Adapter Tuning

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 56

May 16, 2026cs.LG

FIM-LoRA: Task-Informative Rank Allocation for LoRA via Calibration-Time Gradient-Variance Estimation

Low-rank adaptation (LoRA) assigns a uniform rank to every adapted weight matrix - a practical convenience that ignores a fundamental reality: different layers contribute unequally to task adaptation. We address this with a lightweight engineering solution: before fine-tuning begins, run eight calibration backward passes, compute the gradient variance of each LoRA-B matrix as a proxy for layer informativeness, and redistribute the rank budget proportionally. The resulting adapter is a standard LoRA with a per-layer rank pattern - no new parameters, no training overhead, no changes to serving infrastructure. We implement this via an efficient approximation of the empirical Fisher Information Matrix (eFIM) diagonal, restricted to LoRA adapter matrices only, which reduces memory cost by approximately 256x compared to full-model Fisher estimation. On GLUE with DeBERTa-v3-base, FIM-LoRA matches LoRA (88.6 vs. 88.7) at the same parameter budget, and on commonsense reasoning with LLaMA-3-8B reaches 68.5 vs. 68.7 for LoRA. The per-layer rank maps are interpretable: value projections and early-to-middle layers consistently receive higher rank, consistent with established findings on transformer layer roles.

Ramakrishnan Sathyavageeswaran

Intuit

Adapter Tuning Low-Rank Adaptation Adaptive Rank Allocation Parameter-Efficient Fine-Tuning

May 14, 2026cs.LG

PreFT: Prefill-only finetuning for efficient inference

Large language models can now be personalised efficiently at scale using parameter efficient finetuning methods (PEFTs), but serving user-specific PEFTs harms throughput, even with specialised kernels and memory management techniques. This is because, theoretically and empirically, a mismatch exists between prefill (processing a large number of tokens at once) and decode (generating a single token autoregressively): the latter has far lower throughput when serving multiple adapters. Rather than optimising performance relative to parameter count, for efficient multi-adapter serving, we instead ought to optimise performance relative to serving throughput. We therefore propose PreFT (Prefill-only Finetuning), wherein we only apply the adapter to prefill tokens and discard it afterwards. PreFT significantly increases throughput with minimal effect on performance. We develop and release an efficient implementation of two prefill-only PEFTs, LoRA and ReFT, on the vLLM inference engine. We first show that serving multi-user PreFTs is more efficient than traditional PEFTs (

1.9\times

the throughput when serving

512

adapters on Llama 3.1 70B). Then, we compare the performance of prefill-only vs. all-token adapters on a variety of supervised finetuning and reinforcement learning tasks with LMs at varying scales. On SFT, we observe that the evaluation loss of PreFTs is higher than PEFTs, but can be compensated by increasing rank with nearly no reduction in throughput. On RL, we consistently find that PreFTs approach parity with standard PEFTs. Together, this work validates prefill-only adaptation of LLMs as a more favourable accuracy-throughput tradeoff than existing PEFTs for personalised serving.

Andrew Lanpouthakoun, Aryaman Arora, Zhengxuan Wu +4

Stanford University · Tilde Research

Fine-Tuning LLM Serving Adapter Tuning LLM Inference Acceleration Parameter-Efficient Fine-Tuning

May 13, 2026cs.LG

MinT: Managed Infrastructure for Training and Serving Millions of LLMs

We present MindLab Toolkit (MinT), a managed infrastructure system for Low-Rank Adaptation (LoRA) post-training and online serving. MinT targets a setting where many trained policies are produced over a small number of expensive base-model deployments. Instead of materializing each policy as a merged full checkpoint, MinT keeps the base model resident and moves exported LoRA adapter revisions through rollout, update, export, evaluation, serving, and rollback, hiding distributed training, serving, scheduling, and data movement behind a service interface. MinT scales this path along three axes. Scale Up extends LoRA RL to frontier-scale dense and MoE architectures, including MLA and DSA attention paths, with training and serving validated beyond 1T total parameters. Scale Down moves only the exported LoRA adapter, which can be under 1% of base-model size in rank-1 settings; adapter-only handoff reduces the measured step by 18.3x on a 4B dense model and 2.85x on a 30B MoE, while concurrent multi-policy GRPO shortens wall time by 1.77x and 1.45x without raising peak memory. Scale Out separates durable policy addressability from CPU/GPU working sets: a tensor-parallel deployment supports 10^6-scale addressable catalogs (measured single-engine sweeps through 100K) and thousand-adapter active waves at cluster scale, with cold loading treated as scheduled service work and packed MoE LoRA tensors improving live engine loading by 8.5-8.7x. MinT thus manages million-scale LoRA policy catalogs while training and serving selected adapter revisions over shared 1T-class base models.

