A technical but accessible note on why encoder-decoder T5 architectures matter for polymer property prediction, conditional generation, molecule-text translation, and materials discovery workflows.
A note on our Applied Physics A paper showing why load-dependent experimental data can matter more than DFT-derived hardness proxies for Vickers hardness prediction.
A first note on POLYT5, a polymer-native encoder-decoder language model for property prediction, conditional generation, and high-temperature dielectric polymer design.
