Low-Rank Adaptation

A recent landscape analysis of LoRA fine-tuning in the neural tangent kernel regime establishes a sufficient condition $r(r+1)/2 > KN$ on the LoRA rank $r$ for the absence of spurious local minima under squared-error loss, prescribing $r \geq 12$ on canonical few-shot RoBERTa setups. The condition is stated for general output dimension $K$, so its sharpness in any particular regime, and its practical implication for the cross-entropy loss actually used in fine-tuning, are open. We give three results that together reduce the prescribed rank to $r = 1$ for binary classification in this regime. First, replacing the symmetric Sard-form count with the non-symmetric LoRA manifold dimension yields a strictly weaker capacity requirement, $r(m+n) - r^2 > C^* \cdot KN$ with $C^* \approx 1.35$ under Gaussian-iid features, satisfied at $r = 1$ on canonical setups. Second, in the cross-entropy setting the Polyak--Łojasiewicz inequality removes the rank threshold entirely. Third, a Rademacher-complexity bound predicts rank-one variance optimality precisely when the bias term is saturated, which is the case for binary classification but not for $K > 2$. Empirically, across four GLUE-style binary tasks, three encoder architectures, and at scale on RoBERTa-large, rank one is competitive with the existing prescription $r = 12$; on multi-class MNLI the optimal rank shifts above one, also as predicted. The binary-regime guarantees are conditional on standard NTK assumptions; the multi-class extension is left to future work.

Continual semantic segmentation requires models to adapt to new domains or modalities without sacrificing performance on previously learned tasks. Expert-based learning, in which task-specific modules specialize in different domains, has proven effective in mitigating forgetting. These methods include dynamic expansion, which suffers from scalability issues, or parameter isolation, which constrains the ability to learn new tasks. We introduce Mixture of Incremental LoRA Experts (MILE), a modular and parameter-efficient framework for continual segmentation across both domains and modalities. MILE leverages Low-Rank Adaptation (LoRA) to instantiate lightweight experts for each new task while keeping the pretrained base network frozen. Each expert is trained exclusively on its task data, thus avoids overwriting previously learned information. A prototype-guided gating mechanism dynamically selects the most appropriate expert at inference. MILE achieves the benefits of expert-based learning while overcoming its scalability limitations. It requires only a marginal parameter increase per task and tens of LoRA adapters are needed before matching the size of a single full model, making it highly efficient in both training and storage. Across domain- and modality-incremental benchmarks, MILE achieves strong performance while ensuring better stability, plasticity, and scalability.

LoRA fine-tuning of diffusion transformers (DiT) on multi-style data suffers from \emph{style bleed}: a single low-rank residual cannot represent several distinct artist fingerprints, and the optimizer converges to their average. Mixture-of-experts LoRA in the HydraLoRA style replaces the up-projection with $E$ heads under a router, but when every expert is zero-initialized the router receives identical gradient from each head and remains at the uniform prior. The experts then evolve permutation-symmetrically, and the network trains as a single rank-$r$ LoRA at $E{\times}$ the cost. We present \textbf{Ortho-Hydra}, a re-parameterisation that combines an OFT-style Cayley-orthogonal shared basis with per-expert \emph{disjoint output subspaces} carved from the top-$(Er)$ left singular vectors of the pretrained weight. Disjointness makes the router's per-expert score non-degenerate at step~$0$, so specialization receives gradient signal before any expert has trained. We test the predicted deadlock on a DiT pipeline by comparing two HydraLoRA baselines, a zero-initialized shared-basis variant and the original $σ{=}0.1$ Gaussian-jitter mitigation, against Ortho-Hydra under a matched optimiser, dataset, and step budget. Neither baseline leaves the uniform prior within the first $1\text{k}$ steps; Ortho-Hydra begins de-uniformising within the first few hundred. End-task generation quality on multi-style data is out of scope; we report the construction, the cold-start mechanism, and the routing dynamics it changes. Code: https://github.com/sorryhyun/anima_lora.