Mind Lab, :, Song Cao +60

LLM Serving Adapter Tuning Low-Rank Adaptation LLM Inference Acceleration

May 12, 2026cs.LG

Not How Many, But Which: Parameter Placement in Low-Rank Adaptation

We study the \textit{parameter placement problem}: given a fixed budget of

k

trainable entries within the B matrix of a LoRA adapter (A frozen), does the choice of which

k

matter? Under supervised fine-tuning, random and informed subsets achieve comparable performance. Under GRPO on base models, random placement fails to improve over the base model, while gradient-informed placement recovers standard LoRA accuracy. This regime dependence traces to gradient structure: SFT gradients are low-rank and directionally stable, so any subset accumulates coherent updates; GRPO gradients are high-rank and near-orthogonal across steps, so only elements with consistently signed gradients retain the learning signal. Our scoring procedure identifies these critical parameters in under 10 seconds at less than 0.5% of training cost. Selected parameters concentrate on residual-stream-writing projections (V, O, Down), stable across model families and scales (1.5B - 8B).

Arijit Sehanobish, Charles Lovering

Kensho Technologies

Adapter Tuning Low-Rank Adaptation Sparse Fine-Tuning RL Fine-Tuning Parameter-Efficient Fine-Tuning

May 12, 2026cs.CV

TB-AVA: Text as a Semantic Bridge for Audio-Visual Parameter Efficient Finetuning

Audio-visual understanding requires effective alignment between heterogeneous modalities, yet cross-modal correspondence remains challenging when temporally aligned audio and visual signals lack clear semantic correspondence. We propose to use text as a semantic anchor for audio-visual representation learning. To this end, we introduce a parameter-efficient adaptation framework built on frozen audio and visual encoders, centered on Text-Bridged Audio-Visual Adapter (TB-AVA), which enables text-mediated interaction between audio and visual streams. At the core of TB-AVA, Gated Semantic Modulation (GSM) selectively modulates feature channels based on text-inferred semantic relevance. We evaluate the proposed approach on multiple benchmarks, including AVE, AVS, and AVVP, where the proposed framework achieves state-of-the-art performance, demonstrating text as an effective semantic anchor for parameter-efficient fine-tuning (PEFT) in audio-visual learning.

Seongah Kim, Dinh Phu Tran, Hyeontaek Hwang +3

AI2 Lab, KAIST

Audio-Visual Understanding Audio-Visual Representation Learning Cross-Modal Alignment Adapter Tuning Parameter-Efficient Fine-Tuning

May 11, 2026cs.CL

Decomposing Evolutionary Mixture-of-LoRA Architectures: The Routing Lever, the Lifecycle Penalty, and a Substrate-Conditional Boundary

We decompose an evolutionary mixture-of-LoRA system on a from-scratch ~150M-parameter widened-D substrate (D=1536, V=32000; D/V approx 0.048; the "widened-1536" substrate) into three factors -- a router rewrite (parallel sigmoid gate with learnable per-adapter floor and bounded temperature anneal, fed post-stack hidden states rather than token-embedding means), a per-domain leave-one-out evaluation scope, and a lifecycle of death plus alpha-blend inheritance plus SVD mutation plus slot reallocation -- and report a 5-of-8 partial 2^3 factorial run at n=3 seeds and 25000 adaptation steps per cell. The attribution chain is sharp on this substrate: the router rewrite carries the entire +0.0426 nat balanced log-PPL improvement (Delta = log PPL_ref - log PPL_test, positive = improvement; t=12.86, p=0.006) attributed to "the full evolutionary system vs the static B3 baseline"; the headline full-system-vs-B3 balanced contrast itself is +0.015 nats, t=1.94, p=0.19 at n=3 and does not clear alpha=0.05. The per-domain evaluation scope is null at seed-resolution, and the lifecycle is a net drag of approx -0.028 nats (t=-4.46,p=0.047 in the primary chain). An auxiliary alpha=0 inheritance counterfactual at n=3 seeds is sign-inconsistent at the headline metric and underpowered for either an equivalence or load-bearing conclusion (corrected from an earlier arithmetic-mean aggregator that erroneously cleared inheritance; see Appendix B.11). A base-perturbation probe directionally refutes a "genomic-context" reframe of the lifecycle role. A controllable synthetic sandbox locates a substrate-conditional regime boundary: evolutionary search on the routing channel is load-bearing only when adapters are pre-aligned to the task; in every other regime tested it underperforms, ties, or actively degrades the gradient solution.

Ramchand Kumaresan

Murai Labs

Adaptive Model Routing Evolutionary Optimization Adapter Tuning Low-Rank Adaptation

May 11, 2026cs.LG

AdaPaD: Adaptive Parallel Deflation for PEFT with Self-Correcting Rank Discovery

Fine-tuning large language models with LoRA requires choosing a rank r before training starts. Existing approaches either extract rank-1 components sequentially, freezing each component's error permanently into every subsequent residual, or optimize the full low-rank factorization jointly with guarantees that describe only the joint update, not individual rank-1 directions. We present AdaPaD (Adaptive Parallel Deflation), which trains all rank-1 components simultaneously: each worker refines its component against a deflation target built from the latest estimates of all predecessors, and as those estimates improve, the targets improve too. We call this property self-correction: deflation errors converge to zero over rounds rather than persisting as fixed residuals. On top of this backbone, AdaPaD adds advance learning (private pre-training before activation) and per-module dynamic rank discovery (importance-based growth until a shared budget is exhausted), making the rank distribution an output rather than an input. We prove that every component's error decays exponentially after a warm-up period, with a generalization bound that splits into a vanishing algorithmic term and an irreducible statistical floor. Empirically, AdaPaD is competitive with adaptive-rank LoRA baselines on GLUE with DeBERTaV3-base at matched parameter budgets, and competitive with fixed-rank LoRA on Qwen3-0.6B SQuAD/SQuAD v2 while deploying an adapter that is on average 30.7% smaller.

