Memory-Efficient Fine-Tuning

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, up 67% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 33

Oct 6, 2026cs.LG

MemFLoRA: Memory-Floor LoRA for CNN Adaptation at the Edge

On-device learning is necessary when the model encounters user-,sensor-, or environment-specific shifts after deployment. Although parameter-efficient fine-tuning (PEFT) methods, particularly Low-Rank Adaptation (LoRA) variants, enable efficient adaptation at the edge, the limiting resource for Convolutional Neural Network (CNN) adaptation is often not the number of trainable parameters but the activation state that must be retained until the backward pass. This paper introduces Memory-Floor LoRA (MemFLoRA), a low-rank CNN adapter built around a memory-first design principle rather than a direct application of transformer-oriented LoRA. Instead of merely reducing trainable weights, we define an activation-memory-floor criterion: trainable backward computations must not depend on full-width layer inputs. The resulting adapter freezes the down-projection, trains a scale-matched up-projection, and combines eval-mode backbone normalization with activation-minimal backward rules, reducing saved state to the low-rank branch. Evaluated on three Human Activity Recognition (HAR) datasets and two CNN backbones under subject, body-location, and sensor-placement shifts, MemFLoRA reduces saved-activation memory by 98.5-98.7% and peak training-state memory by 94.9-97.3% relative to full fine-tuning, while matching or exceeding CNN PEFT baselines.

Mehmet Emre Akbulut, Johannes Geier, Ulf Schlichtmann

Technical University of Munich Munich, Germany

On-Device Training Memory-Efficient Fine-Tuning Domain Adaptation Low-Rank Adaptation Convolutional Neural Networks

Oct 5, 2026cs.CL

LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches

Reinforcement learning has greatly advanced the capabilities of large language models, but its memory demands remain a barrier to broader adoption. We introduce LoGRA, an approach to RL post-training that reduces memory by retaining useful learning signals in low-rank gradient sketches. These compact representations support both model updates and efficient policy synchronization. To prevent overly large updates from disrupting learning, we complement gradient compression with predicted-KL step control, which estimates policy changes before applying each update and adjusts its magnitude accordingly. With all techniques combined, LoGRA reduces average training memory usage by up to 45.7% across reasoning tasks without compromising performance. It also enables stable training of a 27B-parameter model for over 1,100 steps on a single eight-GPU node, where dense Adam runs out of memory, making previously memory-infeasible RL training practical. Code is available in the Molt library.

Shaokun Zhang, Yifan Zhang, Jian Hu +5

NVIDIA

Memory-Efficient Fine-Tuning RL for Language Model Reasoning RL Post-Training

Oct 5, 2026cs.LG

RoSA: Rotational Sparse Adaptation for Memory-Efficient Fine-Tuning

Parameter-efficient fine-tuning (PEFT) reduces the cost of adapting foundation models by focusing training on a small parameter subset. Complementary to this idea, we introduce RoSA (Rotational Sparse Adaptation), which narrows adaptation to a subset of layers at a time. RoSA freezes lower layers close to the input throughout training and rotates a trainable block over later layers, progressively increasing the number of frozen layers close to the input. This design reduces optimizer-state memory, shortens backpropagation, and even forward propagation if activations at the last frozen layer are cached. Because RoSA is orthogonal to the choice of trainable parameterization, it can be combined with PEFT methods or sparse optimizers within each active block. Experiments across multiple LLM architectures and tasks show that RoSA reduces peak memory while maintaining strong fine-tuning performance.

Muhammad Azeem Lodhi, Chao Zhou, Rebekka Burkholz

Saarland University, Saarbrücken, Germany · CISPA Helmholtz Center for Information Security, Saarbrücken, Germany

Memory-Efficient Fine-Tuning LLM Fine-Tuning Sparse Fine-Tuning Parameter-Efficient Fine-Tuning

Oct 1, 2026cs.LG

TACO: Ternary Absolute-max Column-wise One-sparse Optimizer for LLM Fine-Tuning

Full-parameter fine-tuning of large language models (LLMs) incurs substantial optimizer state memory overhead, limiting the model sizes that fit on modern GPUs. Existing approaches either compress optimizer state, abandon first-order gradients, or change the update geometry while retaining dense state. The recently introduced Muon optimizer reduces optimizer memory through matrix-valued updates. Still, its geometry differs from AdamW and can lead to performance degradation when fine-tuning AdamW-pretrained models. To reduce optimizer memory without sacrificing accuracy or computational efficiency in LLM fine-tuning, we propose Ternary Absolute-max Column-wise One-sparse optimizer, or TACO, which follows Muon's operator-norm steepest-descent view but takes the geometric route further. TACO computes the exact steepest-descent direction under a dimension-normalized

1\to1

operator norm by selecting the sign of the largest magnitude entry in each column of two-dimensional weight matrices. This retains first-order gradients while making optimizer state memory nearly negligible. Our practical TACO optimizer maintains only a small set of low precision gradient components per column, reducing persistent optimizer state by

174\times

relative to AdamW8bit (from 27.7 GB to 0.16 GB) and peak training memory by

2.9\times

(from 80.6 GB to 27.5 GB) on OPT-13B, while achieving comparable accuracy and runtime. TACO further enables full-parameter fine-tuning of 30-32B-parameter models on a single 80 GB H100 GPU across multiple model families and tasks.

Jichao Jiang, Cristian McGee, El Houcine Bergou +2

University of Central Florida · Mohammed VI Polytechnic University

Memory-Efficient Fine-Tuning LLM Fine-Tuning

Oct 1, 2026cs.AI

FedLore: Communication and Memory Efficient Federated Learning via Shared Gradient Low-Rank Projection

Federated training of foundation models is constrained by client memory and communication costs. LoRA-based methods reduce these costs through low-rank adapters, but their fixed rank budget can limit adaptation. Gradient low-rank optimization offers greater flexibility, yet independently chosen client subspaces create a problem we term \emph{subspace fragmentation}: local projections interact with data heterogeneity to bias aggregated directions, while aggregation can increase update rank and communication cost. Thus, accurate local gradient compression need not preserve global descent. We propose \texttt{FedLore}, which shares a low-rank optimization basis within each round and refreshes it across rounds. The shared basis enables exact aggregation in low-rank coordinates and eliminates the identified projection bias. Subspace refresh allows the accumulated model update to exceed the per-round rank budget. We characterize the aggregation bias and establish an

O(T^{-1/2})

stationarity bound for the projected-SGD variant under a global-gradient coverage condition and standard smoothness and variance assumptions, with bounded gradient heterogeneity. Experiments on vision and language tasks, including federated pre-training, show that \texttt{FedLore} outperforms the evaluated low-rank adapter baselines and matches or exceeds full-parameter training, while reducing communication and optimizer-state memory.