Adapting a pretrained language model to a new task often hurts the general capabilities it already had, a problem known as catastrophic forgetting. Sparse Memory Finetuning (SMF) tries to avoid this by adding key-value memory layers to the model and, on each training step, updating only the small set of memory rows that the current batch reads most heavily. We re-implement SMF on Qwen-2.5-0.5B-Instruct and compare it with LoRA and full finetuning on MedMCQA, a 4-choice medical exam task, using WikiText perplexity and TriviaQA accuracy as forgetting probes. SMF improves MedMCQA by 2.5 percentage points while keeping both forgetting probes within roughly 1 point of the base model, whereas LoRA and full finetuning achieve larger gains but with clear drift on both. We also compare two row-selection rules (KL-divergence and TF-IDF), which balance the two forgetting metrics differently.

Video diffusion models leveraging step distillation or causal distillation have achieved remarkable performance. However, adapting existing LoRAs to these variants remains a critical challenge due to weight space mismatches. We observe that direct application leads to style degradation and structural collapse, yet the underlying mechanisms remain poorly understood. To fill this gap, we delve into the weight space and identify that the incompatibility stems from spectral interference within shared functional clusters defined over singular subspaces. Specifically, our analysis reveals that while both paradigms respect spectral rigidity, they establish conflicting routing pathways that clash through constructive overload or destructive cancellation. To address this issue, we propose Cluster-Aware Spectral Arbitration (CASA), a data-free framework that dynamically arbitrates between safeguarding the target's manifold and restoring LoRA alignment based on spectral density. Extensive experiments demonstrate that CASA effectively mitigates artifacts and revives LoRA functionality. Our code is available at https://github.com/Noahwangyuchen/CASA

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.

LoRA adapts large language models (LLMs) by restricting updates to low-rank subspaces of pre-trained weights. While this substantially reduces training cost, the effectiveness of adaptation critically depends on which subspace is chosen at initialization: a poor initialization that allocates capacity to task-irrelevant directions can severely hinder downstream performance. Existing initialization strategies primarily rely on the intrinsic properties of pre-trained weights, implicitly assuming that weight geometry alone reflects task relevance. However, such criteria overlook how the model interacts with the downstream data distribution. In this work, we formulate LoRA initialization as identifying the degree of impact of directions in parameter space under the target data distribution. We argue that data-aware sensitivity, rather than weight-only magnitude, should govern the choice of adaptation subspaces. Building on this perspective, we propose a Fisher-guided framework that leverages curvature information induced by downstream data to characterize how parameter perturbations influence model predictions. This perspective yields a principled, task-dependent criterion for selecting LoRA directions that better align adaptation with the target objective. Empirical results across diverse tasks and modalities demonstrate that data-aware initialization consistently and significantly improves downstream performance over existing approaches.

Exponential growth in the scale of modern foundation models has led to the widespread adoption of Low-Rank Adaptation (LoRA) as a parameter-efficient fine-tuning technique. However, standard LoRA implementations disregard the varying intrinsic dimensionality of model layers and enforce a uniform rank, leading to parameter redundancy. We propose Post-Optimization Adaptive Rank Allocation (PARA), a data-free compression method for LoRA that integrates seamlessly into existing fine-tuning pipelines. PARA leverages Singular Value Decomposition to prune LoRA ranks using a global threshold over singular values across all layers. This results in non-uniform rank allocation based on layer-wise spectral importance. As a post-hoc method, PARA circumvents the training modifications and resulting instabilities that dynamic architectures typically incur. We empirically demonstrate that PARA reduces parameter count by 75-90% while preserving the predictive performance of the original, uncompressed LoRA across multiple vision and language benchmarks. Code will be published upon acceptance.