Barbara Su, Fangshuo Liao, Anastasios Kyrillidis

Department of Computer Science Rice University

LLM Fine-Tuning Adapter Tuning Low-Rank Adaptation Adaptive Rank Allocation Parameter-Efficient Fine-Tuning

May 11, 2026cs.LG

HELLoRA: Hot Experts Layer-Level Low-Rank Adaptation for Mixture-of-Experts Models

Low-Rank Adaptation (LoRA) dominates parameter-efficient fine-tuning of large language models, yet most variants target dense architectures. Mixture-of-Experts (MoE) models scale parameters at near-constant per-token compute, and their sparse activation patterns create untapped opportunities for more efficient adaptation. We propose Hot-Experts Layer-level Low-Rank Adaptation (HELLoRA), which attaches LoRA modules only to the most frequently activated experts at each layer. This simple mechanism reduces trainable parameters and adapter-induced FLOPs while improving downstream performance, an effect we attribute to a form of structured regularization that preserves pretrained expert specialization. To stress-test HELLoRA under extreme parameter budgets, we further compose it with LoRI to form HELLoRI, which freezes the up-projection and sparsifies the down-projection. Across three MoE backbones, namely OlMoE-1B-7B, Mixtral-8x7B, and DeepSeekMoE, and three task families covering mathematical reasoning, code generation, and safety alignment, HELLoRA consistently outperforms strong PEFT baselines. Relative to vanilla LoRA on OlMoE, HELLoRA uses 15.7% of the trainable parameters, reduces adapter FLOPs by 38.7%, achieves 1.9x the training throughput, and improves accuracy by 9.2%. On DeepSeekMoE, HELLoRA outperforms LoRA while using only 23.2% of its trainable parameters. These results demonstrate that activation-aware adapter placement is an effective and practical route to scaling PEFT for MoE language models.

Jia Wei, Zhonghao Zhang, Ping Chen +5

Department of Computer Science and Technlogy Tsinghua University Beijing 100084, China · School of Computer Science and Technlogy Xi’an Jiaotong University · The State Key Laboratory of Blockchain and Data Security, Zhejiang University Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security

Mixture-of-Experts Language Models Fine-Tuning Adapter Tuning Low-Rank Adaptation Parameter-Efficient Fine-Tuning

May 9, 2026cs.CL

LLiMba: Sardinian on a Single GPU -- Adapting a 3B Language Model to a Vanishing Romance Language

Sardinian, a Romance language with roughly one million speakers, has minimal presence in modern NLP. Commercial services do not support it, and current language models do not produce it reliably. We present LLiMba, a 3B parameter Sardinian-ready model adapted from Qwen2.5-3B-Instruct through continued pretraining (CPT) and supervised fine-tuning (SFT) on a single 24 GB consumer GPU. The corpus contains 11.5 million tokens of Sardinian spanning LSC, Logudorese, and Campidanese, augmented with 2.4 million tokens of related Romance text as replay against register blurring. After CPT the model reaches a perplexity of 6.76 on held out Sardinian and outperforms the base across all six FLORES-200 directions. We compare five SFT configurations under matched conditions: full fine-tuning, LoRA r64, rsLoRA r128, rsLoRA r256, and DoRA r256. rsLoRA r256 wins on every direction into Sardinian, reaching 28.5 BLEU from English against 17.3 after CPT and 21.0 with full fine-tuning. The rank ablation places r128 between LoRA r64 and rsLoRA r256 on BLEU but reveals failure modes invisible to the metric, including leakage across scripts no other variant produces. LoRA r64 retains less factual content from SFT than configurations at higher rank and produces more confident fabrications, though all methods fabricate on content absent from training. DoRA r256 yields the smallest gap between training and evaluation but the worst factual accuracy. The findings indicate that adapter capacity matters more than the choice among LoRA variants for adapting a Romance pretrained base to a low resource Romance target, that stronger regularization is not uniformly beneficial, and that translation metrics smoothly order configurations whose qualitative behavior differs categorically. Perplexity comparisons across scripts must account for byte fallback tokenization, which deflates the metric for scripts other than Latin.

