Merge pull request #1031 from Parallel-in-Time/bibtex-bibbot-1030-73b8b4a

pint.bib updates

Author: pancetta

_bibliography/pint.bib

@@ -8533,6 +8533,19 @@ @article{AluthgeEtAl2026
 	year = {2026},
 }
 
+@article{GaraiEtAl2026,
+	author = {Garai, Gobinda and Mandal, Bankim C.},
+	doi = {10.1080/00207160.2026.2614077},
+	issn = {1029-0265},
+	journal = {International Journal of Computer Mathematics},
+	month = {January},
+	pages = {1–23},
+	publisher = {Informa UK Limited},
+	title = {Domain decomposition-based space-time preconditioner for the optimal control problem with constraints imposed by the Cahn-Hilliard equation},
+	url = {http://dx.doi.org/10.1080/00207160.2026.2614077},
+	year = {2026},
+}
+
 @article{HeEtAl2026,
 	author = {He, Tingting and Zhai, Tianle and Huang, Xuhang and Li, Min},
 	doi = {10.1016/j.cnsns.2025.109183},
@@ -8547,6 +8560,15 @@ @article{HeEtAl2026
 	year = {2026},
 }
 
+@unpublished{JiangEtAl2026,
+	abstract = {We present a new training methodology for transformers using a multilevel, layer-parallel approach. Through a neural ODE formulation of transformers, our application of a multilevel parallel-in-time algorithm for the forward and backpropagation phases of training achieves parallel acceleration over the layer dimension. This dramatically enhances parallel scalability as the network depth increases, which is particularly useful for increasingly large foundational models. However, achieving this introduces errors that cause systematic bias in the gradients, which in turn reduces convergence when closer to the minima. We develop an algorithm to detect this critical transition and either switch to serial training or systematically increase the accuracy of layer-parallel training. Results, including BERT, GPT2, ViT, and machine translation architectures, demonstrate parallel-acceleration as well as accuracy commensurate with serial pre-training while fine-tuning is unaffected.},
+	author = {Shuai Jiang and Marc Salvado and Eric C. Cyr and Alena Kopaničáková and Rolf Krause and Jacob B. Schroder},
+	howpublished = {arXiv:2601.09026v1 [cs.LG]},
+	title = {Layer-Parallel Training for Transformers},
+	url = {https://arxiv.org/abs/2601.09026v1},
+	year = {2026},
+}
+
 @inproceedings{YodaEtAl2026,
 	author = {Yoda, Ryo and Bolten, Matthias},
 	booktitle = {Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region},