Low-Rank Adaptation (LoRA), which leverages the insight that model updates typically reside in a low-dimensional space, has significantly improved the training efficiency of Large Language Models (LLMs) by updating neural network layers using low-rank matrices. Since the generation of adversarial examples is an optimization process analogous to model training, this naturally raises the question: Do adversarial perturbations exhibit a similar low-rank structure? In this paper, we provide both theoretical analysis and extensive empirical investigation across various attack methods, model architectures, and datasets to show that adversarial perturbations indeed possess an inherently low-rank structure. This insight opens up new opportunities for improving both adversarial attacks and defenses. We mainly focus on leveraging this low-rank property to improve the efficiency and effectiveness of black-box adversarial attacks, which often suffer from excessive query requirements. Our method follows a two-step approach. First, we use a reference model and auxiliary data to guide the projection of gradients into a low-dimensional subspace. Next, we confine the perturbation search in black-box attacks to this low-rank subspace, significantly improving the efficiency and effectiveness of the adversarial attacks. We evaluated our approach across a range of attack methods, benchmark models, datasets, and threat models. The results demonstrate substantial and consistent improvements in the performance of our low-rank adversarial attacks compared to conventional methods.

Parametric Retrieval-Augmented Generation (PRAG) encodes external documents into lightweight parameter modules that can be retrieved and merged at inference time, offering a promising alternative to in-context retrieval augmentation. Despite its potential, many PRAG implementations train document adapters with task-supervised objectives, which may cause each adapter to encode both document-specific facts and reusable task-solving behavior. This entanglement may make adapter composition less reliable: when multiple adapters are merged at inference time, their overlapping task behaviors can accumulate together with document-specific updates, potentially making the merged adapter less stable and less focused on the intended document knowledge. To examine this issue, we explore Orthogonal Subspace Decomposition (OSD), an adapter-training setup that separates reusable task behavior from document-specific knowledge adapters. Concretely, we first train a Task LoRA to capture reusable task behavior, and then train document LoRAs to encode document-specific knowledge in a orthogonal subspace. This setup provides a controlled way to examine how orthogonalizing task and document LoRA updates affects adapter composition in multi-document PRAG. Experiments across multiple knowledge-intensive tasks and model scales suggest that this orthogonalization strategy can improve compositional robustness in parametric RAG, especially when multiple document adapters are merged.

Despite recent advances, single-image super-resolution (SR) remains challenging, especially in real-world scenarios with complex degradations. Diffusion-based SR methods, particularly those built on Stable Diffusion, leverage strong generative priors but commonly rely on text conditioning derived from semantic captioning. Such textual descriptions provide only high-level semantics and lack the spatially aligned visual information required for faithful restoration, leading to a representation gap between abstract semantics and spatially aligned visual details. To address this limitation, we propose GramSR, a one-step diffusion-based SR framework that replaces text conditioning with dense visual features extracted from the low-resolution input using a pre-trained DINOv3 encoder. GramSR adopts a three-stage LoRA architecture, where pixel-level, semantic-level, and texture-level LoRA modules are trained sequentially. The pixel-level module focuses on degradation removal using $\ell_2$ loss, the semantic-level module enhances perceptual details via LPIPS and CSD losses, and the texture-level module enforces feature correlation consistency through a Gram matrix loss computed from DINOv3 features. At inference, independent guidance scales enable flexible control over degradation removal, semantic enhancement, and texture preservation. Extensive experiments on standard SR benchmarks demonstrate that GramSR consistently outperforms existing one-step diffusion-based methods, achieving superior structural fidelity and texture realism. The code for this work is available at: https://github.com/aimagelab/GramSR.

Low-Rank Adaptation (LoRA) has become the standard for fine-tuning large pre-trained models at reduced computational cost. However, its low-rank point-estimate updates limit expressiveness, leave a persistent gap relative to full fine-tuning accuracy, and provide no built-in uncertainty quantification, limiting its applicability in settings where reliability matters as much as accuracy. We introduce BaLoRA, a Bayesian extension of LoRA with a novel input-adaptive Bayesian parameterization of LoRA matrices that adds minimal parameters and compute. Surprisingly, not only does the Bayesian extension yield well-calibrated uncertainty estimates, but the adaptive noise injection underlying our approach also significantly improves prediction accuracy, narrowing the gap with full fine-tuning across both natural language reasoning and vision tasks. When applied to band gap prediction in metal-organic frameworks, BaLoRA produces zero-shot test-time uncertainty estimates that correlate more strongly with model error than a trained ensemble of LoRA models, and improve monotonically with compute without sacrificing accuracy.