Luca Ballore

Language Model Pretraining Adapter Tuning Low-Resource Language Processing Parameter-Efficient Fine-Tuning

May 8, 2026cs.LG

Queryable LoRA: Instruction-Regularized Routing Over Shared Low-Rank Update Atoms

We present a data-adaptive method for parameter-efficient fine-tuning of large neural networks. Standard low-rank adaptation methods improve efficiency by restricting each layer update to a fixed low-rank form, but this static parameterization can be too rigid when the appropriate correction depends on the input and on the evolving depth-wise computation of the network. Our approach replaces a purely layer-local adapter with a shared queryable memory of low-rank update atoms. For each block of layers, the model forms a query from the current low-rank state and a running summary of previous blocks, uses this query to retrieve a content-dependent combination of shared update components via attention, and applies the resulting routed operator within the low-rank bottleneck. In this way, the method retains the efficiency and scalability of low-rank adaptation while allowing the effective update to vary across inputs and to share reusable structure across layers. The resulting architecture provides a principled middle ground between static LoRA-style updates and fully generated parameter updates: it remains compact and parameter-efficient while supporting dynamic, context-sensitive adaptation. Further, we incorporate instruction-regularization by augmenting routing logits with a language-induced prior over update atoms, thereby biasing the selection of low-rank transformations toward semantically relevant directions without generating unconstrained parameter updates. Experiments on noisy non-linear regression tasks and LLM fine-tuning suggest that this queryable update-memory formulation can improve final test performance and training stability compared to standard low-rank adaptation, while using a comparable number of trainable parameters.

Omatharv Bharat Vaidya, Connor T. Jerzak, Nhat Ho +1

Department of Computer Science University of Texas at Austin · Department of Government University of Texas at Austin · University of Texas at Austin

Memory-Augmented Neural Networks Adapter Tuning Low-Rank Adaptation Parameter-Efficient Fine-Tuning

May 8, 2026cs.CL

MatryoshkaLoRA: Learning Accurate Hierarchical Low-Rank Representations for LLM Fine-Tuning

With the rise in scale for deep learning models to billions of parameters, the computational cost of fine-tuning remains a significant barrier to deployment. While Low-Rank Adaptation (LoRA) has become the standard for parameter-efficient fine-tuning, the need to set a predefined, static rank

r

requires exhaustive grid searches to balance efficiency and performance. Existing rank-adaptive solutions such as DyLoRA mitigate this by sampling ranks during the training from a predefined distribution. However, they often yield sub-optimal results at higher ranks due to lack of consistent gradient signals across the full hierarchy of ranks, thus making these methods data-inefficient. In this paper, we propose MatryoshkaLoRA, a general, Matryoshka-inspired training framework for LoRA that learns accurate hierarchical low-rank representations by inserting a fixed, carefully crafted diagonal matrix

P

between the existing LoRA adapters to scale their sub-ranks accordingly. By introducing this simple modification, our general framework recovers LoRA and DyLoRA only by changing

P

and ensures all sub-ranks embed the available gradient information efficiently. Our MatryoshkaLoRA supports dynamic rank selection with minimal degradation in accuracy. We further propose Area Under the Rank Accuracy Curve (AURAC), a metric that consistently evaluates the performance of hierarchical low-rank adapters. Our results demonstrate that MatryoshkaLoRA learns more accurate hierarchical low-rank representations than prior rank-adaptive approaches and achieves superior accuracy-performance trade-offs across ranks on the evaluated datasets. Our code is available at https://github.com/IST-DASLab/MatryoshkaLoRA.

Ionut-Vlad Modoranu, Mher Safaryan, Dan Alistarh

Institute of Science and Technology Austria (ISTA). · Lancaster University, UK · ISTA

LLM Fine-Tuning Hierarchical Representation Learning Adapter Tuning Low-Rank Adaptation Parameter-Efficient Fine-Tuning

May 8, 2026cs.CV

DIMoE-Adapters: Dynamic Expert Evolution for Continual Learning in Vision-Language Models

Continual learning enables vision-language models to accumulate knowledge and adapt to evolving tasks without retraining from scratch. However, in multi-domain task-incremental learning, large domain shifts intensify the stability-plasticity dilemma. Most existing methods rely on fixed architectures with statically allocated parameters, which limits adaptation to new domains and aggravates catastrophic forgetting. To address these challenges, we propose DIMoE-Adapters, a Dynamic Incremental Mixture-of-Experts Adapters framework that introduces a dynamic expert evolution paradigm to balance stability and plasticity. This paradigm is implemented through two collaborative components: Self-Calibrated Expert Evolution (SCEE) and Prototype-Guided Expert Selection (PGES). SCEE constructs and evolves a sparse expert pool through expert optimization dynamics, improving plasticity while reducing redundant capacity. PGES controls expert utilization based on the pool shaped by SCEE, improving stability across both previously encountered and unseen tasks. Extensive experiments show that DIMoE-Adapters outperforms previous state-of-the-art methods across various settings.

Mengxin Qin, Xiang Zhang, Xi Wang +3

School of Electronic Engineering, Xidian University Xi’an 710071, China

Vision-Language Models Fine-Tuning VLM Adaptation Mixture of Experts Adapter Tuning Incremental Learning+1

May 7, 2026cs.AI

Rethinking Adapter Placement: A Dominant Adaptation Module Perspective

Low-rank adaptation (LoRA) is a widely used parameter-efficient fine-tuning method that places trainable low-rank adapters into frozen pre-trained models. Recent studies show that using fewer LoRA adapters may still maintain or even improve performance, but existing methods still distribute adapters broadly, leaving \emph{where to place a limited number of adapters to maximize performance} largely open. To investigate this, we introduce \textbf{PAGE} (\textbf{P}rojected \textbf{A}dapter \textbf{G}radient \textbf{E}nergy), a gradient-based sensitivity probe that estimates the initial trainable gradient energy available to each candidate LoRA adapter. Surprisingly, we find that PAGE is highly concentrated on a single shallow FFN down-projection across two model families and four downstream tasks. We term this module the \textbf{dominant adaptation module} and show that its layer index is architecture-dependent but task-stable. Motivated by this finding, we propose \textbf{DomLoRA}, a placement method that places a single adapter at the dominant adaptation module. With only \textbf{0.7%} of vanilla LoRA's trainable parameters, DomLoRA outperforms it on average across downstream tasks, including instruction following, mathematical reasoning, coding, and multi-turn conversation. This method also matches or improves other LoRA variants and reduces training time by up to \textbf{2.74}

\times

compared with broad placement, supporting the dominant adaptation module perspective as a practical placement guideline.

