Parameter-Efficient Fine-Tuning

Also known as PEFT

Ask about this topic

Overview

Parameter-efficient fine-tuning studies how to adapt pretrained models while training only a small subset of weights or adding lightweight modules, reducing resource costs and sometimes helping preserve existing capabilities. Common approaches include low-rank updates such as LoRA and quantized QLoRA, adapters and soft prompts, selective layer or rank tuning, and sparse or routed experts. Methods are evaluated on language benchmarks such as GLUE and mathematical reasoning, as well as vision, speech, multimodal, and continual-learning tasks, often with limited data or hardware. A central tension is that fewer trainable parameters do not necessarily mean lower memory use or faster training, and accuracy, robustness, and retention can vary with the model, task, and placement of updates.

Latest papers

CardsList

610 papers75 papers in the last four weeks, up 12% on the four weeks before. 0.4% of all new papers.

Oct 2, 2026

FUSEye: Training-Light Fisheye Detection with Overlapping Views and Zero-Initialized Adapters

Fisheye cameras give mobile robots a single-sensor, low-cost view of their surroundings, yet the COCO-pretrained detectors that practitioners routinely reuse fail on them: strong radial distortion warps local image structure, while boundary compression shrinks objects to near-invisible sizes. Full fine-tuning closes much of the gap but requires abundant fisheye labels and compute. We present FUSEye, a training-light framework that turns a frozen-backbone COCO-pretrained extra-large YOLO26 detector (YOLO26-x) into a fisheye detector. FUSEye adds roughly 227k new parameters while updating the inserted modules and the pretrained detection head. It addresses the transfer gap at three causally linked levels. At the input level, overlapping grid view generation and box remapping (GridViews) enlarge compressed boundary regions. At the feature level, zero-initialized residual adapters (Z-Adapters) correct distortion-induced feature misalignment. At the decision level, learned cross-projection agreement fusion (AgreeFusion) promotes low-confidence detections only when they are supported by consistent evidence across multiple views. On the WoodScape surround-view fisheye benchmark, FUSEye raises YOLO26-x from 0.148 to 0.266 mAP50 and retains 84.3% fully fine-tuned accuracy. Moreover, randomly using only 25% of the labeled training images, FUSEye achieves 0.2597 mAP50, retaining 97.6% of its full-label performance. FUSEye also consistently improves YOLOv8-11 detectors, showing that the recipe is architecture-agnostic. Source code will be available at https://github.com/Su-wenya/FUSEye.

Wenya Su, Kai Luo, Di Wen +5

School of Artificial Intelligence and Robotics and the National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, China · Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology, Germany

Object DetectionEfficient Object DetectionParameter-Efficient Fine-TuningAdapter Tuning
AskPDF
Oct 1, 2026

Harnessing Domain Specialists in Multimodal Mixture-of-Experts for Efficient Adaptation

Mixture-of-Experts (MoE) architectures scale model capacity through sparse computation, routing each token through only a small subset of experts. In this work, we explore whether this sparsity gives rise to emergent intrinsic organization in multimodal MoEs. We find that experts develop strong semantic specialization across modalities and domains despite not being explicitly trained for modularity. Building on this structure, we introduce ExpertLens, a data-free method that identifies domain-specialized experts directly from pretrained model weights by decoding router weights into semantically meaningful vocabulary tokens. We leverage this specialization for efficient multimodal adaptation by selectively fine-tuning experts relevant to a target domain. Across math, medical, and remote sensing tasks, ExpertLens matches or surpasses full fine-tuning while updating only 21.7 - 47.0% of model parameters and achieving a 4.0x average training speedup, and outperforms LoRA in both adaptation performance and training efficiency. These results show that sparsity introduced for efficiency can give rise to semantic modularity that is directly useful for efficient adaptation.

Damiano Marsili, Raphi Kang, Aditya Mehta +2

California Institute of Technology

Mixture of ExpertsMixture-of-Experts ModelsMultimodal LearningParameter-Efficient Fine-Tuning
AskPDF
Oct 1, 2026

Task-Oriented Rank Adaptation for Continual Learning in Text Classification

Continual learning (CL) in text classification faces two critical challenges: catastrophic forgetting and negative transfer across sequential tasks. Parameter-Efficient Fine-Tuning (PEFT) methods such as LoRA enable efficient adaptation by learning low-rank updates of the model parameters. However, these compact representations are normally trained in isolation, limiting their reuse across related tasks. We introduce Task-Oriented Rank Adaptation (TORA), a geometric routing framework that leverages the low-rank structure of LoRA adapters to decide whether to transfer knowledge from the most compatible expert (Boosting) or isolate the new task (Shielding) based on structural similarity. Evaluated across 15 diverse text classification benchmarks, TORA consistently avoids harmful routing decisions: compatible tasks exceed their isolated performance while reducing training time, and structurally distant tasks are protected from interference with no loss in accuracy. With a single geometric threshold and no reliance on task identities or predefined sequences, TORA provides a simple and effective approach for dynamic adapter routing in sequential text classification systems.

Rey Sanchez Lopez, Eduardo Morales Manzanares, Hugo Jair Escalante

INAOE, Puebla, Mexico · The University of Texas at El Paso, El Paso, TX, USA

Continual LearningLow-Rank AdaptationNegative TransferParameter-Efficient Fine-TuningCatastrophic Forgetting
AskPDF
Oct 1, 2026

Beyond Domain-Level Adaptation: Margin-Oriented Semantic-Appearance Interaction Correction for Personalized Federated Vision-Language Models

Federated parameter-efficient fine-tuning enables distributed clients to adapt pretrained vision-language models without sharing raw data or updating the full backbone. Its effectiveness, however, is limited by domain heterogeneity across clients. Existing personalized methods separate globally shared knowledge from client-specific style, but they largely treat each domain as a class-agnostic transformation. We show that this abstraction is insufficient: the cross-domain displacement associated with a fixed domain varies across semantic classes, and only a subset of these class-domain residuals damages the image-text decision margin. We therefore propose Margin-Oriented Semantic-Appearance Interaction Correction (MOSAIC), which first constructs a decision-aware harmfulness score that measures whether a training-derived class-domain residual favors a competing text prototype over the true class. It then models fine-grained class-domain interactions with a low-rank residual adapter whose class factors and residual basis are globally shared while domain factors remain client-private. An image-conditioned gate further controls candidate-wise correction, and harmful-pair-aware reweighting prioritizes decision-relevant residuals during local optimization. Extensive experiments on Office31, OfficeHome, and DomainNet100 demonstrate that MOSAIC consistently improves macro-client top-1 accuracy across all evaluated domain-shift and joint domain-label-shift settings.