Federated learning (FL) offers a promising distributed learning paradigm for internet of vehicles (IoV) applications. However, it faces challenges from communication overhead and dynamic environments. Model compression techniques reduce computing and communication burden yet create trade-offs between compression ratios and vehicle participation strategies. In this paper, we propose a lightweight FL algorithm named federated learning with dynamic low-rank adaptation (Fed-DLoRA), which is combined with low-rank adaptation (LoRA) to effectively reduce parameters and communication costs while enhancing training efficiency. The convergence analysis of Fed-DLoRA is conducted through stochastic gradient descent optimization coupled with singular value decomposition. This analysis establishes the theoretical relationships among LoRA rank, vehicular scheduling strategies and the model's convergence characteristics. Building on these insights, we formulate a joint optimization problem aimed at maximizing system performance. To address this problem, we propose an adaptive rank, bandwidth and vehicle selection (ARBVS) algorithm that integrates enumeration with greedy optimization strategies. The algorithm provides efficient rank selection and resource scheduling strategies for each FL communication round, thereby achieving effective performance improvements for the FL system. Experimental results demonstrate that Fed-DLoRA achieves superior performance compared to conventional federated learning approaches, exhibiting enhanced accuracy, faster convergence, and improved communication efficiency.

We present CRC-SAM, a unified framework for colorectal cancer segmentation across colonoscopy, CT, and histopathology images. Unlike prior single-modality methods, CRC-SAM provides consistent, modality-agnostic segmentation throughout the clinical workflow. Built on MedSAM, it incorporates low-rank adaptation (LoRA) layers into a frozen encoder, enabling efficient domain transfer to underrepresented modalities with minimal trainable parameters. Experiments on MSD-Colon, CVC-ClinicDB, and EBHI-Seg demonstrate superior performance across modalities, outperforming state-of-the-art baselines and highlighting the effectiveness of lightweight LoRA adaptation for foundation-model-based colorectal cancer analysis.

Hybrid language models that interleave attention with recurrent components are increasingly competitive with pure Transformers, yet standard LoRA practice applies adapters uniformly without considering the distinct functional roles of each component type. We systematically study component-type LoRA placement across two hybrid architectures -- Qwen3.5-0.8B (sequential, GatedDeltaNet + softmax attention) and Falcon-H1-0.5B (parallel, Mamba-2 SSM + attention) -- fine-tuned on three domains and evaluated on five benchmarks. We find that the attention pathway -- despite being the minority component -- consistently outperforms full-model adaptation with 5-10x fewer trainable parameters. Crucially, adapting the recurrent backbone is destructive in sequential hybrids (-14.8 pp on GSM8K) but constructive in parallel ones (+8.6 pp). We further document a transfer asymmetry: parallel hybrids exhibit positive cross-task transfer while sequential hybrids suffer catastrophic forgetting. These results establish that hybrid topology fundamentally determines adaptation response, and that component-aware LoRA placement is a necessary design dimension for hybrid architectures.

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.

As model sizes continue to grow, parameter-efficient fine-tuning has emerged as a powerful alternative to full fine-tuning. While LoRA is widely adopted among these methods, recent research has explored vector-based adaptation methods due to their extreme parameter efficiency. However, these methods typically require substantially higher ranks than LoRA to match its performance, leading to increased training costs. This work introduces GiVA, a gradient-based initialization strategy for vector-based adaptation. It achieves training times comparable to LoRA and maintains the extreme parameter efficiency of vector-based adaptation. We evaluate GiVA across diverse benchmarks, including natural language understanding, natural language generation, and image classification. Experiments show that our approach consistently outperforms or achieves performance competitive with existing vector-based adaptation methods and LoRA while reducing rank requirements by a factor of eight ($8\times$).

This technical note provides a first-order formalisation of the logit shift and fact-margin change induced by Low-Rank Adaptation (LoRA). Using a first-order Fréchet approximation around the base model trajectory, we show that the multi-layer LoRA effect can be decomposed into a linear summation of layerwise contributions and a higher-order remainder term representing inter-layer coupling.

