@article{revisitingtransformerlayerparameterizati, title = {Revisiting Transformer Layer Parameterization Through Causal Energy Minimization}, author = {Jin Xu and Camille Couturier and Victor Rühle and Saravan Rajmohan and James Hensman}, year = {2026}, eprint = {2605.07588}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.07588}, }