Wentao Yue, Qingyu Mao, Tianyou Lai +2

VLM AdaptationFederated Fine-TuningFederated LearningParameter-Efficient Fine-Tuning
AskPDF
Oct 1, 2026

Parameter-Efficient Distributionally Robust Adaptation of Tabular Foundation Models under Subpopulation Shift

Despite strong mean accuracy, tabular foundation models (TFMs) can perform poorly on underrepresented groups under subpopulation shift, where group proportions change between training and deployment. We propose DR-TFM, a parameter-efficient distributionally robust adaptation framework that requires no true group annotations. DR-TFM adjusts attention to labeled context examples by fine-tuning an existing query scaling network or adding and training one, while keeping all other parameters fixed. We instantiate the framework with two robust objectives using estimated groups or source conditional distributions derived from training data. For TabPFN-3, adaptation updates only 0.016% of the pretrained model's parameters. Across five tabular benchmarks, DR-TFM achieves substantially higher average worst-group accuracy than pretrained TFMs and the compared robust baselines without true group annotations, while maintaining competitive mean group accuracy. DR-TFM also improves average worst-group accuracy on ACS Income and across four additional TFMs.

Seonghwi Kim, Sung Ho Jo, Minwoo Chae

Pohang University of Science and Technology

Distribution Shift RobustnessTabular Foundation ModelsDistribution ShiftDistributionally Robust OptimizationParameter-Efficient Fine-Tuning
AskPDF
Oct 1, 2026

Efficient Task Adaptation in Large Language Models: A Survey of Weight-Based, Prompt-Based, and Embedding-Based Adaptations

As large language models are increasingly deployed across diverse downstream tasks, efficient task adaptation has emerged as a central challenge. In response, a wide range of task adaptation methods have been proposed, spanning parameter-efficient fine-tuning, in-context learning, and embedding-injection approaches. However, these lines of work have largely evolved within individual paradigms, leaving their cross-paradigm relationships and trade-offs underexplored, especially for recently emerging embedding-based adaptations. This survey presents a unified framework that categorizes task adaptation methods by where and how task information is encoded: model weights, input prompts, or injected task embeddings. We provide a comprehensive taxonomy that integrates these paradigms, analyze their key strengths and limitations to explain how different adaptation paradigms have evolved, clarify relationships across paradigms, and highlight open problems for future research.

Jungwon Park, Changin Choi, Jimyeong Kim +2

RICS · Daegu Gyeongbuk Institute of Science and Technology · IPAI +3

LLM Fine-TuningIn-Context LearningParameter-Efficient Fine-Tuning
AskPDF
Sep 30, 2026

Analysis of Quantized and Efficiently Adapted Protein Language Models

Background: Protein language models (PLMs) are increasingly used for sequence generation and property prediction, but their size makes fine-tuning and deployment expensive. The effects of quantization and parameter efficient fine-tuning on performance, representations and generation remain insufficiently characterized. Results: We evaluated 4-bit quantization and low-rank adapter fine-tuning (QLoRA) across ESM-2, ESMC, ProtBERT, ProtT5, Ankh, Ankh3 and Profluent-E1. Across protein prediction tasks, many model-task pairs retained more than 90% of full fine-tuning performance. Peak GPU memory savings approached 90% for the largest models, although performance and efficiency varied by model, dataset and training configuration. QLoRA often preserved early-layer representations while inducing task-specific adaptations in middle and late layers, resembling full fine-tuning with smaller representational changes. Training speed and power effects were more varied. For unconditional generation with ProLLaMA, ProtGPT2, ProGen2, ProteinGLM and ESM3, 4-bit quantization largely preserved predicted structural and sequence-level properties, but token-level analysis revealed model-dependent shifts in autoregressive output distributions. Conclusion: QLoRA and 4-bit quantization reduce PLM computational requirements, particularly GPU memory usage. Our results support QLoRA as a first-pass strategy for memory limited adaptation, reserving full fine-tuning for challenging tasks, unstable architectures or low validation recovery. For generative PLMs, sequence-level and structural metrics should be complemented with distributional analysis, since downstream predictions alone may miss quantization-induced shifts. These approaches can broaden access to large-scale protein modelling while requiring model- and task-specific validation.

Ilan Yaniv Zeisler, Sebastian Clancy, Pouriya Bayat +8

Leslie Dan Faculty of Pharmacy, University of Toronto, Toronto, ON, Canada. · Department of Electrical and Computer Engineering, University of Toronto, Toronto, Ontario, Canada. · Department of Computer Science, University of Toronto, Toronto, Ontario, Canada. +2

Protein Language ModelsQuantization-Aware LoRAMolecular GenerationParameter-Efficient Fine-Tuning
AskPDF
Sep 30, 2026

Score the Update, Not the Token: Descent-Aligned Routing for Combinatorial LoRA Experts

