71 citations · 74 across the 5 of their papers we have counts for
5 papers
The Slow Drift of Support: Boundary Failures in Multi-Turn Mental Health LLM Dialogues
Youyou Cheng, Zhuangwei Kang, Kerry Jiang +2
Large language models (LLMs) have been widely used for mental health support. However, current safety evaluations in this field are mostly limited to detecting whether LLMs output…
DMSConfig: Automated Configuration Tuning for Distributed IoT Message Systems Using Deep Reinforcement Learning
Zhuangwei Kang, Yogesh D. Barve, Shunxing Bao +2
The Distributed Messaging Systems (DMSs) used in IoT systems require timely and reliable data dissemination, which can be achieved through configurable parameters. However, the hig…
Generative Anomaly Detection for Time Series Datasets
Zhuangwei Kang, Ayan Mukhopadhyay, Aniruddha Gokhale +2
Traffic congestion anomaly detection is of paramount importance in intelligent traffic systems. The goals of transportation agencies are two-fold: to monitor the general traffic co…
FECBench: A Holistic Interference-aware Approach for Application Performance Modeling
Yogesh D. Barve, Shashank Shekhar, Ajay Dev Chhokra +5
Services hosted in multi-tenant cloud platforms often encounter performance interference due to contention for non-partitionable resources, which in turn causes unpredictable behav…
BARISTA: Efficient and Scalable Serverless Serving System for Deep Learning Prediction Services
Anirban Bhattacharjee, Ajay Dev Chhokra, Zhuangwei Kang +3
Pre-trained deep learning models are increasingly being used to offer a variety of compute-intensive predictive analytics services such as fitness tracking, speech and image recogn…