Suoxin Zhang, Run He, Di Fang +3

South China University of Technology, China · Zhejiang University, China

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

May 7, 2026cs.LG

TFM-Retouche: A Lightweight Input-Space Adapter for Tabular Foundation Models

Tabular foundation models (TFMs), such as TabPFN-2.6, TabICLv2, ConTextTab, Mitra, LimiX, and TabDPT, achieve strong zero-shot performance through in-context learning, but their inductive biases remain fixed at inference time. Adapting a pretrained TFM to a specific dataset or task typically requires either full fine-tuning, which is computationally expensive, or parameter-efficient tuning methods (PEFT) such as LoRA, which must be tailored to the internal architecture of each TFM. Furthermore, the evidence on whether weight-space fine-tuning improves accuracy or calibration is mixed \citep{tanna_exploring_2026,rubachev_finetuning_2025}. We introduce TFM-Retouche, a lightweight input-space residual adapter that is architecture-agnostic by design with respect to the frozen TFM backbone. TFM-Retouche learns a small residual correction in the input space to align the input data with the inductive biases of the pretrained model. The adapter is trained end-to-end through the frozen TFM, with a post-training identity guard that falls back to the unmodified TFM whenever adaptation does not help on held-out validation. On TabArena-Lite (51 datasets spanning binary classification, multiclass classification, and regression), TabICLv2-Retouche -- the framework instantiated on TabICLv2 -- is the top-ranked method on the leaderboard with light per-task tuning and ensembling, lifting aggregate Elo by +56 over the frozen TabICLv2 base and sitting on the Pareto front of predictive quality versus both training and inference time.

Duong Nguyen, Mohammed Jawhar, Nicolas Chesneau

Ekimetrics

Tabular Foundation Models Adapter Tuning Parameter-Efficient Fine-Tuning

May 7, 2026cs.CV

EGA: Adapting Frozen Encoders for Vector Search with Bounded Out-of-Distribution Degradation

Vector search systems built on frozen vision encoders face queries from unseen classes at deployment, yet existing adapter training collapses under this shift: high-capacity adapters with global contrastive losses silently reassign unseen-class samples to wrong seen-class clusters, dropping worst-case Label Precision by over 40 points below the frozen baseline in our tests. We propose Euclidean Geodesic Alignment (EGA), a residual adapter that couples three principles: zero initialization, local triplet loss, and hypersphere projection. These collectively induce a self-limiting dynamic: triplets that already satisfy a small margin stop producing gradients, so the adapter automatically stops updating where the local geometry is already correct. Our experiments show that at convergence

96.5\%

of triplets are gradient-free, leaving unseen-class regions largely untouched while still enabling full-capacity refinement of seen classes. Across five diverse out-of-distribution (OOD) benchmarks, EGA achieves the highest worst-case Label Precision on the four primary splits and a consistent improvement on the fifth. The design also transfers to stronger backbones in addition to CLIP, and we provide an analytical justification linking gradient sparsity to bounded OOD perturbation.

Dongfang Zhao

Tacoma School of Engineering and Technology University of Washington

OOD Generalization Vision Foundation Model Adaptation Adapter Tuning Metric Learning

May 4, 2026cs.AI

Compress Then Adapt? No, Do It Together via Task-aware Union of Subspaces

Adapting large pretrained models to diverse tasks is now routine, yet the two dominant strategies of parameter-efficient fine-tuning (PEFT) and low-rank compression are typically composed in sequence. This decoupled practice first compresses and then fine-tunes adapters, potentially misaligning the compressed subspace with downstream objectives and squandering a global parameter budget. To overcome this limitation, we introduce JACTUS (Joint Adaptation and Compression with a Task-aware Union of Subspaces), a single framework that unifies compression and adaptation. From a small calibration set, JACTUS estimates input and pre-activation gradient covariances, forms their orthogonal union with the pretrained weight subspace, performs a projected low-rank approximation inside this union, allocates rank globally by marginal gain per parameter, and trains only a compact core matrix. This explicitly mitigates the potential misalignment between the compressed subspace and downstream objectives by coupling the directions preserved for compression with those required for adaptation, yielding a deployable low-rank model that avoids retaining full frozen weights while enabling fast and robust tuning. On vision, JACTUS attains an average 89.2% accuracy on ViT-Base across eight datasets at 80% retained parameters, surpassing strong 100% PEFT baselines (e.g., DoRA 87.9%). On language, JACTUS achieves an 80.9% average on Llama2-7B commonsense QA at the same 80% retained-parameter budget, outperforming 100% PEFT (e.g., DoRA 79.7%) and exceeding prior compress-then-finetune pipelines under the same ratained-parameter budget. We will release code.

