18 papers
Test-Time Scalable AI-RAN: Inference Time Allocation for Cell-Free MIMO
Seonghoon Yoo, Sangwoo Park, Seok-Hwan Park +1
Artificial intelligence-enabled radio access networks (AI-RANs) are envisioned to consist of multiple AI-based modules, potentially developed independently by different vendors. In…
Reliable Wireless Indoor Localization via Cross-Validated Prediction-Powered Calibration
Seonghoon Yoo, Houssem Sifaou, Sangwoo Park +2
Wireless indoor localization using predictive models with received signal strength information (RSSI) requires proper calibration for reliable position estimates. One remedy is to…
Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems
Qiushuo Hou, Sangwoo Park, Matteo Zecchin +4
Large language models (LLMs) are emerging as key enablers of automation in domains such as telecommunications, assisting with tasks including troubleshooting, standards interpretat…
Adaptive Selection of LoRA Components in Privacy-Preserving Federated Learning
Myoungjun Kim, Sangwoo Park, Yoseob Han +1
Differentially private federated fine-tuning of large models with LoRA suffers from aggregation error caused by LoRA's multiplicative structure, which is further amplified by DP no…
On-Device Fine-Tuning via Backprop-Free Zeroth-Order Optimization
Prabodh Katti, Houssem Sifaou, Sangwoo Park +2
On-device fine-tuning is a critical capability for edge AI systems, which must support adaptation to different agentic tasks under stringent memory constraints. Conventional backpr…
Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guarantees
Sangwoo Park, Matteo Zecchin, Osvaldo Simeone
Selecting artificial intelligence (AI) models, such as large language models (LLMs), from multiple candidates requires accurate performance estimation. This is ideally achieved thr…