Junkang Liu

Tianjin University

Federated Learning Aggregation Memory-Efficient Fine-Tuning Communication-Efficient Distributed Training Federated Learning

Sep 28, 2026cs.LG

AIM-ZO: Activation-Informed Subspace Maintenance for Zeroth-Order LLM Fine-Tuning

Zeroth-order (ZO) optimization offers a memory-efficient alternative for LLM fine-tuning by estimating updates only from forward evaluations of perturbed parameters, without backpropagation or activation storage. However, in billion-parameter LLMs, isotropic perturbations often waste many forward evaluations on weakly informative directions. To make these evaluations more informative, existing ZO methods restrict perturbations to low-dimensional subspaces. Yet the quality of these subspaces is critical: overly compressed or poorly maintained spaces can miss useful update directions. To obtain a high-quality subspace for ZO updates, this paper proposes AIM-ZO, a ZO fine-tuning method based on Activation-Informed Subspace Maintenance. AIM-ZO uses forward activations as local directional information and continuously integrates them into a broad, evolving subspace over training. To access broader gradient-relevant structure while keeping individual perturbations low-dimensional, AIM-ZO activates only a smaller set of shared and sampled directions, decoupling the maintained width from the active width. We evaluate AIM-ZO across 5 LLMs and 11 downstream tasks under matched forward-evaluation budgets; its six-task average exceeds the strongest fully evaluated ZO baseline by 1.26 percentage points on OPT-2.7B and MeZO by 2.85 percentage points on OPT-30B. Our code is available at https://github.com/EkkoXy/AIM-ZO

Yue Xie, Zhi Zheng, Yunpeng Ba +5

Southern University of Science and Technology · National University of Singapore · Huawei Technologies Ltd. +1

Memory-Efficient Fine-Tuning Zeroth-Order Optimization LLM Fine-Tuning

Sep 27, 2026cs.LG

TerMeZO: Ternary Sparse Zeroth-Order Optimization for Fine-tuning BitNet Models at the Edge

Fine-tuning anguage models (LLMs) with first-order optimizers requires a memory several times larger than that required for inference. Memory-efficient zeroth-order optimization (MeZO) sidesteps this cost by estimating gradients from forward passes only. However, for BitNet architectures, a family of LLMs with ternary {-1,0,1} weights and 8-bit activations, fine-tuning requires updating full-precision latent weights, and thus the memory footprint of MeZO no longer matches that of inference. A promising solution is to finetune only a subset of the latent weights, but existing sparse zeroth-order (ZO) methods either ignore the ternary structure or require first-order gradient information to build a sparse mask, which is at odds with the purpose of ZO fine-tuning. We propose TerMeZO, a sparse MeZO scheme that exploits the geometry of the ternary quantizer itself to identify the latent weights that are more likely to change values during fine-tuning, at no additional data or memory cost. Our convergence analysis shows that TerMeZO can converge faster than full-parameter MeZO, owing to its optimized reduction of the fine-tuning effective dimension. We run extensive experiments on BitNet models ranging from 1B to 3B parameters, spanning classification, instruction-following, and mathematical reasoning tasks. TerMeZO matches or exceeds the performance of full-parameter MeZO while substantially reducing the fine-tuning memory footprint.

Houssem Sifaou, Prabodh Katti, Bipin Rajendran +1

Institute for Intelligent Networked Systems, Northeastern University London, UK

Memory-Efficient Fine-Tuning Zeroth-Order Optimization Sparse Fine-Tuning Edge AI

Sep 7, 2026cs.LG

MpSub: A Momentum $p$ -Dimensional Subspace Trust-Region Method for Derivative-Free Fine-Tuning of Large Language Models

Full-parameter fine-tuning of large language models has substantial memory costs because backpropagation stores activations and gradients. Zeroth-order optimization avoids this by estimating update directions from loss evaluations, but existing methods require tuning a sensitive learning rate for each model and task. We propose the momentum

p

-dimensional subspace trust-region method (MpSub). At each iteration, MpSub searches within a

p

-dimensional subspace: one direction preserves historical momentum from the most recent accepted step, while the remaining directions explore via fresh random sampling. The subspace gradient is estimated by central differences, a trial step is computed from a linear trust-region model, and the trust-region radius adapts according to the agreement between predicted and observed loss reduction, eliminating the learning rate. For LLM fine-tuning, evaluations within an iteration share a minibatch, and directions are regenerated in place from seeds, using forward passes alone. For smooth deterministic objectives under unorthogonalized Gaussian directions, we bound the finite-difference error, quantify gradient energy captured by the subspace, and prove that

\lim_{k\to\infty} \|\nabla f(x_k)\|_2 = 0

almost surely under a safeguarded radius update. Under a matched budget of 8,400 training-objective forward passes, we fine-tune OPT-125M and OPT-350M on CommitmentBank. With the same preset parameters at both model sizes, MpSub attains mean test accuracies of 0.673 and 0.690 over three seeds, matching tuned MeZO (0.685) without any learning-rate search.

