Ainkaran Santhirasekaram — accepted AI-conference papers

2025

Counterfactual Identifiability via Dynamic Optimal Transport

Fabio De Sousa Ribeiro, Ainkaran Santhirasekaram, Ben Glocker

NeurIPS 2025poster

We address the open question of counterfactual identification for high-dimensional multivariate outcomes from observational data. Pearl (2000) argues that counterfactuals must be identifiable (i.e., recoverable from the observed data distribution) to justify causal claims. A recent line of work on c…

Cited by 0 Source ↗Scholar ↗

2024

Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention

Avinash Kori, Francesco Locatello, Ainkaran Santhirasekaram, Francesca Toni, Ben Glocker, Fabio De Sousa Ribeiro

NeurIPS 2024poster

Learning modular object-centric representations is said to be crucial for systematic generalization. Existing methods show promising object-binding capabilities empirically, but theoretical identifiability guarantees remain relatively underdeveloped. Understanding when object-centric representations…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