Author name: Paolo Mandica, Micha{\l} Brzozowski, Zuzanna Dubanowska, Neo Christopher Chung

arXiv:2605.14841v1 Announce Type: cross
Abstract: Low-rank adaptation (LoRA) has become the dominant paradigm for parameter-efficient fine-tuning (PEFT) of large language models (LLMs). However, its bilinear structure introduces a critical limitation:…