Yuyang Wang, Haoyu Yao, Pengcheng Xie

Xi’an Jiaotong University, Xi’an, China · Lawrence Berkeley National Laboratory, Berkeley, CA, USA

Memory-Efficient Fine-Tuning Zeroth-Order Optimization LLM Fine-Tuning Trust-Region Optimization

Sep 1, 2026cs.LG

Frozen Cores Need Task Signal: Fisher-Whitened Cross-Covariance for Low-Resource LLM Adaptation

Parameter-efficient fine-tuning is usually framed as a question of how many parameters to update. Under a severe trainable-state budget, however, where those coefficients act is equally consequential. We study this choice through frozen-core adaptation: a calibration pass fixes left and right bases for each weight matrix, and fine-tuning optimizes only an

r\times r

core. This removes the ability of trainable factors to repair a poor initial span and makes subspace quality directly observable. We introduce FCCA, which estimates the signed input--error cross-covariance, whitens it with diagonal Fisher moments, truncates it in the resulting local metric, maps the selected directions back, and applies thin QR to obtain stable core coordinates. Under a matched

r^2

budget, we compare eight basis constructors on 11 tasks, four model settings, and three seeds. On Qwen2.5-3B, FCCA reaches an 83.0 macro-average, 2.3 points above the next-best matched-budget constructor, and exceeds its unwhitened RawGrad control on all 11 tasks. It ranks first at all three Qwen scales and finishes within 0.13 points of the best method on Llama-3.2-1B. Controlled ablations show gains of 2.7--17.2 points from whitening and identify QR as necessary for stable core optimization in the tested regime. Finally, FCCA comes within 0.32 and 0.23 average points of LoRA and DoRA while optimizing 36.9K rather than roughly 7.4M parameters. These results show that a carefully selected fixed span can recover most of the benefit of movable low-rank factors at a much smaller trainable and optimizer-state cost.

Wentao Ye, Zhanming Shen, Zhiqing Xiao +3

Zhejiang University · Hunyuan, Tencent

Memory-Efficient Fine-Tuning LLM Fine-Tuning Low-Rank Adaptation Parameter-Efficient Fine-Tuning

Aug 16, 2026cs.LG

SubZero+: Memory-Efficient Adaptive Zeroth-Order LLM Fine-Tuning in Random Subspaces

Zeroth-order (ZO) optimization with SGD in random subspaces enables memory-efficient fine-tuning of large language models without backpropagation. However, high gradient estimation noise fundamentally undermines adaptive optimizers like Adam. We propose SubZero+, which achieves practical adaptive ZO optimization through a carefully designed dual low-dimensionality strategy: (i) multi-query forward-difference gradient estimation in periodically refreshed random subspaces to mitigate noise amplification in moment buffers, and (ii) Adam updates with periodic restarts performed directly in low-dimensional space rather than full-parameter space. In experiments, this dual design retains memory overhead comparable to momentum-free ZO methods while achieving stronger optimization performance than the evaluated ZO baselines. Theoretically, in the exact-directional limit,

K

-query averaging preserves conditional unbiasedness, while the coefficient estimator's covariance and mean-squared error, as well as query-induced second-moment inflation, scale exactly as

1/K

. Extensive experiments across SuperGLUE with models from 1.3B to 32B parameters under both full fine-tuning and LoRA schemes demonstrate consistent improvements over competing ZO methods. SubZero+ significantly narrows the performance gap with first-order optimization while preserving ZO's inference-time memory efficiency.

Ziming Yu, Shuyao Xiao, Xingyu Zhao +6

Beijing Normal University · Singapore Management University · Xiaomi Inc. +2

Memory-Efficient Fine-Tuning Zeroth-Order Optimization LLM Fine-Tuning Memory-Efficient Optimization

Aug 12, 2026cs.CV

Curvature-Aware Zeroth-Order Optimization for Memory-Efficient Test-Time Adaptation

Test-time adaptation (TTA) aims to enhance the cross-domain performance of pre-trained models by adapting to unlabeled test data. While most existing TTA methods rely on backpropagation (BP) for finetuning, BP-free methods such as zeroth-order (ZO) methods are more desired in practical on-device scenarios. ZO methods rely only on forward computation, which can largely reduce the complexity and memory overhead of on-device deployment. However, ZO methods suffer from much higher variance compared with first-order methods in estimating the gradient. To address this, we propose an improved ZO method to substantially boost the performance of ZO optimization based TTA. First, we provide an observation to reveal the persistent low-rank Hessian structure of the loss during the adaptation process. Based on this insight, we then propose a loss-landscape curvature-aware zeroth-order (CAZO) method, which leverages a sliding-average estimation of the diagonal Hessian to construct a covariance matrix for anisotropic perturbation sampling. CAZO operates by freezing pretrained weights and optimizing minimal adapter parameters via forward-only passes based gradient estimation, which can substantially reduce the memory overhead compared to BP-based methods. Extensive experiments demonstrate that CAZO significantly outperforms existing TTA methods, achieving state-of-the-art performance while maintaining an excellent balance between accuracy and memory efficiency. Code is available at https://github.com/Hollyming/CAZO.

Junming Zhang, Shuyu Yin, Peilin Liu +2

Shanghai Jiao Tong University, China

On-Device Training Test-Time Adaptation Memory-Efficient Fine-Tuning Zeroth-Order Optimization

Aug 8, 2026cs.LG

ZeroLock: Concurrent Memory-Efficient LLM Training via Modular Update Decoupling

Large language model (LLM) fine-tuning at the edge adapts the model to scenario-specific data while preserving privacy. Although existing studies proposed pipeline parallelism to address the limited memory and computing resources of edge devices, they commonly rely on backpropagation (BP) training, which has a fundamental limitation of update locking and could experience severe throughput and memory bottlenecks. In this work, we propose a BP-free algorithm, called ZeroLock, that decouples the model updates into independent chunk updates by local objective construction. It breaks the update locking of BP and hence can improve throughput at the algorithm level and lower memory usage by reducing activation storage. To the best of our knowledge, we provide the first theoretical framework for such local objective construction-based approaches under general model chunk division by mapping local objectives to the global objective. We prove that ZeroLock has a convergence rate of

\tilde{\mathcal{O}}(1/\sqrt{T})

, which differs from BP only by polylogarithmic factors. We design a system for ZeroLock and build real-world prototypes, incorporating techniques such as early forwarding and failure recovery for efficient and robust implementation. Experiments on the prototype show that compared to BP-based baselines, ZeroLock reduces the memory by 26.5% and improves throughput by 4.9%.

