💡 Our findings highlight the urgent need for widespread testing and active monitoring of exposed passengers in confined travel settings to prevent sustained transmission. 🛡️
🔗 Read the full paper on arXiv here: https://t.co/dkYWXZX9Kh (4/4)
🚨You may already know or you may not know yet, but a new variant of Hantavirus has spread for weeks on a cruise on the Atlantic🚢with 8 cases already identified and 3 cases already dead🦠. Will this become the next COVID?😷
📢 I am excited to share our latest preprint (1/4)
⚠️ Relying solely on symptom-based surveillance is not enough - our model shows that several exposed individuals remain undetected during the early outbreak phase, creating a hidden reservoir for the virus. 🕵️♂️ (3/4)
where we developed a stochastic SEIRD model to estimate the hidden transmission dynamics aboard the ship. 📊
🔍 Key findings from our early analysis:
📈 We estimate a basic reproduction number (R0) of 2.76 (95% CI: 2.52-2.99) on the ship. (2/4)
Our initial work on bridging LLM-based multi-agent systems with well-established mechanistic modeling frameworks. Proposing directions in combining the flexibility of ML for individual-level data with the explainability and reliability of mechanistic models.
🚀 Introducing PhysicsAgentABM!
We propose a novel Physics-Guided Generative Agent Based Modeling framework for scalable and calibrated simulation of complex social systems!
⚡ 6.7x fewer API calls, 2.1-3.4x cost reduction
🎯 Superior temporal accuracy across all domains (EETE, ET-F1)
📊 Calibrated uncertainty (near-diagonal reliability curves)
🔄 Robust to regime shifts (policy shocks, market crashes, viral events)
Huge kudos to my collaborator @inhan_y , Prof. @LiJundong and my advisor @jiamingcui1997!
We’ll be giving a tutorial on “AI-Driven Multimodal Frameworks for Healthcare Decision-Making” at ICDM 2025! @jiamingcui1997,@xwang174,@zhezeng0908,@du_hongru
Time & Location: Thursday, Nov 13, 10:30 AM – 12:30 PM, Ohio Room
Looking forward to connecting with many of you there!
I am at #ICML24 all week. Catch me at my poster session:
What: Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learning
When: Wed 24 Jul 11:30 a.m. — 1 p.m. CEST
Where: Hall C 4-9 #2200
Paper: https://t.co/dQRufCBgIh
Code: https://t.co/yKCsUggkam
Catch Haoxin @icmlconf 2024 in Vienna, presenting our work on out of distribution generalization (OOD) in time-series forecasting. Get OOD robustness for *any* forecasting method via invariant learning using FOIL, our new model agnostic framework! https://t.co/9kbWf9R0YS
@GTCSE
(1/3): Congrats to Dr. @jiamingcui1997 who just defended his thesis on cutting edge ML and Epi Models for surveillance&control in clinical settings!! Pleasure advising and learning with+from you. Next: Asst. Prof. @VT_CS after a short stay @UVA_BI 🥳🎉
@GTCSE@gtcomputing@mlatgt
1/3 I am excited to share that I will join @virginia_tech CS @VT_CS as a tenure-track assistant professor starting from Spring 2025.
I will continue my research in machine learning and modeling, aiming to bridge public health and clinical decisions!
@GTCSE@mlatgt@gtcomputing
@badityap@bijayaAdh@_arodriguezca @Kong_GT 3/3 I am actively seeking PhD students to join my research group at @VT_CS. Please feel free to reach out to me or help me spread the message.
Looking forward to the new adventure.
2/3 Thanks to my advisor @badityap, and the mentors and friends who helped me in the job search. Partial list: Anil Vullikanti, @bijayaAdh, @_arodriguezca, @Kong_GT
We're excited to announce that the Epi meets Data workshop will be held in conjunction with @kdd_news 2024 in Barcelona! We invite submissions of both short and full papers. Make sure to submit by May 28.
#KDD2024#ML#AI#DataScience#PublicHealth#epidemiology
1/3
Thanks for the award, I am really excited to receive it.
I also want to thank my advisor @badityap and collaborators @ Vivek Anand @JackHeavey @AnilVullikanti @GTCSE@gtcomputing@UVA_BI.
Paper: https://t.co/9nXJ8ux9Af
Code: https://t.co/CEC7Fho7jq.
Joint work with my advisor @badityap and collaborators @ VivekAnand @JackHeavey @AnilVullikanti @GTCSE@gtcomputing@UVA_BI. Paper: https://t.co/9nXJ8ux9Af Code: https://t.co/CEC7Fho7jq. 3/3
We will present our new @SIAMDataMining paper “H2ABM: Heterogeneous Agent-based Model on Hypergraphs to Capture Group Interactions” on Friday, April 19 (https://t.co/s8OkfkZKxU). 1/3
We introduce the idea of hypergraphs into complex agent based models for epidemics and use it for real-world healthcare-associated infection MRSA outbreaks in hospitals - better explanations of past spread and better forecasting as well! Welcome to attend & discuss with us! 2/3