Researchers · Interviewed at NeurIPS 2025

Dingling Yao

ISTA

NeurIPS 2025 in San Diego. Causal Representations from Observational Data

NeurIPS 2025 · December 26, 2025 · 15 min

NeurIPS 2025 in San Diego. Causal Representations from Observational Data

In this #NeurIPS 2025 highlight, Dingling Yao (ISTA Austria) presents a compelling framework for evaluating causal representation learning using purely observational data - with a fascinating real-world case study from ecology 🐜

Key insights: • High-performing representations can still fail causal inference • Causal representation learning is a measurement problem • T-MEX score allows researchers to evaluate causal representations without randomized interventions

More from NeurIPS 2025

All event interviews →