellbeing Analytics
Yanxin Xi, Xiang Su, Jie Feng +3
Understanding urban wellbeing from multimodal data requires integrating heterogeneous spatial and temporal signals, posing significant challenges for current multimodal large langu…
Autonomic Federated-Market Orchestration for the Edge-Cloud Continuum
Lauri Lovén, Roberto Morabito, Abhishek Kumar +3
The edge-cloud computing continuum demands self-management mechanisms that scale across autonomous administrative domains while honouring tenant- and operator-specified data sovere…
Credibility Trilemma in Polymatroidal Service Markets
Lauri Lovén, Sujit Gujar, Kalle Timperi +4
Mechanism-mediated service markets with polymatroidal feasibility admit efficient, dominant-strategy incentive-compatible (DSIC) allocation, but these guarantees implicitly assume…
The Behavioral Credibility Trilemma: When Calibrated Autonomy Becomes Impossible
Lauri Lovén, Nam Do, Hassan Mehmood +2
We prove that no reinforcement learning policy with confidence-gated autonomy can simultaneously achieve maximum helpfulness, optimal calibration, and full autonomy under rational…
Neural Router: Semantic Content Matching for Agentic AI
Lauri Lovén, Abhishek Kumar, Alexander Engelhardt +5
Large language models (LLMs) can serve as the semantic-matching engine of a content-based publish/subscribe broker for agentic AI across the edge-cloud computing continuum, bridgin…