Mixture-of-LoRA-experts methods raise the capacity of low-rank adaptation by routing each token to a few low-rank experts. Nearly all of them tie one input-side factor to one output-side factor per expert, and nearly all of them route by scoring the token: the router picks experts without seeing what any of them would write. We argue that the router should score the update. To first order, adding an expert's update to a layer output lowers the loss by the inner product between that update and the negative loss gradient at the output. This usefulness is quadratic in the token, so a router that is linear in the token sees only the part of it that runs through the token mean, and routers that rank experts by the norm of their own activations never see the output factor. If each expert is split into a reader (down-projection) and a writer (up-projection), the usefulness of every reader--writer pair becomes an inner product in the shared rank-rr space, and all NANBN_AN_B pairs can be scored from NA+NBN_A+N_B vectors. We build VANE on this identity. A low-rank compass predicts the descent direction of each token. VANE scores every pair by the alignment between its update and the compass without forming any update, activates the top-kk pairs with additive gates, and gives every pair its exact first-order router gradient. On single-domain commonsense reasoning and a four-domain multi-task mixture with Llama-3.2-3B and Llama-3.1-8B, VANE attains the best average among twelve PEFT and MoE-LoRA baselines, by 0.9--1.1 and 1.3--1.5 points respectively, with less than half the trainable parameters of an 8-expert MoE-LoRA. Its router scores also track the measured usefulness of experts far more closely than token routers do.

Priya Nair, Lukas Brenner, Maya Lindqvist +5

University of California, Irvine · University of Washington

Mixture-of-Experts Language ModelsParameter-Free Mixture-of-Experts RoutingLow-Rank AdaptationMixture-of-Experts ModelsParameter-Efficient Fine-Tuning
AskPDF
Sep 30, 2026

ChainLoRA: Geometry-Preserving Task Vector Merging for Continual Learning in LLMs

Continual parameter-efficient fine-tuning for large language models (LLMs) must balance retention of previously acquired knowledge, adaptation to new tasks, and strict parameter budgets. We present ChainLoRA, a replay-free continual merging framework built on chain-updated task-vector geometry. From a parameter-merging perspective, we formulate a geometric view of forgetting through a measurable interaction between task updates, separating directional overlap from coefficient coupling. Building on this view, ChainLoRA combines chain-updated training with post-stream adaptive SVD merging. During training, initialization and a one-sided orthogonality proxy use only the last carrier, keeping their historical-state footprint and regularization overhead constant as the task stream grows. At merging time, Adaptive SVD extracts a shared carrier and aligns it to the latest task through Procrustes adaptation. Our theoretical analysis shows that Procrustes adaptation facilitates geometric approximate separation of shared and task-specific components. The one-sided proxy further bounds inter-task interference. An effective-rank penalty additionally promotes efficient utilization of the task subspace during continual learning. Experiments show that ChainLoRA achieves state-of-the-art performance among the evaluated replay-free methods on the Large and SuperNI benchmarks, while remaining competitive on Standard CL and attaining almost the closest average scores to the evaluated replay-based method across all three benchmarks.

Hang Yin, Haozhe Wang, Yuhua Luo +3

Shanghai Jiao Tong University · Shanghai Innovation Institute · Beijing Zhongguancun Academy +3

Continual Learning for LLMsLow-Rank AdaptationTask Vector MergingLanguage Model MergingModel MergingParameter-Efficient Fine-Tuning
AskPDF
Sep 30, 2026

Dynamic LoRA-Experts and Prototype-Ensemble Matching for Class-Incremental Learning

Class-Incremental Learning (CIL) aims to continuously learn new classes without forgetting previously acquired knowledge. Parameter-efficient fine-tuning with pre-trained models reduces parameter overhead but can suffer from cumulative interference and suboptimal alignment between inference samples and specialized modules. We propose Dynamic LoRA-Experts and Prototype-Ensemble Matching (DLEPEM), a two-stage rehearsal-free framework. DLEPEM allocates a task-specific LoRA-Expert for each incremental task to reduce cross-task interference, then combines frozen pre-trained-model prototypes with task-adaptive LoRA-Expert prototypes for reliable task-level discrimination. Experiments on standard CIL and Few-Shot CIL benchmarks demonstrate strong performance under the evaluated protocols.

Hongwei Zhao, Rui Liu, Yansong Liu

School of Computer Science and Engineering, Beihang University

Class-Incremental LearningPrototype-Based ClassificationContinual LearningLow-Rank AdaptationParameter-Efficient Fine-Tuning
AskPDF
Sep 30, 2026

T-Router: Learning Thalamic Routing for Reasoning with Parameter-Efficient Reinforcement Learning

Parameter-efficient reinforcement learning aims to improve reasoning with a compact trainable interface to a pretrained model. We introduce the Thalamic Router (T-Router), which concentrates adaptation on the reuse of completed computations. A compressed, addressable bank preserves block changes; a depth-recurrent controller conditions their selection and relative-scale writeback. This coupling gives thalamic context-dependent routing a concrete computational form: learn which earlier contributions a receiving layer uses, and with what influence. Correctness rewards train the interface while preserving backbone parameters and layer order. On an 8.95B-parameter backbone, T-Router allocates 41.73M parameters (0.466% of the backbone) and achieves 83.64 +/- 1.16 MathAvg after GSM8K RL, compared with 73.79 +/- 1.83 for full-parameter GRPO across three evaluation rounds. At a comparable parameter budget and with matched retries, it exceeds LoRA's 77.28 +/- 1.95 MathAvg, improving all three task families and raising mean AIME accuracy from 48.33 to 60.56. Capacity-controlled comparisons favor addressable block changes and recurrent context; separate search training extends the interface to tool-mediated reasoning. These results establish controlled computation reuse as an effective route to parameter-efficient reasoning reinforcement learning.

