This page collects transcripts of select research talks and tutorials by collaborators and colleagues in our group. Each entry links to the corresponding video and provides a written record of the talk.
The topics span from natural‑language processing – such as using large language models to rewrite text while removing unwanted variables – to novel uses of Earth‑observation data and machine learning for causal inference.
- Nicolas Audinet de Pieuchon presents: Benchmarking Debiasing Methods for LLM-based Parameter Estimates (@EMNLP)
- Nicolas Audinet de Pieuchon presents: Can Large Language Models (or Humans) Disentangle Text? (@NLP+CSS)
- Sam Balter presents: Multiplication in Multimodal LLMs: Computation with Text, Image, and Audio Inputs (@ACL)
- Isaac Corley presents a guest lecture: Cloud-Native GeoAI (@Gov 355M)
- Adel Daoud presents: A First Course in Planetary Causal Inference: Confounding (@IC2S2)
- Adel Daoud presents: From Online Traces to Material Imprints: Articulating a Vision for Planetary Social Computing (@ICSC)
- Adel Daoud presents: Planetary Causal Inference: Overview (@Yale)
- Connor Jerzak presents: Fast Rerandomization Using Accelerated Computing (@SoftwareX)
- Connor Jerzak presents: Seeing Like a Satellite While Learning Across Scales: Remote Audits + Multi-Scale Optimization for Heterogeneity (@Columbia)
- Connor Jerzak presents: MiniMax Learning of Interpretable Factored Stochastic Policies from Conjoint Data, with Uncertainty Quantification (@ICML)
- Connor Jerzak presents: MiniMax Learning of Interpretable Factored Stochastic Policies from Conjoint Data, with Uncertainty Quantification (@UT Dallas & National Chung Hsing University)
- Richard Johansson presents: Conceptualizing Treatment Leakage in Text-based Causal Inference (@NAACL)
- Satiyabooshan Murugaboopathy presents: Platonic Representations for Poverty Mapping: Unified Vision-Language Codes or Agent-Induced Novelty? (@ICSC)
- Satiyabooshan Murugaboopathy presents: Statistical Self-Correction for LLM Reasoning Evaluation Using PPI & DSL
- Markus Pettersson presents: Debiasing ML Predictions for Causal Inference Without Additional Ground Truth Data (@AAAI)
- Kazuki Sakamoto presents: A Scoping Review of Earth Observation and Machine Learning for Causal Inference
- Joe Liang and Xiaolong Yang present: Can AI Count Cashmere Goats? Lessons from a Real Computer Vision Project on the Farm (@Gov 355M)
- Fucheng Warren Zhu presents: Optimizing Multi-Scale Representations to Detect Effect Heterogeneity Using EO and Computer Vision (@CLeaR)
See also [Video Library].
–