5 papers
Agentic MPC for Semantic Control System Resynthesis
Yuya Miyaoka, Masaki Inoue
While MPC effectively handles structured, diverse, and low-level specifications, it lacks the capability to dynamically incorporate high-level contextual information such as social…
Chat-Driven Optimal Management for Virtual Network Services
Yuya Miyaoka, Masaki Inoue, Kengo Urata +1
This paper proposes a chat-driven network management framework that integrates natural language processing (NLP) with optimization-based virtual network allocation, enabling intuit…
Control Barrier Function for Aligning Large Language Models
Yuya Miyaoka, Masaki Inoue
This paper proposes a control-based framework for aligning large language models (LLMs) by leveraging a control barrier function (CBF) to ensure user-desirable text generation. The…
Chat-Driven Reconfiguration of Model Predictive Control
Yuya Miyaoka, Masaki Inoue, Jos'e M Maestre
Traditional control personalization requires users to understand optimization parameters and provide repetitive numerical feedback, creating significant barriers for non-expert use…
CBF-LLM: Safe Control for LLM Alignment
Yuya Miyaoka, Masaki Inoue
This paper proposes a control-based framework for aligning large language models (LLMs) by leveraging a control barrier function (CBF) to ensure user-desirable text generation. The…