Liuxian Ma, Jiale Dai, Jiaqi Li +1

College of Artificial Intelligence, Tsinghua University · State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · Beijing Institute for General Artificial Intelligence

Reinforcement LearningRL for Language Model ReasoningMathematical ReasoningParameter-Efficient Fine-Tuning
AskPDF
Sep 29, 2026

A foundation model for energy and radiation systems built on heterogeneous scientific interfaces

Scientific foundation models are commonly evaluated after heterogeneous physical problems have already been translated into a compatible gridded, tokenized or symbolic representation. This leaves the scientific interface outside both the pretrained model and the audit of what is actually reused. We study the complementary setting in which boundary histories, sparse monitor records and loading histories retain their native inference classes and their outputs remain on Cartesian, latitude-longitude and unstructured domains. GEODE couples task-specific scientific interfaces to a shared routed library of wavelet operators. A single jointly pretrained model represents cavity flow, radiation dose and elastoplastic stress, then acquires a heat exchanger and a reactor subchannel by training a private interface containing 2.1% of its parameters. Earlier predictions remain unchanged by parameter isolation, whereas unrestricted fine-tuning degrades them by factors of 14-29. Crucially, preservation alone does not establish reuse: norm-matched randomized-library controls show that the contribution of pretrained computation is conditional on the task and data regime. A separate decomposition shows that full-field relative L2 error can substantially understate error relative to spatial variation when field level dominates the norm. Task-specific operators remain more accurate on three of the five problems. These results distinguish multi-task coverage, preservation and pretrained reuse as separate properties that must be tested independently when scientific foundation models span heterogeneous interfaces.

Samrendra Roy, Tapas Tripura, Yoon Pyo Lee +2

Department of Nuclear, Plasma, and Radiological Engineering, University of Illinois Urbana-Champaign, Urbana, IL 61801, USA · Department of Applied Mechanics, Indian Institute of Technology Delhi, Hauz Khas, New Delhi 110016, India · Yardi School of Artificial Intelligence (ScAI), Indian Institute of Technology Delhi, Hauz Khas, New Delhi 110016, India +1

Physical Foundation ModelsPDE Surrogate ModelingNeural OperatorsParameter-Efficient Fine-TuningCatastrophic Forgetting
AskPDF
Sep 29, 2026

FedLAFP: Low-Rank Aggregation Meets Full-Rank Personalization in Federated Fine-Tuning

Federated parameter-efficient fine-tuning enables clients to adapt pre-trained models without sharing raw data or communicating the full model, but statistical heterogeneity makes a single global adapter insufficient for personalized prediction. Existing personalized methods typically use the same low-rank structure for both shared and private adaptation, overlooking their distinct requirements for aggregation and personalization. We propose FedLAFP, a role-aware framework that couples a compact, globally aggregated LoRA branch with a client-private, full-rank-capable RandLoRA branch. The shared branch provides an efficient interface for transferring common knowledge, whereas the private branch combines fixed random low-rank bases with learned scaling coefficients to provide expressive client-specific adaptation without additional communication. Client- and layer-specific mixing coefficients jointly fuse the two branches, and only the shared LoRA parameters are exchanged. A controlled linear study supports this role assignment: LoRA yields more aligned client updates and lower aggregation error, while RandLoRA more accurately recovers client-specific residuals. Experiments across four visual recognition benchmarks show that FedLAFP consistently outperforms local-only and federated LoRA baselines, achieving an average personalized accuracy of 86.93%86.93\% and exceeding the best baseline average by 1.301.30 percentage points.

Mengjun Yi, Huaian Gu, Yinghao Ai +2

State Key Laboratory for Novel Software Technology · School of Artificial Intelligence · School of Computer Science +1

Low-Rank AdaptationFederated Fine-TuningFederated LearningParameter-Efficient Fine-Tuning
AskPDF
Sep 29, 2026

Beyond Low-Rank Parameterization: Narrowing the Gap Between LoRA and Full Fine-Tuning via Gradient Decomposition

Low-Rank Adaptation (LoRA) is a widely used approach to parameter-efficient fine-tuning (PEFT), yet a performance gap can remain relative to full fine-tuning (FFT). Many LoRA variants improve the initialization or optimization of low-rank factors. At each training step, however, their first-order weight-space directions are constrained by the current parameterization. We characterize the corresponding LoRA-accessible gradient space and show that it coincides with the tangent space induced by the current LoRA parameterization. This characterization yields an orthogonal decomposition of the full weight gradient at the current model parameters. We term the component orthogonal to this space the normal gradient. Based on this decomposition, we propose GDLoRA (Gradient-Decomposed Low-Rank Adaptation). GDLoRA reconstructs the full weight gradient from forward activations and backward signals, extracts its normal component, and directly updates the base weights with this component, while retaining standard AdamW optimization for the LoRA factors. GDLoRA incorporates complementary normal gradients without increasing standard LoRA's optimizer-state memory budget under matched adapter and optimizer configurations. Experiments on natural language understanding, mathematical reasoning, commonsense reasoning, and image classification show that GDLoRA consistently improves over LoRA and narrows the performance gap to FFT. The code is available at https://anonymous.4open.science/r/GDLoRA.

Yihao Ouyang, Shiwei Li, Haozhao Wang +5

Huazhong University of Science and Technology, Wuhan, China · Hebei University of Technology, Tianjin, China

Low-Rank AdaptationParameter-Efficient Fine-Tuning
AskPDF
Sep 29, 2026

CF-LoRA: Decoupled Factor Aggregation and Adaptation-Aware Client Clustering for Federated LoRA Fine-Tuning

Federated LoRA fine-tuning enables parameter-efficient adaptation of pre-trained models without sharing private data, but suffers from two fundamental mismatches under heterogeneous client data: a structural aggregation mismatch caused by independently averaging LoRA factors, and a statistical collaboration mismatch caused by enforcing a single global adapter across divergent clients. To address these issues, we propose CF-LoRA, a clustered federated LoRA fine-tuning framework that combines decoupled factor aggregation with adaptation-aware client clustering. CF-LoRA first learns a globally shared AA factor while retaining personalized BiB_i factors, then identifies clients with similar adaptation patterns based on the cosine similarity of their learned BiB_i factors, and finally performs intra-cluster BB-factor aggregation with a frozen AA factor. By decoupling LoRA factor aggregation, CF-LoRA preserves the low-rank structure and mitigates the structural aggregation mismatch, while adaptation-aware clustering promotes collaboration among clients with similar adaptation patterns and reduces negative transfer caused by statistical heterogeneity. Experiments on four language tasks and four vision datasets with RoBERTa and ViT show that CF-LoRA achieves the highest average accuracy in both modalities while communicating only one LoRA factor per optimization round.

