Jerry Ji

UofT CS PhD student

[Jerry Ji @jerryji2019]

Clinical ML has a generalization problem. The standard playbook: train a model, watch it fail at the next hospital, and retrain it with new tricks. We invert this! Don't change the model—change the input so any model will generalize. Introducing Record2Vec at #ICLR2026! 🔄🚀 1/5

[Jerry Ji @jerryji2019]

Check out our work! 📖
📄 Paper: https://t.co/QlKsl4xVkQ
🌐 Project: https://t.co/vpldjQ3KMm
📍 At #ICLR2026? Come find us at poster P3-#1123!
🗓️ Thursday, April 23 🕙 10:30 AM – 1:00 PM

Come say hi! 👋🇧🇷 #ICLR2026 #HealthAI #MachineLearning #LLMs

[Jerry Ji @jerryji2019]

Clinical ML has a generalization problem. The standard playbook: train a model, watch it fail at the next hospital, and retrain it with new tricks. We invert this! Don't change the model—change the input so any model will generalize. Introducing Record2Vec at #ICLR2026! 🔄🚀 1/5

[Jerry Ji @jerryji2019]

The deployment payoff: one representation, many predictors, many sites. 🏥➡️🏥 Across MIMIC-IV, HiRID, and PPICU, we see smaller performance drops under hospital transfer, stronger few-shot learning, and no added demographic leakage—all without retraining the whole stack! 4/5

[ML4H @SymposiumML4H]

We are underway with our first session:

MEDS: Building Models and Tools in a Reproducible Health AI Ecosystem

Given by Matthew McDermott!

#ML4H2025

[ML4H @SymposiumML4H]

Registration is underway! Find us on the second floor of the Westin San Diego Gaslamp. You can also register now with us at the desk! #ML4H2025

[ML4H @SymposiumML4H]

🚨 Demos Deadline Extended to October 3rd, 11:59pm AoE
This is your chance to showcase mature tools that are making an impact in clinical or health settings.
Accepted demos will be presented live at #ML4H2025, with select submissions featured in talks.
https://t.co/fNPnqL10BT

[Jerry Ji @jerryji2019]

@CHILconference @rahulgk

[Jerry Ji @jerryji2019]

1/7 🚀 Thrilled to announce that our paper ExOSITO: Explainable Off-Policy Learning with Side Information for ICU Lab Test Orders has been accepted to #CHIL2025! Please feel free to come by my poster session this Thursday to chat. #MedAI #HealthcareAI

[Jerry Ji @jerryji2019]

7/7 💡 Huge thanks to our clinical collaborators and ICU data teams! If you're at #CHIL2025 this Thursday, drop by my poster session—happy to demo ExOSITO and gather your feedback. 🙏 #MachineLearning #AI4Health

[Vahid Balazadeh @vahidbalazadeh]

Can neural networks learn to map from observational datasets directly onto causal effects?

YES! Introducing CausalPFN, a foundation model trained on simulated data that learns to do in-context heterogeneous causal effect estimation, based on prior-fitted networks (PFNs). Joint work with @Layer6AI & @hamid_R_kamkar
w/ @_valthomas, Jeremy Ma, Benson Li, Jesse C. Cresswell, & @rahulgk

📝ArXiv: https://t.co/jc9plTMo44
🔗Code: https://t.co/MVO8j24mR8
🗣️Oral paper @ ICML SIM workshop

🧵[1/7]

[Michael Cooper @ ICML @coopermj_aiml]

📢 New Paper at #UAI2023! 🎉

Dependent censoring presents a *common and substantial* source of bias in modern survival analysis. We show how to use copulas to mitigate this bias.

https://t.co/os7Ei8xw8R

So what is dependent censoring? And why is it problematic? 🧵👇 (1/n)

[Vahid Balazadeh @vahidbalazadeh]

There's been a lot of success in causal effect estimation using machine learning. But what if point identification is impossible? Our NeurIPS 2022 paper, "Partial Identification of Treatment Effects with Implicit Generative Models," estimates bounds on causal effects instead. 🧵

[Jerry Ji @jerryji2019]

@elonmusk DOTA2