Jingze Ge, Yun Liu, Xue Geng +4

National University of Singapore · Nankai University · Institute for Infocomm Research (I2R), A*STAR

Model Compression Adapter Tuning Low-Rank Adaptation Low-Rank Compression Parameter-Efficient Fine-Tuning

May 2, 2026cs.AI

SCALE-LoRA: Auditing Post-Retrieval LoRA Composition with Residual Merging and View Reliability

Libraries of Low-Rank Adaptation (LoRA) adapters are becoming a practical by-product of parameter-efficient adaptation. Once such adapters accumulate, a natural question is no longer how to train one adapter for one task, but how to reuse an open pool of adapters for a new task given only a small support set. Prior work has shown that LoRA modules can be composed at the task level and dynamically selected at the instance level. However, open-pool LoRA reuse is not automatic: retrieving relevant adapters does not guarantee that their parameter updates are compatible, and composing adapters does not guarantee reliable outputs. We introduce the Sparse-Composition Agreement Layer (SCALE), a post-retrieval audit and composition framework for open-pool LoRA reuse. SCALE contains a deployable 1.0* merge path, Layer-Adaptive Sparse Residual Composition (LASRC), and a higher-cost reliability-analysis layer for multi-view disagreement. LASRC addresses merge interference by preserving a linear anchor while residualizing block-wise adapter update directions. The reliability layer treats disagreement among sparse composition views as an observable uncertainty signal and compares agreement, support-loss proxy selection, and oracle headroom under explicit path cost. In matched FLAN-T5-Large, BIG-Bench Hard (BBH), and 97-LoRA experiments, LASRC gives a directional single-view gain under fixed retrieval, while SCALE-support is reported as a query-label-free 3.0* reliability-analysis variant rather than as a calibrated or throughput-equivalent selector. Protocol-distinct BBH-8 validation shows the same qualitative trend on three decoder-only backbones. Detailed scores, paired audits, and path-cost records are reported in the experimental section.

Shuaipeng Zhou, Yu Zhang

School of Computer Science and Technology, Shenyang University of Chemical Technology · 2Liaoning Key Laboratory of Intelligent Technology for Chemical Process Industry

Uncertainty Quantification Adapter Tuning Low-Rank Adaptation Language Model Auditing

May 2, 2026cs.CL

GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models

A promising paradigm for adapting instruction-tuned language models is to learn task-specific updates on a pretrained base model and subsequently merge them into the instruction-tuned model. However, existing approaches typically treat the instruction-tuned model as a passive target that is only involved at the final merging stage, without guiding the training process. We propose GIFT (Guided Fine-Tuning and Transfer), a simple and efficient framework that incorporates guidance from the instruction model into task adaptation. GIFT fine-tunes a low-rank adapter on the pretrained base model using confidence signals derived from the instruction-tuned model. The learned adapter is then merged into the instruction-tuned model, yielding task-specialized models that preserve general instruction-following behavior. We evaluate GIFT on mathematical and knowledge-intensive benchmarks across multiple model families and scales. Results show that GIFT consistently outperforms direct fine-tuning and representative transfer-based baselines, while maintaining robust generalization and favorable test-time scaling behavior.

Zhiwen Ruan, Yichao Du, Jianjie Zheng +6

Southern University of Science and Technology · Alibaba Group · Shanghai University of Finance and Economics +2

LLM Fine-Tuning Large Language Model-Guided Optimization Adapter Tuning Language Model Merging Parameter-Efficient Fine-Tuning

Apr 30, 2026cs.LG

BoostLoRA: Growing Effective Rank by Boosting Adapters

Parameter-efficient fine-tuning (PEFT) methods face a tradeoff between adapter size and expressivity: ultra-low-parameter adapters are confined to fixed low-rank subspaces, capping performance even with extended training. We propose BoostLoRA, a gradient-boosting framework that overcomes this limit by iteratively training and merging minimal adapters on the examples the current model gets wrong. A ROTATE SVD basis strategy assigns each round to an orthogonal subspace, so cumulative effective rank grows linearly with the number of rounds while each adapter remains ultra-low-rank. After merging, adapters are discarded, leaving zero inference overhead. On Qwen2.5-3B, BoostLoRA reaches 89.1% on GSM8K and 68.8% on MATH-500, surpassing both the best single-shot ultra-low parameter adapter (TinyLoRA) and full fine-tuning; on code generation it reaches 57.2% on MBPP and 80.4% on HumanEval while full fine-tuning drops below the zero-shot baseline. We also demonstrate cross-architecture transfer on protein binding classification with ESM2-650M and cross-entropy training. BoostLoRA is, to our knowledge, the first PEFT method whose effective rank grows with training, separating per-round parameter cost from total representational capacity.

