Francesco Locatello shows AI plus causal inference replacing manual experiment analysis
FrancescoLocat8 · x · 2026-10-26
At the CBR AI Conclave, Prof. Francesco Locatello presented how AI can change drawing conclusions from experimental data: hand analysis is slow and bias-prone, while prediction-powered causal inference — using post-trained CLIP-ViT-L on ant videos as an automatic measurement instrument with Augmented Inverse Propensity Weighting (Robins et al. 1994) — yields asymptotically correct causal-effect confidence intervals, outperforming vanilla fine-tuning per NeurIPS 2024/25 work from the Cadei/Schmid group.
More from Research
- World models matter even without realtime: closed loops and persistent memory — cocktailpeanut · 2026-10-27
- EMNLP paper probes why some LLM biases survive rewording while others don't — radamihalcea · 2026-10-27
- MS-Human-700: open-source human model with 700 muscle actuators lands in MuJoCo — yisongyue · 2026-10-27
- Datology webinar: Curation Studio matched top data baselines with under 20% compute — josh_wills · 2026-10-27
- KANLab: an interactive browser playground for Kolmogorov-Arnold Networks — Lukas Niehaus · 2026-10-27
- CMU's LLM2Cert synthesizes stability certificates verified via SMT and Lean — CarnegieMellonU · 2026-10-27