@article{llmforgemultibackendhardwareawareneurala,
  title = {LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models},
  author = {Xinting Jiang and Junyi Luo and Ruichen Qi and Kauna Lei and Ben Laurie and Gregory Kielian and Mehdi Saligane},
  year = {2026},
  eprint = {2605.17653},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.17653},
}