Wentao Dai, Xuanran Li, Yuxiang Zhang +2

Department of Computer Science and Engineering, Southern University of Science and Technology, China · Department of Mathematics, Southern University of Science and Technology, China · School of Computing, Montclair State University, New Jersey, USA

On-Device Training Memory-Efficient Fine-Tuning LLM Fine-Tuning Neural Network Optimization Memory-Efficient Optimization Memory-Efficient Training

Aug 5, 2026cs.CL

Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs

Despite rapid advances in large language models (LLMs), deploying and personalizing them on resource-constrained devices remains impractical due to high VRAM, time, and energy costs. Parameter-Efficient Fine-Tuning (PEFT) of Small Language Models (SLMs) offers a promising alternative, yet few studies compare PEFT methods across architectures using both general and personalization benchmarks while accounting for energy consumption. We compare five fine-tuning approaches (Full Fine-Tuning, LoRA, LoRA+, QLoRA, and BitFit) on four SLMs from two families (Transformer-based: TinyLlama-1.1B, Qwen3-1.7B; SSM-based: Mamba-1.4B, Mamba-2-1.3B) across three GLUE tasks (SST-2, QNLI, STS-B) and three LaMP personalization tasks (LaMP-1, LaMP-2, LaMP-3). Each configuration is evaluated with the energy-focused NetScore-E and the memory-focused NetScore-M, the two variants that reflect the constraints binding on-device deployment. Methods are selected with a strict energy-first rule (highest NetScore-E, ties broken by NetScore#). LoRA+ achieves the highest NetScore-E in 19 of 24 configurations and the highest NetScore-M in 13 of 24, and is the selected method in 18 of 24. QLoRA, available only for the Transformer models, cuts peak finetuning VRAM by up to 3.9x relative to LoRA and therefore takes the best NetScore-M in 5 of the 12 Transformer configurations, although its de-quantization overhead leaves it selected in only one of them once energy decides. BitFit and full fine-tuning are almost never competitive on either variant, and TinyLlama-1.1B leads the energy-focused NetScore-E on five of the six benchmarks and the memory-focused NetScore-M on four. These results show that compact SLMs paired with PEFT provide a practical, energy-aware path to personalized on-device deployment, with the optimal method set by the dominant constraint: LoRA+ for energy and QLoRA for memory.

Kuanysh Akhmetzhanov, Jurn-Gyu Park

Department of Computer Science, Nazarbayev University, Astana 010000, Kazakhstan

Fine-Tuning On-Device Language Model Inference Memory-Efficient Fine-Tuning Energy-Efficient ML Small Language Models Personalized Language Models+2

Aug 4, 2026cs.LG

Pin Once, Swap Light: Subspace-Aligned Centroid-Residual Training for Efficient Ultra-LoRA Serving

Modern multi-tenant Low-Rank Adapters (LoRAs) serving systems concurrently host tens to hundreds of LoRA adapters. Though powerful, this introduces a critical system dilemma between serving efficiency and task performance: higher-rank adapters generally achieve better downstream task performance, but their GPU VRAM footprint and Host-to-Device PCIe swapping overhead severely constrain scalability. Conversely, ultra-low-rank adapters (

r \le 2

) minimize both VRAM footprint and PCIe transfer overhead, but suffer from downstream task performance degradation. To solve this problem, we propose Subspace-Aligned LoRA Training (SALT), a serving efficiency-aware hierarchical fine-tuning framework. Our solution operates in three phases. First, a provider jointly trains high-capacity domain centroids on public data within the domain using a novel alignment regularizer that coheres in-domain task subspaces into a unified basis. Next, users fine-tune ultra-low-rank task residual adapters on private data atop those frozen centroids. Finally, during inference, the provider pins the centroid in GPU VRAM and dynamically swaps in each user's task residual on demand. Across LLMs of varying scales, SALT recovers high-rank accuracy using

r \le 2

residuals, achieving up to 18.5% absolute accuracy gains over state-of-the-art compression baselines and reducing per-adapter memory by up to 16x. When integrated into vLLM, SALT improves serving throughput by up to 51% under PCIe bandwidth pressure and 28% under GPU VRAM constraints for Llama-3.2-3B.

Xiang Li, Pengcheng Wang, Huazheng Wang +1

1Purdue University · 2Oregon State University

LLM Inference Efficiency LLM Serving Memory-Efficient Fine-Tuning Low-Rank Adaptation Low-Rank Compression Parameter-Efficient Fine-Tuning

Aug 4, 2026cs.LG

Noise-Aware Shrinkage for Differentially Private Zeroth-Order Fine-Tuning of Large Language Models

Differentially private zeroth-order optimization (DP-ZO) enables memory-efficient private fine-tuning of large language models using only forward evaluations. Existing aggregation-based DP-ZO methods reconstruct model updates at a fixed scale, ignoring that the strength of useful signals varies throughout training. Consequently, noise-dominated updates may receive excessive weight and degrade model utility. To address this issue, we propose SAGE, a noise-aware shrinkage method that adaptively attenuates privatized estimates according to their estimated signal quality. SAGE subtracts the known Gaussian noise variance from the observed second moment to estimate the underlying signal energy, stabilizes this estimate through temporal tracking, and compares its current signal-to-noise level with a warm-up reference to derive a bounded shrinkage factor. As pure post-processing, SAGE requires neither additional privacy budget nor model queries and introduces only constant additional state. Our theoretical analysis shows that shrinkage reduces the quadratic update-risk term faster than the linear descent term, preserving useful descent while limiting the influence of noise-dominated updates. Experiments on RoBERTa-large, OPT-1.3B, and OPT-6.7B demonstrate that SAGE outperforms existing baselines in most settings under the same privacy budgets while preserving the forward-only memory efficiency of DP-ZO.

