activity
20232025
most citedUncovering Cross-Domain Recommendation Ability of Large Language Models

9 citations · 27 across the 12 of their papers we have counts for

collaborators

12 papers

cs.CL2025

DocCHA: Towards LLM-Augmented Interactive Online diagnosis System

Xinyi Liu, Dachun Sun, Yi R. Fung +2

Despite the impressive capabilities of Large Language Models (LLMs), existing Conversational Health Agents (CHAs) remain static and brittle, incapable of adaptive multi-turn reason…

cs.SI2025

SCRAG: Social Computing-Based Retrieval Augmented Generation for Community Response Forecasting in Social Media Environments

Dachun Sun, You Lyu, Jinning Li +4

This paper introduces SCRAG, a prediction framework inspired by social computing, designed to forecast community responses to real or hypothetical social media posts. SCRAG can be…

cs.DC2025

FailLite: Failure-Resilient Model Serving for Resource-Constrained Edge Environments

Li Wu, Walid A. Hanafy, Tarek Abdelzaher +3

Model serving systems have become popular for deploying deep learning models for various latency-sensitive inference tasks. While traditional replication-based methods have been us…

cs.IR2025★ 9 cited

Uncovering Cross-Domain Recommendation Ability of Large Language Models

Xinyi Liu, Ruijie Wang, Dachun Sun +2

Cross-Domain Recommendation (CDR) seeks to enhance item retrieval in low-resource domains by transferring knowledge from high-resource domains. While recent advancements in Large L…

cs.LG2025★ 1 cited

Foundation Models for CPS-IoT: Opportunities and Challenges

Ozan Baris, Yizhuo Chen, Gaofeng Dong +9

Methods from machine learning (ML) have transformed the implementation of Perception-Cognition-Communication-Action loops in Cyber-Physical Systems (CPS) and the Internet of Things…

cs.LG2024

MMBind: Unleashing the Potential of Distributed and Heterogeneous Data for Multimodal Learning in IoT

Xiaomin Ouyang, Jason Wu, Tomoyoshi Kimura +4

Multimodal sensing systems are increasingly prevalent in various real-world applications. Most existing multimodal learning approaches heavily rely on training with a large amount…