5 papers
Localizing Safety Alignment: MLP Layers and Mid-Network Blocks Encode Refusal Behavior in Large Language Models
Mingyu Zong, Sampad Mohanty, Bhaskar Krishnamachari
Safety alignment in large language models is often treated as a distributed property of the entire network, yet its practical brittleness suggests that refusal behavior may be conc…
AURA: Adaptive Unified Reasoning and Automation with LLM-Guided MARL for NextG Cellular Networks
Narjes Nourzad, Mingyu Zong, Bhaskar Krishnamachari
Next-generation (NextG) cellular networks are expected to manage dynamic traffic while sustaining high performance. Large language models (LLMs) provide strategic reasoning for 6G…
Engagement and Disclosures in LLM-Powered Cognitive Behavioral Therapy Exercises: A Factorial Design Comparing the Influence of a Robot vs. Chatbot Over Time
Mina Kian, Mingyu Zong, Katrin Fischer +10
Many researchers are working to address the worldwide mental health crisis by developing therapeutic technologies that increase the accessibility of care, including leveraging larg…
The Internet of Things in the Era of Generative AI: Vision and Challenges
Xin Wang, Zhongwei Wan, Arvin Hekmati +4
Advancements in Generative AI hold immense promise to push Internet of Things (IoT) to the next level. In this article, we share our vision on IoT in the era of Generative AI. We d…
Integrating Large Language Models with Internet of Things Applications
Mingyu Zong, Arvin Hekmati, Michael Guastalla +2
This paper identifies and analyzes applications in which Large Language Models (LLMs) can make Internet of Things (IoT) networks more intelligent and responsive through three case…