Mengjun Yi, Langxing Yang, Suhan Guo +2

State Key Laboratory for Novel Software Technology · School of Artificial Intelligence School of Electronic Science and Engineering Nanjing University

Federated Learning AggregationFederated Fine-TuningClustered Federated LearningFederated LearningParameter-Efficient Fine-TuningHeterogeneous Federated Learning
AskPDF
Sep 28, 2026

Reducing the Adaptation Gap Through Reachable Fisher Geometry

Parameter-efficient fine-tuning (PEFT) determines not only how many parameters are trained, but also which local directions a model can move in, so similar adapters can affect subgroup losses differently. Since curvature matrices are infeasible to form at adapter scale, scalar summaries such as the Fisher trace are often used instead. We study what the trace reveals and what it loses through the reachable Fisher: each subgroup's full-model Fisher pulled back through the adapter Jacobian. Under likelihood losses, it represents the Gauss-Newton curvature accessible to the adapter, and its trace can be computed from score-gradient norms without forming the full matrix. Under matched subgroup gradients, a positive-definite reachable-Fisher difference, with a margin exceeding the Hessian-Fisher defect, implies that every sufficiently small nonzero model-changing update increases the signed gap. In contrast, the restricted operator norm determines worst-case quadratic change, while a matrix-free Frobenius discrepancy bounds its reachable-Fisher component. Trace alone cannot certify definiteness or control matrix mismatch. Equal traces rule out a positive-definite difference but can still hide large operator discrepancies. Across 306 single-seed models, higher trace accompanies greater subgroup difficulty in 75.7 percent of 1,218 eligible evaluations, while trace matching reduces the best-worst subgroup gap in all 30 dataset-encoder-adapter combinations. However, held-out audits show that operator discrepancy decreases in 23 of 30 combinations, while the unbiased squared-Frobenius statistic decreases in only 16 of 30. Fisher trace is therefore a scalable diagnostic and training heuristic, but not a certificate of local gap behavior or matrix alignment.

Wasif Jalal, Sachin Deb, Asif Salekin

Arizona State University Tempe, Arizona, USA

Parameter-Efficient Fine-TuningGroup FairnessInformation Geometry
AskPDF
Sep 28, 2026

RoboFL: Federated Expert Assembly for World Action Models

Vision-language-action and world-action models are increasingly popular, yet remain bottlenecked by physical interaction data that is scarce, institutionally siloed, and task-heterogeneous. A natural federated solution is to let each client adapt a shared foundation model through parameter-efficient fine-tuning, avoiding the exchange of full-model updates. However, federating these adapters is nontrivial, as naive aggregation can entangle incompatible updates, while incorporating MoE-style routing into federated aggregation may dilute specialization and destabilize expert selection. We present RoboFL, which instantiates MoSAIC (Mixture of Slotted Adapters) for federated world-action learning. MoSAIC directly installs locally trained LoRA adapters as the expert branches of a server MoE. Server-side routers learn token assignments over these prior-informed branches while jointly refining routing and expert parameters. Foresight-to-Action Routing Distillation (FARD) aligns routing across the model's three paths, while Path-Consensus Expert Aggregation (PCEA) converts complete expert updates into a compact global adapter for personalized redistribution. Experiments on RoboTwin 2.0, RLBench, and a real-world Franka robot arm show the superiority of RoboFL with structured expert assembly, as it outperforms centralized PEFT InternVLA-A1 by 12.23% on the Franka arm, while reducing per-round client communication by up to 86.81% relative to MoE-based federated VLA baselines.

Rongyu Zhang, Ruizhi Fan, Yunfan Lou +8

Nanjing University · Hong Kong University of Science and Technology · State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University

Mixture of ExpertsWorld Action ModelsFederated Fine-TuningFederated LearningParameter-Efficient Fine-Tuning
AskPDF
Sep 28, 2026

Distribution-Conditioned Task Routing for Class-Incremental Learning

Parameter-efficient adaptation enables continual learners to acquire task-specific knowledge through compact model updates while maintaining strong within-task performance. However, class-incremental inference requires each input to be classified among all classes seen so far without access to its task identity. For learners equipped with task-specific parameter-efficient modules, this introduces a critical task-routing challenge beyond catastrophic forgetting. We study post-hoc task routing without retraining the learner or introducing a separately trained router. Such training-free inference-time calibration remains comparatively underexplored in parameter-efficient class-incremental learning. We identify three sources of routing error (feature-level, task-level, and class-level misalignment) and propose Feature Distribution Calibration (FDC). Its three components address these misalignments: Task Subspace Filtering (TSF) suppresses feature components outside each task's principal subspace, Residual Likelihood Calibration (RLC) evaluates the typicality of its subspace residual, and Prototype Affinity Calibration (PAC) measures compatibility with the task's class prototypes. Experiments demonstrate plug-and-play applicability to eight parameter-efficient class-incremental methods using a shared encoder. With one component configuration selected per method across all five benchmarks, FDC improves final accuracy in all 40 method-dataset pairs by 4.39 percentage points on average. Enabling all components improves 35 of the 40 pairs, with an average gain of 4.45 points. When applied to a simple baseline, FDC achieves strong overall performance.

