Publications (19)
CASPIAN: Online Detection and Attribution of Cascade Attacks in LLM Multi-Agent Systems via Cross-Channel Causal Monitoring
Kavana Venkatesh, Jafar Isbarov, Saad Amin +2
Cascade attacks in LLM multi-agent systems (MAS) arise when adversarial influence propagates across agents and leads to escalated system-level failures through complex agent intera…
Autoregressive Diffusion Model for Graph Generation
Lingkai Kong, Jiaming Cui, Haotian Sun +3
Diffusion-based graph generative models have recently obtained promising results for graph generation. However, existing diffusion-based graph generative models are mostly one-shot…
QueenBee Planner: Skill-Evolving Communication Topologies for Token-Efficient LLM Multi-Agent Systems
Congjia Tian, Yuhang Yao, Jiaming Cui
Large language model (LLM) multi-agent systems increasingly depend not only on how individual agents reason, but also on how agents are connected. This paper introduces QueenBee Pl…
EINNs: Epidemiologically-informed Neural Networks
Alexander RodrÃguez, Jiaming Cui, Naren Ramakrishnan +2
We introduce EINNs, a framework crafted for epidemic forecasting that builds upon the theoretical grounds provided by mechanistic models as well as the data-driven expressibility a…
Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysis
Haoxin Liu, Shangqing Xu, Zhiyuan Zhao +8
Time series data are ubiquitous across a wide range of real-world domains. While real-world time series analysis (TSA) requires human experts to integrate numerical series data wit…
Modeling the Impact of Exposed Cases in a Hantavirus Outbreak on a Cruise Ship
Jiaming Cui
The emergence of a hantavirus variant aboard a commercial cruise ship presents a significant public health concern. This study develops a discrete-time stochastic Susceptible-Expos…
Beyond Tier Labels: Role- and Deployment-Dependent Model Substitution in Multi-Call LLM Workflows
Renxiang Wang, Jiaming Cui
Large multi-call LLM systems pose a scientific problem that query-level routing does not capture: the value of a model depends on where it enters a dependent computation and on the…
How (Not) to Hybridize Neural and Mechanistic Models for Epidemiological Forecasting
Yiqi Su, Ray Lee, Jiaming Cui +1
Epidemiological forecasting from surveillance data is a hard problem and hybridizing mechanistic compartmental models with neural models is a natural direction. The mechanistic str…
SAGE-ICP: Semantic Information-Assisted ICP
Jiaming Cui, Jiming Chen, Liang Li
Robust and accurate pose estimation in unknown environments is an essential part of robotic applications. We focus on LiDAR-based point-to-point ICP combined with effective semanti…
TinyDef-DETR: A Transformer-Based Framework for Defect Detection in Transmission Lines from UAV Imagery
Feng Shen, Jiaming Cui, Wenqiang Li +1
Automated defect detection from UAV imagery of transmission lines is a challenging task due to the small size, ambiguity, and complex backgrounds of defects. This paper proposes Ti…
Cross-Modal Purification and Fusion for Small-Object RGB-D Transmission-Line Defect Detection
Jiaming Cui, Wenqiang Li, Shuai Zhou +2
Transmission line defect detection remains challenging for automated UAV inspection due to the dominance of small-scale defects, complex backgrounds, and illumination variations. E…
PhysicsAgentABM: Physics-Guided Generative Agent-Based Modeling
Kavana Venkatesh, Yinhan He, Jundong Li +1
Large language model (LLM)-based multi-agent systems enable expressive agent reasoning but are expensive to scale and poorly calibrated for timestep-aligned state-transition simula…
Accurately Estimating Unreported Infections using Information Theory
Jiaming Cui, Bijaya Adhikari, Arash Haddadan +4
One of the most significant challenges in combating against the spread of infectious diseases was the difficulty in estimating the true magnitude of infections. Unreported infectio…
End-to-End Stochastic Optimization with Energy-Based Model
Lingkai Kong, Jiaming Cui, Yuchen Zhuang +3
Decision-focused learning (DFL) was recently proposed for stochastic optimization problems that involve unknown parameters. By integrating predictive modeling with an implicitly di…
DF2: Distribution-Free Decision-Focused Learning
Lingkai Kong, Wenhao Mu, Jiaming Cui +4
Decision-focused learning (DFL), which differentiates through the KKT conditions, has recently emerged as a powerful approach for predict-then-optimize problems. However, under pro…
Improving Hospital Risk Prediction with Knowledge-Augmented Multimodal EHR Modeling
Rituparna Datta, Jiaming Cui, Zihan Guan +5
Accurate prediction of clinical outcomes using Electronic Health Records (EHRs) is critical for early intervention, efficient resource allocation, and improved patient care. EHRs c…
GraphDC: A Divide-and-Conquer Multi-Agent System for Scalable Graph Algorithm Reasoning
Wenjin Li, Jiaming Cui
Large Language Models (LLMs) have demonstrated strong potential for many mathematical problems. However, their performance on graph algorithmic tasks is still unsatisfying, since g…
Do Agent Societies Develop Intellectual Elites? The Hidden Power Laws of Collective Cognition in LLM Multi-Agent Systems
Kavana Venkatesh, Jiaming Cui
Large Language Model (LLM) multi-agent systems are increasingly deployed as interacting agent societies, yet scaling these systems often yields diminishing or unstable returns, the…
CALYPSO: Forecasting and Analyzing MRSA Infection Patterns with Community and Healthcare Transmission Dynamics
Rituparna Datta, Jiaming Cui, Gregory R. Madden +1
Methicillin-resistant Staphylococcus aureus (MRSA) is a critical public health threat within hospitals as well as long-term care facilities. Better understanding of MRSA risks, eva…