Can small language models achieve strong tool-use performance without complex adaptation mechanisms? This paper investigates this question through Meta-Tool, a controlled empirical study comparing hypernetwork-based LoRA adaptation against carefully designed few-shot prompting. Using a Llama-3.2-3B-Instruct backbone, we evaluate four adaptation mechanisms--few-shot prompting, documentation encoding, hypernetwork-generated LoRA weights, and value-guided beam search--across four diverse benchmarks: Gorilla APIBench, Spider 2.0, WebArena, and InterCode. Our central finding is a well-supported negative result: despite generating non-trivial weight matrices, the 227.8M-parameter hypernetwork provides no measurable improvement over few-shot prompting alone. Comprehensive ablation studies reveal that few-shot examples contribute +21.5% to performance and documentation contributes +5.0%, while the hypernetwork adds 0%. A 3B model with well-designed prompts achieves 79.7% of GPT-5's average performance at $10 \times$ lower latency. Error analysis across 722 failure cases spanning all shot counts (0--5) shows that at the 5-shot configuration (106 failures), failure modes are task-dependent: schema-heavy tasks (Spider 2.0, WebArena) show near-zero format errors with remaining failures semantic, while format errors dominate on Gorilla (100%) and InterCode (70%). These findings redirect practitioners toward prompt engineering and example curation rather than complex adaptation architectures.

Fine-tuning Large Language Models (LLMs) remains structurally uncertain despite parameter-efficient methods such as Low-Rank Adaptation (LoRA), as the layer-specific roles of internal representations are poorly understood, leading to heuristic decisions about where adaptation should be applied. We model the evolution of hidden states as a high-dimensional geometric trajectory and propose using the Ramer-Douglas-Peucker (RDP) algorithm, a parameter-free and training-free polygon simplification method that preserves global structural transitions while eliminating locally redundant changes, to identify critical breakpoints along the representation path. Crucially, we use these geometric pivots not merely for analysis, but as a direct decision signal for determining which layers should be adapted during parameter-efficient fine-tuning. By integrating this geometry-aware layer selection strategy into LoRA fine-tuning of Qwen3-8B-Base, we achieve superior performance on MMLU-Math using only 13 RDP-selected layers (81.67%), significantly outperforming both full 36-layer adaptation (79.32%) and random 13-layer selection (75.56%), as well as the baseline Qwen3-8B-Base model (74.25%). These results demonstrate that leveraging the intrinsic geometry of representation trajectories provides a robust, interpretable, and training-free signal for optimizing layer selection during model adaptation.

The combination of Mixture-of-Experts (MoE) and Low-Rank Adaptation (LoRA) has shown significant potential for enhancing the multi-task learning capabilities of Large Language Models. However, existing methods face two primary challenges: (1)Imprecise Routing in the current MoE-LoRA method fails to explicitly match input semantics with expert capabilities, leading to weak expert specialization. (2)Uniform weight fusion strategies struggle to provide adaptive update strengths, overlooking the varying complexity of different tasks. To address these limitations, we propose SAMoRA (Semantic-Aware Mixture of LoRA Experts), a novel parameter-efficient fine-tuning framework tailored for task-adaptive learning. Specifically, A Semantic-Aware Router is proposed to explicitly align textual semantics with the most suitable experts for precise routing. A Task-Adaptive Scaling mechanism is designed to regulate expert contributions based on specific task requirements dynamically. In addition, a novel regularization objective is proposed to jointly promote expert specialization and effective scaling. Extensive experiments on multiple multi-task benchmarks demonstrate that SAMoRA significantly outperforms the state-of-the-art methods and holds excellent task generalization capabilities. Code is available at https://github.com/boyan-code/SAMoRA

Low-Rank Adaptation (LoRA) has become a widely adopted parameter-efficient fine-tuning method for large language models, with its effectiveness largely influenced by the allocation of ranks and scaling factors, as well as initialization. Existing LoRA variants typically address only one of these factors, often at the cost of increased training complexity or reduced practical efficiency. In this work, we present Task-aware Low-Rank Adaptation (TLoRA), a unified framework that jointly optimizes initialization and resource allocation at the outset of training. TLoRA introduces a data-driven initialization strategy that aligns the LoRA $A$ matrix with task-relevant subspaces by performing singular value decomposition on the product of pre-trained weights and input activation covariance. After this, the $A$ matrix is frozen, and only the $B$ matrix is trained. Furthermore, TLoRA employs a sensitivity-based importance metric to adaptively allocate ranks and scaling factors across layers under a fixed parameter budget. We conduct extensive experiments that demonstrate TLoRA consistently performs excellently across various tasks, including natural language understanding, commonsense reasoning, math reasoning, code generation, and chat generation, while significantly reducing the number of trainable parameters.