Longhuan Xu, Zhipeng Zhou, Wei Ji +3

Nanjing University · Nanyang Technological University · Shanghai Jiao Tong University

Class-Incremental LearningClassificationParameter-Efficient Fine-Tuning
AskPDF
Sep 28, 2026

Learn Here, Move Less Elsewhere: Input-Conditioned Plasticity from Retained-Domain Activation Atlases

Task-specific fine-tuning can rewrite a language model's answers beyond the training task, complicating updates that must preserve existing behavior. We introduce ATLAS, which turns retained-domain representations into an input-dependent rule for task adaptation. An activation atlas supplies local reference centers and directional filters to a shared low-rank residual. Target supervision learns the residual, while retained geometry shapes its action throughout training and inference. On Qwen3-8B, ATLAS achieves lower mean retained-output Kullback-Leibler (KL) divergence than all seven published baselines at shared coding-performance requirements, with consistent advantages across multiple training seeds. Structural comparisons identify the contributions of retained reference states and directional conditioning, and answer-level analyses show fewer rewritten mathematical answers and more stable commonsense choices. Experiments spanning five backbones and two retained domains further demonstrate coding gains with reduced retained-output movement. With compact storage and modest decoding overhead, ATLAS provides a practical mechanism for acquiring specialized skills while maintaining continuity in existing responses.

Jiangtao Lin, Bangyang Wei, Yihang Ding +2

Tsinghua Shenzhen International Graduate School, Tsinghua University · School of Vehicle and Mobility, Tsinghua University · SZ DJI Technology Co., Ltd. +1

Continual Learning for LLMsDomain Adaptation for LLMsRepresentation Geometry in Language ModelsParameter-Efficient Fine-TuningCatastrophic Forgetting
AskPDF
Sep 28, 2026

Loop Dropout: Regularizing Shared Updates in Looped Language Models

Looped language models separate computational depth from parameter count by repeatedly applying the same transformer block. Adapting these models requires a shared update that remains effective as hidden states evolve throughout the recurrent computation. Our empirical analysis reveals a pronounced late-loop bias in standard low-rank adaptation (LoRA): the shared update provides limited adaptation at early loop positions. This imbalance motivates training shared updates under varying combinations of their applications. Randomly omitting adapter applications alone, however, does not improve task performance; it reduces expected update strength during training while leaving inference unchanged. We introduce Loop Dropout, which couples stochastic masking of adapter applications with inverse-survival rescaling to preserve expected update strength and promote effective adaptation across loops. Extensive experiments demonstrate improved mathematical reasoning across model sizes, adapter ranks and training recipes, with benefits extending to general instruction tuning and code generation. Loop Dropout outperforms existing LoRA variants and adapter regularizers, while further analysis shows stronger early-loop adaptation. Every backbone loop remains active, and inference applies the adapter at all loops using standard LoRA without additional trainable parameters or inference computation. Code is available at https://github.com/NUS-HPC-AI-Lab/loop-dropout .

Zirui Zhu, Hailun Xu, Xuanlei Zhao +5

Low-Rank AdaptationParameter-Efficient Fine-TuningRecursive Language Models
AskPDF
Sep 27, 2026

Optimizing the Phi-2 Small Language Model for Real-time Chatbot Applications Using Parameter-Efficient Fine-Tuning (PEFT) with QLoRA Quantization

This study explores the optimization of the Phi-2 Small Language Models (SLMs) for real-time chatbot applications through Parameter-Efficient Fine-Tuning (PEFT) and Quantized Low-Rank Adaptation (QLoRA). QLoRA specifically refers to the integration of PEFT with LoRA alongside a 4-bit quantization process, aimed at enhancing computational efficiency. These models, initially designed for high performance with minimal computational overhead, are further refined to address the constraints of mobile and edge computing environments. By integrating PEFT with QLoRA, the research aims to reduce memory usage significantly while maintaining, or potentially improving, the accuracy of model responses in real-time interactions. The effectiveness of these techniques was evaluated using the ROUGE metric system, which showed notable improvements in the summarization tasks performed by the models. This approach not only confirms the feasibility of using SLMs in resource-restricted environments but also opens up new avenues for deploying advanced AI-driven applications in real-time settings. The study's findings have significant implications for the development of efficient, scalable, and accessible AI technologies, paving the way for broader adoption in various industries.

PhanTan Khanh Nguyen, Ashfaq Ali Shafin, Khandaker Mamun Ahmed

Beacom College of Computer and Cyber Sciences, Dakota State University · Mathematics and Computer Science, Augustana College

On-Device Language Model InferenceSmall Language ModelsQuantization-Aware LoRAParameter-Efficient Fine-Tuning
AskPDF
Sep 27, 2026

Resource-Aware Parameter-Efficient Model Adaptation for Onboard High-Dimensional Data

Onboard satellite models often require frequent updates, but the weights adapted to earlier data distributions can quickly become outdated. However, updating large-scale model parameters in orbit presents significant challenges due to the limited uplink bandwidth of Low Earth Orbit (LEO) satellite systems, particularly for hyperspectral satellite imagery, where high-dimensional spectral-spatial inputs lead to increased model size and update costs. Existing full fine-tuning methods are thus expensive to retrain and difficult to deploy under strict communication constraints. To address this challenge, we propose NE-LoRA, a parameter-efficient adaptation framework for bandwidth-constrained onboard hyperspectral model updates. NE-LoRA combines a primary low-rank branch with a nonlinear auxiliary branch to capture both global update trends and complex spectral-spatial variations. Additionally, we introduce a differentiated training strategy for multi-matrix adapters, motivated by the asymmetric initialization and gradient dynamics of different adapter matrices. Experiments on four hyperspectral datasets and three representative backbone models demonstrate that NE-LoRA consistently outperforms LoRA-based baselines and remains competitive with, and in several cases superior to, full fine-tuning. Across the evaluated settings, NE-LoRA updates only a small fraction of the total parameters on average while preserving low deployment overhead, offering a favorable accuracy-communication trade-off for onboard hyperspectral adaptation.