Raviteja Anantha, Nick Levato, Layne C. Price

Amazon

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

Apr 23, 2026cs.LG

Low-Rank Adaptation Redux for Large Models

Low-rank adaptation (LoRA) has emerged as the de facto standard for parameter-efficient fine-tuning (PEFT) of foundation models, enabling the adaptation of billion-parameter networks with minimal computational and memory overhead. Despite its empirical success and rapid proliferation of variants, it remains elusive which architectural choices, optimization techniques, and deployment constraints should guide practical method selection. This overview revisits LoRA through the lens of signal processing (SP), bridging modern adapter designs with classical low-rank modeling tools and inverse problems, as well as highlighting how SP principles can inform principled advances of fine-tuning approaches. Rather than providing a comprehensive enumeration and empirical comparisons of LoRA variants, emphasis is placed on the technical mechanisms underpinning these approaches to justify their effectiveness. These advances are categorized into three complementary axes: architectural design, efficient optimization, and pertinent applications. The first axis builds on singular value decomposition (SVD)-based factorization, rank-augmentation constructions, and cross-layer tensorization, while the second axis deals with initialization, alternating solvers, gauge-invariant optimization, and parameterization-aware methods. Beyond fine-tuning, emerging applications of LoRA are accounted across the entire lifecycle of large models, ranging from pre- and post-training to serving/deployment. Finally, open research directions are outlined at the confluence of SP and deep learning to catalyze a bidirectional frontier: classical SP tools provide a principled vocabulary for designing principled PEFT methods, while the unique challenges facing modern deep learning, especially the overwhelming scale and prohibitive overhead, also offer new research lines benefiting the SP community in return.

Bingcong Li, Yilang Zhang, Georgios B. Giannakis

Dept. of CS, ETH Zürich, Switzerland · Dept. of ECE, U. of Minnesota, USA · Morgan Stanley, USA

Adapter Tuning Low-Rank Adaptation Low-Rank Approximation Parameter-Efficient Fine-Tuning

Apr 18, 2026cs.CL

Crowded in B-Space: Calibrating Shared Directions for LoRA Merging

Merging separately trained LoRA adapters is a practical alternative to joint multi-task training, but it often hurts performance. Existing methods usually treat the LoRA update

ΔW = BA

as a single object and do not distinguish the two LoRA matrices. We show that the main source of LoRA merge interference comes from the output-side matrix

B

. Across tasks,

B

repeatedly uses a small set of shared directions, while

A

remains much more task-specific. As a result, the merged adapter overemphasizes these shared directions, and task-specific information is lost. We propose Pico (Pre-merge interference calibration in output-space), a data-free method that calibrates

B

before merge by downscaling over-shared directions and then rescaling the merged update. Pico plugs directly into existing merging methods such as Task Arithmetic, TIES, and TSV-M. Across eight different benchmarks from math, coding, finance, and medical domains, Pico improves average accuracy by 3.4-8.3 points over the corresponding base method and achieves the best overall average performance. Pico also enables merged adapters to outperform the LoRA trained with all task data. These results show that LoRA merging works better when the two LoRA matrices are treated separately.

Yixuan Tang, Yi Yang

The Hong Kong University of Science and Technology

Adapter Tuning Low-Rank Adaptation Task Vector Merging Language Model Merging Model Merging

Apr 18, 2026cs.AI

Introspection Adapters: Training LLMs to Report Their Learned Behaviors

When model developers or users fine-tune an LLM, this can induce behaviors that are unexpected, deliberately harmful, or hard to detect. It would be far easier to audit LLMs if they could simply describe their behaviors in natural language. Here, we study a scalable approach to rapidly identify learned behaviors of many LLMs derived from a shared base LLM. Given a model

M

, our method works by finetuning models

M_i

from

M

with implanted behaviors

b_i

; the

(M_i, b_i)

pairs serve as labeled training data. We then train an introspection adapter (IA): a single LoRA adapter jointly trained across the finetunes

M_i

to cause them to verbalize their implanted behaviors. We find that this IA induces self-description of learned behaviors even in finetunes of

M

that were trained in very different ways from the

M_i

. For example, IAs generalize to AuditBench, achieving state-of-the-art at identifying explicitly hidden concerning behaviors. IAs can also be used to detect encrypted finetuning API attacks. They scale favorably with model size and training data diversity. Overall, our results suggest that IAs are a scalable, effective, and practically useful approach to auditing fine-tuned LLMs.

Keshav Shenoy, Li Yang, Abhay Sheshadri +4

Anthropic Fellows · Ashwood Centre on AI Science and Policy, University of Cambridge · Anthropic

LLM Auditing Language Model Introspection Language Model Self-Assessment Adapter Tuning Language Model Probing

Mar 14, 2026cs.CV

SK-Adapter: Skeleton-Based Structural Control for Native 3D Generation

Native 3D generative models have achieved remarkable fidelity and speed, yet they suffer from a critical limitation: inability to prescribe precise structural articulations, where precise structural control within the native 3D space remains underexplored. This paper proposes SK-Adapter, a simple yet efficient and effective framework that unlocks precise skeletal manipulation for native 3D generation. Moving beyond text or image prompts, which can be ambiguous for precise structure, we treat the 3D skeleton as a first-class control signal. SK-Adapter is a lightweight structural adapter network that encodes joint coordinates and topology into learnable tokens, which are injected into the frozen 3D generation backbone via cross-attention. This design allows the model to not only effectively ``attend'' to specific 3D structural constraints but also preserve its original generative priors. To bridge the data gap, we contribute the Objaverse-TMS dataset, a large-scale dataset of 24k text-mesh-skeleton pairs. Extensive experiments confirm that our method achieves robust structural control while preserving the geometry and texture quality of the foundation model, significantly outperforming existing baselines. Furthermore, we extend this capability to local 3D editing, enabling region-specific editing of existing assets with skeletal guidance, which is unattainable by previous methods. Project page: https://sk-adapter.github.io/

