TaRA: Training-Aware Low-Rank Adaptation Initialization proposes a new way to initialize LoRA by aligning the gradients of low‑rank factors with those of the full‑rank weight matrix. This approach directly incorporates training dynamics, improving gradient fidelity at the start of fine‑tuning while adding negligible computational cost. Experiments on a variety of challenging fine‑tuning tasks show that TaRA consistently outperforms existing state‑of‑the‑art initialization methods, offering a simple, robust, and scalable solution for effective LoRA initialization.
By Taehyeon Kim, Eunhyeok Park
arXiv:2607. 09757v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) has become a cornerstone of parameter-efficient fine-tuning (PEFT); however, the conventional practice of uniform rank assignment ignores the functional heterogeneity of neural layers.
By Jiaqi Liu, Haidong Kang, Qihui Zhao, Guo Yu
arXiv:2607. 26247v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) fine-tunes large pretrained models at a fraction of the cost of full fine-tuning, but its performance depends strongly on how the adapters are initialized.
By Dianze Liu, Farshid Ghezelbash
arXiv:2606. 10929v1 Announce Type: cross Abstract: Task vectors, LoRA, activation steering, and random search around pretrained weights all suggest that learned behaviour can be controlled by linear directions.
By Irina Piontkovskaia, Sergey Nikolenko
Normalized Low-Rank Adaptation (NoRA) is a lightweight enhancement to the widely used LoRA technique that normalizes the down‑projection matrices during training. By doing so, NoRA stabilizes early optimization dynamics, accelerates convergence, and improves performance across pretraining, supervised fine‑tuning, and reinforcement learning. The method adds no extra trainable parameters or inference‑time cost, making it broadly applicable.
By Jiale Kang, Ziyin Yue, Zheng Zhan, Yangyi Huang, Weiyang Liu
arXiv:2606. 06902v1 Announce Type: new Abstract: Targeted post-training aims to improve reasoning, math, and code without degrading strengths.
By Chengkai Zhang, Ziteng Liu, Junpu Wang, Zeyi Tao, Yang Wang, Sagar Chordia, Qin Huang
arXiv:2602. 20062v2 Announce Type: replace Abstract: Pretraining and fine-tuning are central stages in modern machine learning systems.
By Nicolas Anguita, Francesco Locatello, Andrew M. Saxe, Marco Mondelli, Flavia Mancini, Samuel Lippl, Clementine Domine
Parameter-efficient post-training reduces the number of trainable parameters, but still requires repeated end-to-end backpropagation through the frozen backbone. Every adaptation step therefore needs backward-capable hardware and must store or recompute activations.
arXiv:2606. 16454v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) enables efficient adaptation of large pre-trained models to downstream tasks by parameterizing weight updates with low-rank matrices.
By Junghun Oh, Sungyong Baik, Kyoung Mu Lee
arXiv:2605. 04913v4 Announce Type: replace-cross Abstract: LLM post-training typically propagates task gradients through the full depth of the model.
By Hengyu Shi, Tianyang Han, Peizhe Wang, Zhiling Wang, Xu Yang, Junhao Su
The paper introduces ISO-LoRA, an optimizer that improves rank utilization in Low‑Rank Adaptation (LoRA) by coupling factor updates through spectral descent on the induced tangent perturbation in weight space. Experiments on GPT‑2 adaptation show that standard optimizers like AdamW concentrate updates in a few singular directions, whereas ISO-LoRA distributes energy more evenly, leading to higher effective rank and better downstream performance across 0.1B‑7B models. The authors provide theoretical guarantees under a stylized spiked‑gradient model and demonstrate that ISO-LoRA consistently outperforms factor‑wise optimizers, especially at moderate‑to‑large LoRA ranks.
By Zihan Zhu, Zhehang Du, Xuyang Chen, Tim Tsz-Kit Lau, Jiayuan Wu, X. Y. Han, Qi Long, Weijie Su
arXiv:2608. 03020v1 Announce Type: new Abstract: Parameter-efficient post-training reduces the number of trainable parameters, but still requires repeated end-to-end backpropagation through the frozen backbone.
By Linhan Xia, Rui Liu, Zhaofeng Zhang, Yihao Wang, Binrui Shen, Shengxin Zhu