Lele Zheng, Weifeng Kong, Xinyi Zhang +3

School of Computer Science and Technology, Xidian University

Memory-Efficient Fine-Tuning Privacy-Preserving Language Models Zeroth-Order Optimization LLM Fine-Tuning Privacy-Preserving ML Differential Privacy

Jul 28, 2026cs.AI

How Small Can You Go? A Controlled Study of LoRA Rank, Target Modules, and Quantization Trade-offs for Text-to-SQL on a 60M-Parameter Model

Parameter-efficient fine-tuning (PEFT) and low-bit quantization are now standard tools for adapting language models under tight compute budgets, yet their interaction is most often studied on billion-parameter models where the design space is expensive to explore. We ask a complementary question: on a specific, fully reproducible 60M-parameter encoder-decoder model (T5-small) and a single-table text-to-SQL benchmark (WikiSQL), how much task accuracy does each efficiency knob actually cost? We run a controlled, single-variable study over (i) LoRA rank r in {2, 4, 8, 16, 32}, (ii) the set of adapted modules, and (iii) numerical precision. We report task accuracy alongside system-level metrics including trainable parameters, peak training memory, inference latency, and throughput, and frame adaptation as a constrained trade-off rather than an accuracy-only objective. Our results show that LoRA with r=16 recovers within 11.6 percentage points of full fine-tuning accuracy (59.6% vs. 71.2% exact-match) while training fewer than 1% of parameters and consuming 31% less peak GPU memory. Within this setting, rank beyond r=16 yields no measurable accuracy gain. QLoRA with INT8 and NF4 quantization achieves comparable accuracy (52.8% and 53.2%) at dramatically lower memory cost (0.60 GB each), demonstrating a compelling trade-off for memory-constrained deployments. All code, configurations, and logs are released for full reproducibility.

Mahendra Singh Rathor, Anagheem Azzam

Independent Researcher · Jaipur, India · Hamburg, Germany

Memory-Efficient Fine-Tuning Small Language Models Low-Rank Adaptation Text-to-SQL Low-Bit Quantization Parameter-Efficient Fine-Tuning

Jul 24, 2026cs.LG

\k{appa}-LoRA: Condition Numbers Reveal Which LoRA Matrices Worth Updating

Low-Rank Adaptation (LoRA) has become a widely adopted technique for efficient neural network fine-tuning, decomposing model updates into low-rank matrices. However, LoRA remains computationally costly because it updates all matrices uniformly, regardless of their actual contribution to adaptation. This cost is especially prohibitive for large-scale models with billions of parameters and for resource-constrained settings such as edge deployment and on-device fine-tuning. We show for the first time that not all LoRA matrices are equally worth tuning: matrices with smaller condition numbers (the ratio of largest to smallest singular value) are already well-balanced across directions and contribute only marginally to adaptation, whereas matrices with larger condition numbers contain underdeveloped directions that span richer subspaces and drive most of the performance gains. This observation itself is a key contribution of our work, and it motivates a more selective approach to fine-tuning. Building on this insight, we propose \k{appa}-LoRA, a method that optimizes LoRA by focusing updates on the matrices with the largest condition numbers, which capture the most informative directions of change. By restricting LoRA updates to the top 50% of weight matrices ranked by condition number, \k{appa}-LoRA halves the trainable parameter count and correspondingly reduces compute and memory cost. Extensive experiments across multiple benchmarks show that this design cuts fine-tuning time by 16.2% on average while matching the accuracy of standard LoRA and reducing memory cost by 4.5%. Further analysis reveals that the condition numbers of the selected matrices consistently decrease over training, suggesting that \k{appa}-LoRA's effectiveness stems from targeted spectral rebalancing rather than parameter selection alone.

Jianghui Wang, Silong Yong, Francesco Orabona +3

King Abdullah University of Science and Technology · Carnegie Mellon University

Fine-Tuning Memory-Efficient Fine-Tuning Low-Rank Adaptation Selective Fine-Tuning Parameter-Efficient Fine-Tuning

Jul 16, 2026cs.AI

Long-Context Fine-Tuning with Limited VRAM

Parameter-efficient fine-tuning reduces model and optimizer memory, but dense attention still makes long training sequences expensive. We combine Hierarchical Global Attention (HGA) with segment-wise backpropagation and tiered KV storage. Only the active segment remains differentiable in VRAM; older KV is detached into RAM or NVMe, and HGA loads a bounded set of exact historical tokens for each query block. On Qwen3-8B with 4-bit QLoRA and PG19, dense training on a 16 GB Quadro RTX 5000 fits 2,048 tokens but fails at 4,096, whereas HGA reaches 16,384 tokens with 15.28 GB peak VRAM. Under evaluation the same adapter runs through 131,072 tokens on this card; VRAM is not constant but grows gently with the resident chunk summaries, so RAM and NVMe capacity set the practical limit beyond these lengths. At the shared 2K training length, HGA-trained and dense-trained adapters obtain 2.7405 and 2.7383 nat under the same dense-attention readout, while the stock model obtains 2.9541. At this boundary HGA training is already marginally faster (217.75 vs. 207.02 tokens/s), and the HGA-to-dense throughput ratio improves from 1K to 2K; because HGA keeps the attended historical set per token approximately constant while dense work per token grows, we expect this lead to widen as context grows. Dense attention is used for the main quality and retrieval comparisons so that they measure the learned weights and remain compatible with standard generation frameworks. HGA can also be used for retrieval and generation; an optimized production-grade serving implementation is under development.

Vladimir Fedosov, Aleksandr Sazhin, Artemiy Grinenko +1

BMW Group

Fine-Tuning KV-Cache Offloading Memory-Efficient Fine-Tuning Efficient Language Model Training Attention Mechanisms Parameter-Efficient Fine-Tuning

Jul 11, 2026cs.LG

CARE-LoRA: Compressed Activation REconstruction for Memory-Efficient LoRA

As the scale of large pre-trained models continues to grow, fine-tuning them under limited memory budgets has become increasingly challenging. Low-Rank Adaptation (LoRA), currently one of the most widely adopted parameter-efficient fine-tuning (PEFT) methods, mitigates this challenge by optimizing only low-rank adaptation matrices, thereby greatly reducing the number of trainable parameters. With the parameter overhead substantially reduced, the activations retained for backpropagation have emerged as the primary remaining memory bottleneck during LoRA fine-tuning. To address this, we propose CARE-LoRA, a data-aware Compressed Activation REconstruction framework. By exploiting the inherent projection structure of LoRA, CARE-LoRA replaces the full input activation with the low-rank compressed activation naturally produced by the LoRA branch. It further computes a lightweight reconstruction matrix during the forward pass with negligible additional computation cost, which is used during backpropagation to reconstruct the gradient signal, thereby keeping LoRA matrices fully trainable. Extensive experiments across diverse models and downstream tasks demonstrate that, while substantially reducing the overall memory footprint, CARE-LoRA achieves competitive or even superior performance compared with standard LoRA and representative LoRA variants. Our code is publicly available at https://github.com/fishandyu/CARE-LoRA .