Qiyang Zhang, Xinhao Li, Lei Shi +4

Beijing University of Posts and Telecommunications · Wuhan University · Communication University of China +1

Fine-TuningLow-Rank AdaptationHyperspectral ImagingParameter-Efficient Fine-Tuning
AskPDF
Sep 27, 2026

PoE-Fuse: Precision-Weighted Expert Fusion for Bi-Temporal Change Understanding

Bi-temporal change understanding, which localizes and characterizes what changed between two satellite images, is central to disaster response and environmental monitoring, spanning change detection, building localization, and damage assessment. Strong vision-language models address these tasks, but adapting them typically requires full fine-tuning or reinforcement learning, which is costly and unstable. We propose PoE-Fuse, a parameter-efficient framework that instead composes frozen foundation experts for geometry, grounding, and language, resampling their features onto a shared spatial grid and training only a lightweight fusion trunk. PoE-Fuse treats the aligned features as Gaussian observations of a latent scene state and fuses them by learned per-cell precision. This product-of-experts estimator strictly generalizes uniform summation and scalar gating, and extends to change fields by composing the precisions of the two timestamps. A single shared trunk solves the three tasks at once, reaching a mean F1 of 59.2%, compared with 40.7% for an instruction-tuned temporal vision-language assistant, and surpassing dedicated change-detection models retrained under the same protocol and training budget.

Haruki Watase, Shunya Nagashima, Takayuki Nishimura

Neurogica Inc., Tokyo, Japan

Remote Sensing Change DetectionRemote SensingMixture of ExpertsParameter-Efficient Fine-Tuning
AskPDF
Sep 27, 2026

QuPID: Quantum Parameter-Efficient Input-Dependent Retrieval Adaptation for Medical RAG

Fidelity-based quantum retrieval ranks candidates by the fidelity between query and archive states. Applying a shared input-independent unitary after fixed state encoding leaves that fidelity unchanged, so training the circuit cannot alter the ranking. Quantum parameter-efficient input-dependent retrieval adaptation (QuPID) repairs this by making the circuit input-dependent through data re-uploading and by comparing measurement readouts, vectors of local Pauli expectations, rather than states. The result is a small readout for adapting frozen image features to a local archive with limited data: training simulates the circuit classically, and inference runs on a GPU with fixed learned parameters. We characterize the class as a structured factorization of input-modulated quadratic feature maps, bound the frequency support of its re-uploading channel, and give a parameter-count generalization bound that motivates its small budget. Under a shared frozen backbone and a label-free protocol, QuPID's 60 parameters give higher precision-at-5 (P@5) on ChestX-ray14 and MURA than frozen medical encoders, and than adapters and low-rank adaptation (LoRA) with up to 5.25 million trainable parameters. On ChestX-ray14, the P@5 gain over the frozen encoder is +0.116, the lead over retuned adapters is widest at 512 adaptation examples (+0.040), and the full-budget margin over an equally compact classical rotation-plane head is +0.023 with a 95% interval excluding zero. Medical imaging is the primary testbed; the pattern recurs on two non-medical benchmarks, in report generation, and under simulated gate noise and finite-shot readout.

Hyojun Ahn, Emily Jimin Roh, Soohyun Park +3

Korea University · Sookmyung Women’s University · Virginia Tech +2

Quantum Feature MapsMedical Image RetrievalRetrieval-Augmented GenerationQuantum Machine LearningParameter-Efficient Fine-Tuning
AskPDF
Sep 26, 2026

Understanding and Exploiting Anisotropy in Post-Training

LLM post-training combines supervised fine-tuning (SFT), a mode-covering forward-KL objective, with reinforcement learning (RL), a mode-seeking reverse-KL objective. Frequency-weighted likelihood training leaves a well-known signature: anisotropy, in which a few residual channels carry disproportionately large activations. Anisotropy is widely documented and usually treated as a defect, yet its function and its interaction with post-training remain unclear. We first analyze it. A label-free outlier rule isolates about 5% of residual channels that are essential for language modeling: removing them raises perplexity from 10 to over 10610^6, versus 35 for count-matched random channels. Yet they barely distinguish correct from incorrect reasoning. SFT reshapes them, whereas RL leaves them largely intact and adapts the complementary channels. These channels therefore form the model's coherence substrate, and reasoning adaptation happens elsewhere. We then exploit this. SphereGate learns one bounded gain per residual channel on a frozen backbone. Its activation-weighted gradients provably limit movement of high-energy coherence channels and leave the remaining channels free. With 0.1M trainable parameters, SphereGate outperforms parameter-efficient baselines by 2.0--7.3 points on MATH-500 across Qwen2.5 (0.5B--7B) and Llama-3-8B, is comparable or exceeds full-model GRPO. Anisotropy is not a defect but a division of labor that post-training can exploit.

Samyak Jha, Harshvardhan Saini, Yizhen Liao +2

Indian Institute of Technology Dhanbad · National University of Singapore

LLM Post-TrainingRepresentation Geometry in Language ModelsRL for Language Model ReasoningLLM ReasoningParameter-Efficient Fine-Tuning
AskPDF
Sep 26, 2026

Reuse or Relearn? A Spectral View of Earth Observation Foundation Models

Foundation models are rarely used as generic, frozen feature extractors; instead, they are fine-tuned for the target downstream application. This practice is particularly prevalent in Earth observation (EO), and it raises a question that downstream accuracy alone cannot answer: does fine-tuning reuse the pretrained representation, or does it relearn a new one? We study this with spectral diagnostics that compare a model before and after adaptation, quantifying how well its dominant singular subspaces are preserved, how broadly the weight update is distributed, and how large it is. Using natural image models such as CLIP and DINO as a reference, we find that, under the evaluated fine-tuning settings, EO models undergo far larger, higher-rank updates and retain much less of their pretrained structure, so their downstream performance is often obtained with substantial changes to the pretrained weight structure. The diagnostics further provide insight into how cheaply a model can be adapted: where the pretrained subspaces are preserved, adapting a small fraction of the parameters can match full fine-tuning, and where they are not, it can fall behind. More broadly, foundation models, and EO foundation models in particular, should be assessed not only by benchmark accuracy, but also by how reusable their pretrained representation is.

