README
⚡
AI & ML interests
Planetary causal inference // Text-based AI systems // Adversarial dynamics
Recent Activity
View all activity
Papers
Multiplication in Multimodal LLMs: Computation with Text, Image, and Audio Inputs
Detecting and Mitigating Treatment Leakage in Text-Based Causal Inference: Distillation and Sensitivity Analysis
cjerzak
updated a
Space 1 day ago
cjerzak
authored a
paper 5 days ago
cjerzak
submitted a
paper to Daily Papers 6 days ago
Post
741
Ethos: In our team at UT Austin, we train students to become full-stack researchers—and increasingly, designers of the systems that do research. Our students learn to carry projects end-to-end: from idea generation and theory to data creation, analysis, and iterative refinement across diverse subfields. Using modern AI (including agentic workflows) and scalable computation, students build reproducible pipelines that can ingest and update planetary-scale data—like satellite imagery and other high-dimensional sources. But the goal isn’t tool use for its own sake: students learn to set the objectives, constraints, and evaluation standards that guide these systems through large spaces of hypotheses, while grounding results in causal inference and careful measurement. The outcome is scholarship that can rigorously test policy counterfactuals and translate evidence into durable, responsible improvements in societal well-being.
We welcome students at every stage to engage with projects—from motivated high-schoolers to undergraduates, graduate students, and those from highly non-traditional backgrounds.
Join us! https://connorjerzak.com/students/
We welcome students at every stage to engage with projects—from motivated high-schoolers to undergraduates, graduate students, and those from highly non-traditional backgrounds.
Join us! https://connorjerzak.com/students/
- 2 replies
cjerzak
authored 2
papers 3 months ago
Post
2898
>>> We're writing a new book, <Planetary Causal Inference>, on how to model counterfactuals at planetary scale by combining satellite imagery + other global data with local studies and RCTs. Forthcoming in 2026+.
>>> Book info: https://planetarycausalinference.org/book-launch
>>> All datasets used in the book will be openly available on our lab’s Hugging Face hub:
theaidevlab
>>> Book info: https://planetarycausalinference.org/book-launch
>>> All datasets used in the book will be openly available on our lab’s Hugging Face hub:
cjerzak
authored 2
papers 7 months ago
Remote Auditing: Design-based Tests of Randomization, Selection, and Missingness with Broadly Accessible Satellite Imagery
Paper • 2510.00128 • Published
Chinese vs. World Bank Development Projects: Insights from Earth Observation and Computer Vision on Wealth Gains in Africa, 2002-2013
Paper • 2509.25648 • Published
Post
278
Excited to share LinkOrgs Online, a web app hosted here on HF for embedding and linking organization names using character-level Transformer encoder models trained on half a billion scraped LinkedIn records.
Upload CSVs or paste text, generate 1024D embeddings (v1–v4), PCA viz, and download results!
Try it: cjerzak/LinkOrgs_Online
Details/paper: https://connorjerzak.com/linkorgs-summary/
Training/inference code: https://github.com/cjerzak/LinkOrgs-software
Upload CSVs or paste text, generate 1024D embeddings (v1–v4), PCA viz, and download results!
Try it: cjerzak/LinkOrgs_Online
Details/paper: https://connorjerzak.com/linkorgs-summary/
Training/inference code: https://github.com/cjerzak/LinkOrgs-software
Post
371
Just dropped IWI-Africa: 69k DHS clusters linked with satellite imagery + agent/LLM text so you can predict wealth from space and the web. Poke the vision-language-agentic convergence yourself.
Hugging Face: theaidevlab/IWI-Africa-Multimodal
Paper: https://arxiv.org/abs/2508.01109.
Hugging Face: theaidevlab/IWI-Africa-Multimodal
Paper: https://arxiv.org/abs/2508.01109.
cjerzak
updated 2
collections 9 months ago
cjerzak
authored 3
papers 9 months ago
Attenuation Bias with Latent Predictors
Paper • 2507.22218 • Published • 1
Platonic Representations for Poverty Mapping: Unified Vision-Language Codes or Agent-Induced Novelty?
Paper • 2508.01109 • Published • 4
Debiasing Machine Learning Predictions for Causal Inference Without Additional Ground Truth Data: "One Map, Many Trials" in Satellite-Driven Poverty Analysis
Paper • 2508.01341 • Published • 1
cjerzak
updated a
dataset 9 months ago
cjerzak
updated 2
collections 9 months ago
Post
267
Global Leadership Project v1 dataset released: 50k+ political elites, 156 countries, hand-coded. v2 in progress.
HF link: cjerzak/GlobalLeadershipProject_v1
HF link: cjerzak/GlobalLeadershipProject_v1