# Towards a Generalizable AI for Materials Discovery: Validation through Immersion Coolant Screening

arXiv: https://arxiv.org/abs/2510.23371 · HTML: https://mlsanity.com/paper/2510.23371/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 32 references that are in the map.
- First posted on arXiv 27 Oct 2025.

## Builds on (most cited first, 5 of 5)

- [Geometrically Aligned Transfer Encoder for Inductive Transfer in Regression Tasks](https://mlsanity.com/paper/2310.06369/) (2023)
- [Materials Discovery with Extreme Properties via Reinforcement Learning-Guided Combinatorial Chemistry](https://mlsanity.com/paper/2303.11833/) (2023)
- [Multitask Extension of Geometrically Aligned Transfer Encoder](https://mlsanity.com/paper/2405.01974/) (2024)
- [Task Addition in Multi-Task Learning by Geometrical Alignment](https://mlsanity.com/paper/2409.16645/) (2024)
- [Scalable Multi-Task Transfer Learning for Molecular Property Prediction](https://mlsanity.com/paper/2410.00432/) (2024)

## Abstract (arXiv)

Artificial intelligence (AI) has emerged as a powerful accelerator of materials discovery, yet most existing models remain problem-specific, requiring additional data collection and retraining for each new property. Here we introduce and validate GATE (Geometrically Aligned Transfer Encoder) -- a generalizable AI framework that jointly learns 34 physicochemical properties spanning thermal, electrical, mechanical, and optical domains. By aligning these properties within a shared geometric space, GATE captures cross-property correlations that reduce disjoint-property bias -- a key factor causing false positives in multi-criteria screening. To demonstrate its generalizable utility, GATE -- without any problem-specific model reconfiguration -- applied to the discovery of immersion cooling fluids for data centers, a stringent real-world challenge defined by the Open Compute Project (OCP). Screening billions of candidates, GATE identified 92,861 molecules as promising for practical deployment. Four were experimentally or literarily validated, showing strong agreement with wet-lab measurements and performance comparable to or exceeding a commercial coolant. These results establish GATE as a generalizable AI platform readily applicable across diverse materials discovery tasks.