Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation

• URL: http://arxiv.org/abs/2510.23123v1
• Date: Mon, 27 Oct 2025 08:57:24 GMT
• Title: Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation
• Authors: Shiwei Li, Xiandi Luo, Haozhao Wang, Xing Tang, Ziqiang Cui, Dugang Liu, Yuhua Li, Xiuqiang He, Ruixuan Li,
• Abstract summary: Low-rank adaptation (LoRA) is a parameter-efficient fine-tuning (PEFT) method widely used in large language models (LLMs)<n>In standard LoRA, all input tokens share the same weights and undergo an identical input-output projection.<n>TopLoRA dynamically adjusts LoRA weights according to the input token, thereby learning token-wise input-output projections.
• Score: 30.618404778567776
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Low-rank adaptation (LoRA) is a parameter-efficient fine-tuning (PEFT) method widely used in large language models (LLMs). LoRA essentially describes the projection of an input space into a low-dimensional output space, with the dimensionality determined by the LoRA rank. In standard LoRA, all input tokens share the same weights and undergo an identical input-output projection. This limits LoRA's ability to capture token-specific information due to the inherent semantic differences among tokens. To address this limitation, we propose Token-wise Projected Low-Rank Adaptation (TopLoRA), which dynamically adjusts LoRA weights according to the input token, thereby learning token-wise input-output projections in an end-to-end manner. Formally, the weights of TopLoRA can be expressed as $B\Sigma_X A$, where $A$ and $B$ are low-rank matrices (as in standard LoRA), and $\Sigma_X$ is a diagonal matrix generated from each input token $X$. Notably, TopLoRA does not increase the rank of LoRA weights but achieves more granular adaptation by learning token-wise LoRA weights (i.e., token-wise input-output projections). Extensive experiments across multiple models and datasets demonstrate that TopLoRA consistently outperforms LoRA and its variants. The code is available at https://github.com/Leopold1423/toplora-neurips25.

Related papers

• Beyond SGD, Without SVD: Proximal Subspace Iteration LoRA with Diagonal Fractional K-FAC [50.36542772932594]
  Low-Rank Adaptation (LoRA) fine-tunes large models by learning low-rank updates on top of frozen weights.<n>In this work, we address the gap between training with full steps with low-rank projections (SVDLoRA) and LoRA fine-tuning.<n>We propose LoRSum, a memory-efficient subroutine that closes this gap for gradient descent.
  arXiv  Detail & Related papers  (2026-02-18T13:41:41Z)
• Faster Than SVD, Smarter Than SGD: The OPLoRA Alternating Update [50.36542772932594]
  Low-Rank Adaptation (LoRA) fine-tunes large models by learning low-rank updates on top of frozen weights.<n>There is still a gap between full training with low-rank projections (SVDLoRA) and LoRA fine-tuning, indicating that LoRA steps can be further improved.
  arXiv  Detail & Related papers  (2025-09-24T10:32:50Z)
• Uni-LoRA: One Vector is All You Need [21.893406288629734]
  Low-Rank Adaptation (LoRA) has become the de facto parameter-efficient fine-tuning (PEFT) method for large language models.<n>Recent works such as Tied-LoRA, VeRA, and VB-LoRA push efficiency further by introducing additional constraints to reduce the trainable parameter space.<n>We show that the parameter space reduction strategies employed by these LoRA variants can be formulated within a unified framework, Uni-LoRA.
  arXiv  Detail & Related papers  (2025-06-01T03:00:09Z)
• GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning [13.657093411434511]
  Low-Rank Adaptation (LoRA) is a popular method for parameter-efficient fine-tuning (PEFT) of generative models.<n>We introduce a novel structure, Granular Low-Rank Adaptation (GraLoRA)<n>GraLoRA partitions weight matrices into sub-blocks, each with its own low-rank adapter.
  arXiv  Detail & Related papers  (2025-05-26T06:48:20Z)
• Activated LoRA: Fine-tuned LLMs for Intrinsics [6.057520371260868]
  Low-Rank Adaptation (LoRA) has emerged as a highly efficient framework for finetuning the weights of large foundation models.<n>We propose Activated LoRA, an adapter architecture which modifies the LoRA framework to only adapt weights for the tokens in the sequence after the aLoRA is invoked.
  arXiv  Detail & Related papers  (2025-04-16T18:03:21Z)
• LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization [78.93425154518705]
  Low-rank adaption (LoRA) is a widely used parameter-efficient finetuning method for LLM that reduces memory requirements.<n>This paper introduces LoRA-RITE, a novel adaptive matrix preconditioning method for LoRA optimization.
  arXiv  Detail & Related papers  (2024-10-27T22:57:12Z)
• LoRA-Pro: Are Low-Rank Adapters Properly Optimized? [121.0693322732454]
  Low-rank adaptation, also known as LoRA, has emerged as a prominent method for parameter-efficient fine-tuning of foundation models.<n>Despite its computational efficiency, LoRA still yields inferior performance compared to full fine-tuning.<n>We introduce LoRA-Pro, a method that enhances LoRA's performance by strategically adjusting the gradients of low-rank matrices.
  arXiv  Detail & Related papers  (2024-07-25T17:57:12Z)
• SBoRA: Low-Rank Adaptation with Regional Weight Updates [19.15481369459963]
  This paper introduces Standard Basis LoRA (SBoRA), a novel parameter-efficient fine-tuning approach for Large Language Models. SBoRA reduces the number of trainable parameters by half or doubles the rank with the similar number of trainable parameters as LoRA. Our results demonstrate the superiority of SBoRA-FA over LoRA in various fine-tuning tasks, including commonsense reasoning and arithmetic reasoning.
  arXiv  Detail & Related papers  (2024-07-07T15:37:13Z)
• LoRA+: Efficient Low Rank Adaptation of Large Models [13.074320303580361]
  We show that Low Rank Adaptation (LoRA) leads to suboptimal finetuning of models with large width (embedding dimension) We then show that this suboptimality of LoRA can be corrected simply by setting different learning rates for the LoRA adapter matrices A and B with a well-chosen ratio. In our experiments, LoRA$+$ improves performance (1-2 $%$ improvements) and finetuning speed (up to $sim$ 2X SpeedUp) at the same computational cost as LoRA.
  arXiv  Detail & Related papers  (2024-02-19T18:33:49Z)
• LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks [72.88244322513039]
  LoRA employs lightweight modules to customize large language models (LLMs) for each downstream task or domain. We propose LoRA-Flow, which utilizes dynamic weights to adjust the impact of different LoRAs. Experiments across six generative tasks demonstrate that our method consistently outperforms baselines with task-level fusion weights.
  arXiv  Detail & Related papers  (2024-02-18T04:41:25Z)
• DoRA: Weight-Decomposed Low-Rank Adaptation [57.68678247436207]
  We introduce a novel weight decomposition analysis to investigate the inherent differences between FT and LoRA. Aiming to resemble the learning capacity of FT from the findings, we propose Weight-Decomposed Low-Rank Adaptation (DoRA) DoRA decomposes the pre-trained weight into two components, magnitude and direction, for fine-tuning.
  arXiv  Detail & Related papers  (2024-02-14T17:59:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.