activity
20242026
collaborators

5 papers

cs.AI2026

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…

cs.NI2025

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…

cs.RO2025

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…

cs.DC2024

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…

cs.AI2024

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…