Gengyu Zhang, Haiyin Ran, Zhengbao He +4

Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai 200240, China

Fine-Tuning Memory-Efficient Fine-Tuning LLM Fine-Tuning Low-Rank Adaptation Low-Rank Compression Neural Network Compression+1

Jul 10, 2026cs.LG

Super-Tuning: From Activation-Aware Pruning to Sparse Fine-Tuning

Large language models (LLMs) remain expensive to fine-tune because full-parameter updates require substantial memory, compute, and per-task storage. We study whether saliency signals originally developed for pruning can be reused to choose where a model should adapt. We propose Super, a sparse parameter-efficient fine-tuning (PEFT) method that fixes a small trainable support using a Wanda-style activation-weighted magnitude score [Sun et al., 2023] computed from a calibration pass. We then introduce Supra, a hybrid adapter that combines this sparse update with LoRA while preserving a matched trainable-parameter budget through a simple budget-splitting rule. In single-seed Math17K arithmetic experiments on Llama-3.2-1B and Meta-Llama-3-8B, the best Super/Supra variants achieve the highest average accuracy among the tested schedule-selected adapter configurations. We also include a PaFi-style magnitude-only support as a closest training-free sparse baseline and find that low-score supports under both magnitude and Wanda-style orderings can be effective. These results suggest that simple pruning-inspired orderings can provide useful fixed sparse supports for PEFT, especially when combined with low-rank adapters.

Ivan Ilin, Philip Zmushko, Peter Richtárik

KAUST

Memory-Efficient Fine-Tuning Low-Rank Adaptation Sparse Fine-Tuning Selective Fine-Tuning Parameter-Efficient Fine-Tuning

Jul 2, 2026cs.CV

Efficient PEFT Methods with Adaptive Checkpointing for Vision Models and VLMs on Resource Constrained Consumer-GPUs

Modern pretrained vision models achieve strong accuracy but demand substantial GPU memory for fine-tuning, making edge deployment impractical. This paper compares five parameter-efficient fine-tuning (PEFT) methods (Full FT, LoRA, AdaLoRA, QLoRA, BitFit) on Transformers- (ViT-Small, TinyViT) and Mamba-based vision backbones (Vim-Small, MambaVision-T) under an on-device VRAM budget (e.g., 2 GB), together with three gradient-checkpointing strategies (none, static, and a proposed memory-budget-aware adaptive algorithm); and we evaluate three families of foundation-model baselines: zero-shot contrastive vision language models (OpenCLIP, SigLIP), self-supervised vision backbones with lightweight evaluation protocols (DINOv2), and autoregressive VLMs for prompt-based classification (PaliGemma, MobileVLM, SmolVLM). Experiments on CIFAR-100 and DTD report accuracy, training time, energy, and the NetScore family of multi-objective metrics, which we extend with two deployment-aware variants. QLoRA and BitFit cut energy 20-30% at a 1-2% accuracy cost; the adaptive algorithm reduces peak memory 43-79% with 9-30% energy overhead. DINOv2 surpasses fine-tuned models on CIFAR-100 (0.917 vs. 0.897) at a fraction of the energy, while small autoregressive VLMs remain uncompetitive.

Altay Toktassyn, Jurn-Gyu Park

Department of Computer Science, Nazarbayev University, Astana 010000, Kazakhstan

Fine-Tuning Memory-Efficient Fine-Tuning Vision Foundation Model Adaptation Parameter-Efficient Fine-Tuning

Jul 2, 2026cs.AI

InduceKV: Fixed-Footprint Continual Adaptation of Multimodal LLMs via Inducing KV Memories

Multimodal large language models must adapt to evolving tasks and domains, yet continual improvement under bounded deployment footprint remains difficult because repeated parameter updates or growing replay stores can accumulate adaptation state over time. We study fixed-footprint continual adaptation: the deployed adaptation state is kept under a fixed memory budget, while the backbone model is left unchanged and task-specific updates are externalized. We propose InduceKV, a retrieval-based method that stores each selected training prefix as an attention-ready memory entry, consisting of a frozen retrieval key and compact layerwise key--value (KV) payloads that can be appended to the model's self-attention cache. Under a strict memory budget, InduceKV constructs a compact inducing set through bilevel selection: a lightweight calibration is fit for retrieval, while the selected memory balances current-task likelihood, anchor-based retention, and coverage in the frozen retrieval space. Across task-incremental instruction tuning, continual VQA, domain-incremental adaptation, and lifelong multimodal instruction tuning, InduceKV consistently improves over PEFT, MoE, replay, and prompt-retrieval baselines under matched memory budgets. We further report backbone-matched, stage-1 CoIN, compute-matched, and scalability diagnostics, showing that the gains are not due to a stronger backbone, replay alone, or an unbounded candidate pool.