Mehmet Ozgur Turkoglu, Valerio Marsocci, Dominik J. Mühlematter +3

Agroscope, EO of Agroecosystems · ESA, Φ-lab · ETH Zurich

Fine-TuningGeospatial Foundation ModelsRepresentation DriftParameter-Efficient Fine-Tuning
AskPDF
Sep 26, 2026

Stabilizing the Dynamic Low-Rank Training

Training neural networks directly in a low-rank parameterization is an appealing route to reducing memory, compute, and storage simultaneously during both training and inference. Dynamic low-rank training (DLRT), which confines weights to a rank-rr manifold via the Galerkin projection of the gradient flow, is particularly attractive because it identifies efficient subnetworks on the fly without specialized initialization or post-factorization. However, DLRT fails to find trainable networks under high compression. In this paper, we derive the gradient flow of the best rank-rr approximation and point out that the offset of DLRT comes from a curvature-coupling term which is large and thus non-negligible under aggressive compression. Guided by this analysis, we propose a stable dynamic low-rank training method, named SDLRT, which maintains a lightweight compensation buffer that reinjects the top neglected singular directions. Additionally, we introduce a negative feedback on the truncation tolerance to stabilize each layer's rank. Experimentally, SDLRT reliably finds trainable subnetworks where DLRT collapses and as a PEFT adapter on DeBERTa-v3, it achieves the best average score on SuperGLUE at only 2.8%2.8\% parameter overhead over LoRA.

Zhonghan Xu, Ling Wang, Junhao Chen +2

School of Communications and Information Engineering University of Electronic Science and Technology of China

Low-Rank ApproximationNeural Network Training DynamicsLow-Rank AdaptationParameter-Efficient Fine-Tuning
AskPDF
Sep 26, 2026

Spectral Reversal: Counteracting Singular Value Bias for Graph Prompting

Pre-training Graph Neural Networks (GNNs) via self-supervised learning has become a dominant paradigm, yet efficiently adapting frozen encoders remains a challenge. Graph prompting offers a parameter-efficient alternative to fine-tuning, but existing methods largely treat pre-trained models as opaque feature extractors, ignoring their internal spectral structure. In this work, we identify a systematic phenomenon in pre-trained GNNs, which we term spectral bias: optimization during pre-training disproportionately aligns representations with directions associated with large singular values, leaving low-energy directions under-explored. We show that these underutilized directions can encode complementary information that is beneficial for downstream adaptation, especially under distribution shift. To leverage this insight, we propose Spectral Reverse Prompt (SRP), a prompting framework that rebalances the spectral contributions of frozen GNN encoders. SRP applies a learnable soft-thresholding mask in the spectral domain to down-weight dominant directions while amplifying weaker ones. In addition, SRP incorporates a null-space augmentation module that captures variation in directions with minimal activation under the frozen encoder. Extensive experiments across multiple benchmarks demonstrate that SRP achieves state-of-the-art performance with minimal additional parameters, highlighting that reweighting spectral components is a principled and effective strategy for parameter-efficient graph adaptation.

Hanxu Yang, Yuhuan Zhao, Xiaodong He +1

School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China

Graph Neural NetworksSpectral BiasPrompt EngineeringParameter-Efficient Fine-TuningSpectral Methods
AskPDF
Sep 25, 2026

Freeze the Decoder, Heal the Encoder: Parameter-Efficient Adaptation for SVD-Based KV-Cache Compression

Comparing parameter-efficient fine-tuning recipes under a single, shared learning rate is a common but flawed practice: when the arms being compared have very different trainable-parameter counts, a shared rate can simultaneously depress the larger arms' means and inflate their variance, manufacturing a large, seemingly multi-seed-significant advantage for the smallest arm that is not a real effect. We document this confound in a concrete setting: post-hoc SVD-based KV-cache compression, where an already-pretrained model is converted to a low-rank (multi-head-latent-attention-style) cache by factorizing its key/value weights into a down-projection ("encoder") and an up-projection ("decoder"), after which a short fine-tune ("healing") recovers the accuracy lost to truncation. Under a shared learning rate, freezing the decoder and healing only the encoder looks like a clear win over healing the decoder or both factors; once every arm is given its own tuned learning rate, that apparent advantage disappears, and encoder-only healing instead reaches parity with the alternatives, at a real, measured saving of 3x fewer trainable parameters and 3x less optimizer-state memory. We verify this parity with per-arm learning-rate tuning and three seeds per configuration on a vision-language model (Qwen2.5-VL-3B-Instruct), at the one compression ratio this protocol covers, and replicate it on a text-only testbed across two backbones. Encoder-only healing is therefore a lower-memory drop-in recipe for retrofitting low-rank KV-cache compression at training time, and the shared-learning-rate pitfall we document and correct is a cautionary result for comparing any fine-tuning recipes whose arms differ in trainable-parameter count.

Yufeng Wang

KV-Cache CompressionParameter-Efficient Fine-TuningLow-Rank CompressionHyperparameter Optimization
AskPDF
Sep 25, 2026

Awaken, Then Scale: Tiny Adaptation for MRI Reconstruction

Dormant Awakening (DA) specializes a magnetic resonance imaging (MRI) reconstruction model by fitting a small set of zero weights to one labeled slice. Across fourteen U-shaped convolutional network (U-Net) and vision transformer (ViT) sources, fitting 1,004 or 10,560 weights gives mean peak signal-to-noise ratio (PSNR) gains of .430 and .509 dB. We analyze how scaling the fitted output correction changes evaluation PSNR, then use the calibration correction size to cap changes on new images. The cap bounds changes in root mean squared error (RMSE) relative to the source without an evaluation reference. At 10% adaptation budget, we compare fixed halving and dynamic capping for DA, unrestricted sparse adaptation and low-rank adaptation (LoRA). The controls increase both measured calibration-evaluation correlations across all six tested architecture-adapter settings. Experiments concern one constructed fastMRI-to-M4Raw shift with fixed source checkpoints and participant panels.

Mohammed Wattad, Tamir Shor, Alexander M. Bronstein

Faculty of Computer Science, Technion-Israel Institute of Technology, Haifa, Israel

Domain AdaptationParameter-Efficient Fine-TuningAccelerated MRI ReconstructionFew-Shot LearningSparse Fine-Tuning
AskPDF