Anbang Wang, Yuzhuo Ao, Shangzhe Wu +1

The Hong Kong University of Science and Technology · University of Cambridge

3D Foundation Models 3D Asset Generation Adapter Tuning 3D Shape Generation

Feb 26, 2026cs.LG

CeRA: Breaking the Linear Ceiling of Low-Rank Adaptation with Non-linearity Retained at Inference

Low-Rank Adaptation (LoRA) dominates parameter-efficient fine-tuning (PEFT). However, it faces a ``linear ceiling'': increasing the rank yields diminishing returns in expressive capacity due to linear constraints. We introduce CeRA (Capacity-enhanced Rank Adaptation), a weight-level parallel adapter that injects SiLU gating and dropout to induce non-linearity during inference, thereby placing it in a different function class from adapters whose non-linearity exists during training and collapses to an affine map at inference time. On both the basic arithmetic (GSM8K) and the complex MATH benchmark, CeRA is markedly more parameter-efficient. Across a full rank

\times

learning rate sweep, CeRA at rank 64 achieves the highest MATH pass@1 of any configuration in the grid (23.6%), matching or exceeding both a rank-512 LoRA (22.4%) and DoRA (19.8%) while using only 1/8 of the parameter budget. With the rank and learning rate fixed, CeRA equals or outperforms LoRA in 10 of 12 matched settings. Spectrally, CeRA's learned updates utilize the singular-value spectrum more broadly than linear adapters, which exhibit rank collapse at high rank, although a scale-matched control shows that this difference stems mostly from output scale and partially from non-linearity. Additionally, dropout appears to contribute to regularization rather than rank expansion. We release the code for reproducibility: https://github.com/hhchen1105/cera.

Hung-Hsuan Chen

Computer Science and Information Engineering National Central University Taoyuan, Taiwan

Adapter Tuning Low-Rank Adaptation Parameter-Efficient Fine-Tuning

Jun 10, 2025cs.LG

MetaTT: A Global Tensor-Train Adapter for Parameter-Efficient Fine-Tuning

We present MetaTT, a Tensor Train (TT) adapter framework for fine-tuning of pre-trained transformers. MetaTT enables flexible and parameter-efficient model adaptation by using a single shared TT to factorize transformer sub-modules. This factorization indexes key structural dimensions, including layer and matrix type, and can optionally incorporate heads and tasks. This design allows MetaTT's parameter count to scale with the sum, rather than the product, of the modes, resulting in a substantially more compact adapter. Our benchmarks compare MetaTT with LoRA along with recent state-of-the-art matrix and tensor decomposition based fine-tuning methods. We observe that when tested on single-task standard language modeling benchmarks, MetaTT achieves competitive parameter efficiency to accuracy tradeoff. We further demonstrate that MetaTT performs competitively when compared to state-of-the-art methods on multi-task learning. Finally, we leverage the TT decomposition to design a rank adaptive optimizer inspired by the DMRG method from many-body physics. Our results demonstrate that integrating this approach with AdamW enhances optimization performance for a specified target rank.

Javier Lopez-Piqueres, Pranav Deshpande, Archan Ray +3

Global Technology Applied Research, JPMorgan Chase, New York, NY 10001, USA

Transformer Tensor Decomposition TT Decomposition Adapter Tuning Parameter-Efficient Fine-Tuning

Date pendingcs.CL

ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning

Popular low-rank parameter-efficient fine-tuning (PEFT) methods represent adaptation as separate updates to selected backbone weights, without maintaining an explicit task-specific state that is updated and reused across depth. These updates also require the backbone at inference and therefore cannot operate as standalone predictors. We propose ShadowPEFT, which consolidates trainable adaptation into a modular shadow component centered on a compact shadow model and lightweight Transformer layer-specific coupling modules. A persistent shadow state refines the frozen backbone representations and is updated from them in an interactive manner. Because the shadow model is trained as a complete predictor, it can be detached for shadow-only inference without executing the base model and can be initialized from a pretrained model. Experiments on text and image generation and understanding benchmarks show that ShadowPEFT matches or outperforms LoRA and DoRA under comparable trainable-parameter budgets. Additional analyses on shadow pretraining, cross-dataset transfer, parameter scaling, inference latency, and system-level evaluation suggest that centralized layer-space adaptation is a competitive and flexible alternative to conventional low-rank PEFT.

Xianming Li, Zongxi Li, Tsz-fung Andrew Lee +3

PolyU · School of Data Science, Lingnan University, Hong Kong SAR

Fine-Tuning Adapter Tuning Low-Rank Adaptation Parameter-Efficient Fine-Tuning