Qianyu Chen, Ziteng Feng, Canran Xiao +1

1Nanyang Technological University · University of Science and Technology of China · 3Shenzhen Campus of Sun Yat-sen University

Continual Learning for LLMs Memory-Efficient Fine-Tuning Memory-Augmented Language Models VLM Adaptation KV Caching Multimodal Large Language Models+2

Jun 18, 2026cs.CL

Latent Personal Memory: Represent personal memory as dynamic soft prompts

Personalizing large language models (LLMs) requires encoding long-term, user-specific behavioral patterns in a way that is computationally efficient, scalable, and compatible with a frozen base model. We present Latent Personal Memory (LPM), a scalable framework that represents user-specific history as a compact, persistent matrix of N latent slots, that are interpretable. A shared cross-attention projection network maps these slots into dynamic, input-conditioned soft prompts that are prepended to the input of a frozen LLM. We evaluate LPM on PersonaMem v1 and LoCOMO benchmarks across Qwen3-1.7B, 4B, and 8B backbones. Results demonstrate that LPM outperforms LoRA and Prompt Tuning by up to 8.8% and 54.4% in overall accuracy respectively on PersonaMem v1, while reducing KV-cache usage by over 64x. On LoCoMo, LPM matches LoRA accuracy with 120x fewer trainable parameters. We also show that the efficiency of LPM grows with context length and outperforms full-context at 128K context length.

Debrup Das, Avinash Amballa, Yashas Malur Saidutta +3

University of Massachusetts Amherst · Samsung Research America

LLM Inference Efficiency Memory-Efficient Fine-Tuning Memory-Augmented Language Models Persistent Memory for Language Models Prompt Tuning Personalized Language Models

Jun 17, 2026cs.LG

Techniques for Peak Memory Reduction for LoRA Fine-tuning of LLMs on Edge Devices

Fine-tuning of Large Language Models (LLMs) using Low-Rank Adaptation (LoRA) on an end-user's data offers personalized experiences while keeping data private, but faces severe memory constraints on consumer hardware. Peak memory during fine-tuning often exceeds device limits, especially for models with billions of parameters and long-context training data. This paper introduces a suite of complementary techniques to reduce memory footprint without sacrificing model quality: (1) base model quantization with on-the-fly dequantization, (2) memory-efficient checkpointing combining selective activation caching and disk offloading, (3) softmax approximation using semantically relevant token subsets, and (4) logits masking. Experiments on Llama-3.2 3B and Qwen-2.5 3B demonstrate up to

26\times

and

28\times

reduction in peak memory, enabling fine-tuning on resource-constrained devices.

Hassan Dbouk, Matthias Reisser, Prathamesh Mandke +2

Qualcomm AI Research is an initiative of Qualcomm Technologies, Inc. · work done while at Qualcomm

Memory-Efficient Fine-Tuning LLM Fine-Tuning Low-Rank Adaptation Parameter-Efficient Fine-Tuning

Jun 6, 2026cs.AI

How Small Can You Go? LoRA Fine-Tuning 270M-8B Models for Merchant Information Extraction in Financial Transactions

Merchant information extraction turns noisy financial transaction descriptors into structured fields at production scale. Our deployed LoRA-fine-tuned LLaMA~~3.1-8B reaches 96.95% F1, but its memory and throughput motivate smaller replacements. We evaluate 23 retained fine-tuning runs plus a separately trained production reference, spanning Gemma~~3 (270M--4B), Qwen~~3.5 (0.8B--4B), Aya~~3.35B, and LLaMA~~3.1-8B across LoRA ranks, prompts, training templates, and serving environments. A rank-8 LLaMA fine-tune reaches 96.75% F1, only 0.20 points below the rank-32 production reference. Qwen~~3.5~~4B with JSON-Only prompting reaches 96.60% F1 and strict record-level exact match of 91.67%, with a $3.8\times$ lower inverse-throughput time estimate than the rank-8 8B model. Qwen~~3.5~0.8B reaches 94.75% F1, and Qwen Think and Nothink templates differ by less than 0.004 F1. Across 14 Databricks endpoints, mean F1 change from local evaluation is

-0.0081

; Aya is the only family with a 2.7--5.1 point decline. These results show that compact fine-tuned models can preserve most extraction accuracy, but model selection must account for prompt choice, throughput, and serving-stack behavior.

Donghao Huang, Tomas Drietomsky, Benjamin Barrett +1

Research and Development, Mastercard, Arlington, VA, USA · School of Computing and Information Systems, Singapore Management University, Singapore · Economic Intelligence, Mastercard, Prague, Czech Republic

Financial Services Memory-Efficient Fine-Tuning LLM Fine-Tuning Document Information Extraction LLM Information Extraction Efficient Language Model Inference+2

Jun 3, 2026cs.LG

Dominant-Layer ZO: A Single Layer Dominates Zeroth-Order Fine-Tuning of LLMs

Zeroth-order (ZO) optimization enables memory-efficient fine-tuning of large language models (LLMs) using only forward passes, but it remains unclear how useful adaptation is distributed across layers. In this work, we reveal a surprising phenomenon: ZO fine-tuning is sharply dominated by a single decoding layer. Across multiple LLM families and downstream tasks, fine-tuning this dominant layer alone consistently matches or even exceeds full-model ZO fine-tuning. We further show that the dominant layer is task-agnostic but model-specific, and can be identified before training through a simple inference-only analysis of activation outliers. Specifically, the dominant layer consistently aligns with the first activation-outlier layer in the pre-trained model. To explain this phenomenon, we analyze how perturbation effects propagate under ZO optimization. We find that the dominant layer combines two key properties: high perturbation sensitivity and early placement in the residual stream, allowing perturbation-induced effects to propagate and accumulate through remaining subsequent decoding layers. As a result, this layer produces disproportionately strong and stable optimization signals under forward-only updates. Extensive experiments on LLaMA2-7B and Qwen3-8B across nine benchmarks show that dominant-layer ZO fine-tuning improves average performance over full-model MeZO and LoRA-based ZO fine-tuning while achieving up to 4.52

\times

training speedup.

Wanhao Yu, Ziyan Wang, Zheng Wang +7

University of North Carolina at Charlotte · University of Houston · State University of New York at Binghamton +2

Fine-Tuning Memory-Efficient Fine-Tuning Zeroth-Order Optimization LLM Fine-Tuning Parameter-Efficient Fine-Tuning

Jun 1, 2026cs.LG

GRZO: Group-Relative Zeroth-Order Optimization for Large Language Model Fine-Tuning

Zeroth-order (ZO) optimization is a memory-efficient alternative to backpropagation for fine-tuning large language models, but its deployment is limited by the high variance of gradient estimation. We propose GRZO, a Group-Relative Zeroth-Order optimizer that draws one pseudo-independent perturbation per mini-batch example and aggregates the per-example losses through group-relative normalization, raising the effective gradient-direction count from one to the batch size at no additional forward cost while preserving inference-level memory. We prove that GRZO is directionally unbiased with variance shrinking proportionally to the batch size, yielding a tighter nonconvex convergence bound than MeZO. Across RoBERTa-large, Llama3-8B, and OPT-13B over multiple tasks, GRZO improves average accuracy on Llama3-8B by

+3.0

over MeZO at

23\%

lower peak GPU memory; as a drop-in replacement for the MeZO core, it lifts sparse, low-rank, and quantized ZO variants by

+6.0

on average.

Liyan Tan, Yequan Zhao, Yifan Yang +3

University of California, Santa Barbara

Fine-Tuning Memory-Efficient Fine-Tuning Zeroth-Order Optimization LLM Fine-Tuning Memory-Efficient Optimization Memory-Efficient Training

May 22, 2026cs.LG

Signs Beat Floats: Low-Rank Double-Binary Adaptation for On-Device Fine-Tuning

On-device adaptation of large language models commonly keeps a quantized base model frozen while training and deploying a small, task-specific LoRA adapter. In the unmerged adapter-mode setting, however, the adapter is more than a compact storage module; it introduces an additional dense floating-point branch, maintains a trainable state for local updates, and acts as a unit of communication and hot-swapping.We introduce LoRDBA, a LoRA-compatible adapter that replaces both low-rank factors with binary sign carriers while representing magnitudes through lightweight, channel-wise scales, converting the dense adapter branch into two sign-accumulation matrix multiplications interleaved with channel-wise scaling. A finite-sample analysis shows that reconstruction quality is governed by the residual-to-magnitude ratio of the original LoRA factors. In adapter-mode experiments, LoRDBA outperforms low-bit baselines at matched model sizes while matching fp16 LoRA quality in selected regimes. The unmerged adapter incurs at most 8% prefill latency overhead at matched rank r=16 despite an over 10x reduction in adapter footprint, with moderate training memory overhead of approximately 1.6x that of fp16 LoRA.

Yoshihiko Fujisawa, Yuma Ichikawa, Yudai Fujimoto +2

Fujitsu Limited · Institute of Science Tokyo · RIKEN Center for AIP +1

LLM Quantization Memory-Efficient Fine-Tuning LLM Fine-Tuning Adapter Tuning Low-Rank Adaptation Quantization-Aware LoRA+1

May 20, 2026cs.LG

ChunkFT: Byte-Streamed Optimization for Memory-Efficient Full Fine-Tuning

This work presents \textsc{ChunkFT}, a memory-efficient fine-tuning framework that reformulates full-parameter fine-tuning around a dynamically activated working set. \textsc{ChunkFT} enables gradient computation for arbitrary sub-tensors without modifying the network architecture, providing an algorithmic foundation for optimizing arbitrary sub-networks while avoiding standard dense gradient computation. We provide a theoretical convergence analysis of \textsc{ChunkFT} in the deterministic setting. Empirically, we apply \textsc{ChunkFT} to fine-tune Llama 3-8B and Llama 3-70B using a single RTX 4090-24GB GPU and 2

\times

H800-80GB GPUs, respectively. Full-parameter fine-tuning of a 7B model with a 1K input length requires only 13.72GB of GPU memory. The results demonstrate the effectiveness of \textsc{ChunkFT} in memory usage, running time, and optimization quality. Moreover, downstream evaluations on language understanding, mathematical reasoning, and MT-Bench show that \textsc{ChunkFT} consistently outperforms existing memory-efficient baselines. Notably, \textsc{ChunkFT} achieves performance comparable to, and in some cases exceeding, full-parameter fine-tuning. Our repository is on https://github.com/misonsky/chunk.

Yongkang Liu, Zijing Wang, Mengjie Zhao +7

Northeastern University, China · Shanghai Jiao Tong University, China · CIS, LMU Munich, Germany +2

Fine-Tuning Memory-Efficient Fine-Tuning LLM Fine-Tuning Memory-Efficient Optimization Memory-Efficient Training

May 19, 2026cs.LG

AR1-ZO: Topology-Aware Rank-1 Zeroth-Order Queries for High-Rank LoRA Fine-Tuning

Zeroth-order (ZO) optimization enables large-language-model fine-tuning without storing backpropagation activations, while LoRA supplies compact trainable adapters. Combining them creates a rank paradox: increasing LoRA rank improves adapter capacity, but standard two-point ZO either perturbs a rank-dependent number of coordinates or, under atomwise updates, can make the finite-difference signal unobservable. This paper shows that the bottleneck is a measurement-topology problem rather than a need for an external subspace. LoRA already decomposes into matched rank-

1

atoms, each a complete factor-coordinate block of dimension

d_\text{out}+d_\text{in}

. Querying one atom per step keeps the stored adapter rank

r

while removing

r

from the single-query perturbation dimension. The naive atomwise query is still miscalibrated: if it inherits canonical LoRA scaling

α/r

, the active finite-difference signal shrinks as

1/r

and the active finite-difference signal-to-noise ratio (FD-SNR) as

1/r^2

, producing directional collapse under a fixed residual evaluation-noise floor. AR1-ZO pairs alternating rank-

1

atom queries with topology-aware scaling

γ=αr

, restoring rank-invariant active signal without auxiliary bases, activation hooks, curvature estimates, or extra forward queries. Theory proves atom minimality, rank-independent active query dimension, directional collapse and restoration, and the remaining rank dependence as an amortized coverage cost. Experiments on OPT and Qwen3 models validate the signal mechanism and show that AR1-ZO makes high-rank LoRA effective among matched-budget ZO methods under the standard two-forward-pass query budget.

Ziye Chen, Hongbin Lin, Chenyu Zhang +3

Memory-Efficient Fine-Tuning Zeroth-Order Optimization LLM Fine-Tuning Adapter Tuning Low-Rank Adaptation Parameter-Efficient Fine-Tuning