Large Language Models (LLMs) have shown strong potential for recommendation (LLMRec) due to their powerful reasoning and generalization abilities. However, effectively aligning the textual semantics modeled by LLMs with the collaborative signals remains a key challenge. Existing methods either translate collaborative information into textual prompts or inject pre-trained embeddings into the LLM, both of which treat structural information as static input and fail to capture high-order relational dependencies. To bridge this gap, we propose GraphLoRA, a novel framework that generalizes low-rank adaptation from independent to structure-aware propagation. GraphLoRA embeds a trainable graph message-passing network within the low-rank adaptation pathway, enabling structural signals to propagate through the parameter space. This design allows collaborative topology to explicitly guide parameter updates, fostering deep integration between graph-structured and textual semantic information. Extensive experiments on multiple benchmarks demonstrate that GraphLoRA not only outperforms state-of-the-art LLM-based recommendation methods but also achieves superior generalization, effectively balancing structural reasoning capability with computational efficiency. Code is available at \href{https://github.com/wgj15965/GraphLoRA}{https://github.com/wgj15965/GraphLoRA}.

Deploying large language models (LLMs) on smartphones poses significant engineering challenges due to stringent constraints on memory, latency, and runtime flexibility. In this work, we present a hardware-aware framework for efficient on-device inference of a LLaMA-based multilingual foundation model supporting multiple use cases on Samsung Galaxy S24 and S25 devices with SM8650 and SM8750 Qualcomm chipsets respectively. Our approach integrates application-specific LoRAs as runtime inputs to a single frozen inference graph, enabling dynamic task switching without recompilation or memory overhead. We further introduce a multi-stream decoding mechanism that concurrently generates stylistic variations - such as formal, polite, or jovial responses - within a single forward pass, reducing latency by up to 6x. To accelerate token generation, we apply Dynamic Self-Speculative Decoding (DS2D), a tree-based strategy that predicts future tokens without requiring a draft model, yielding up to 2.3x speedup in decode time. Combined with quantization to INT4 and architecture-level optimizations, our system achieves 4-6x overall improvements in memory and latency while maintaining accuracy across 9 languages and 8 tasks. These results demonstrate practical feasibility of deploying multi-use-case LLMs on edge devices, advancing the commercial viability of Generative AI in mobile platforms.

Merging multiple Low-Rank Adaptation (LoRA) experts into a single backbone is a promising approach for efficient multi-task deployment. While existing methods strive to alleviate interference via weight interpolation or subspace alignment, they rest upon the implicit assumption that all LoRA matrices contribute constructively to the merged model. In this paper, we uncover a critical bottleneck in current merging paradigms: the existence of $\textit{negative modules}$ -- specific LoRA layers that inherently degrade global performance upon merging. We propose $\textbf{E}$volutionary $\textbf{N}$egative $\textbf{M}$odule $\textbf{P}$runing ($\textbf{ENMP}$), a plug-and-play LoRA pruning method to locate and exclude these detrimental modules prior to merging. By leveraging an evolutionary search strategy, ENMP effectively navigates the discrete, non-differentiable landscape of module selection to identify optimal pruning configurations. Extensive evaluations demonstrate that ENMP consistently boosts the performance of existing merging algorithms, achieving a new state-of-the-art across both language and vision domains. Code is available at https://github.com/CaoAnda/ENMP-LoRAMerging.

Face morphing attacks pose a substantial risk to the reliability of face recognition systems used in passport issuance, border control, and digital identity verification. Detecting morphing attacks from a single facial image remains challenging owing to the lack of a trusted reference and the diversity of attack generation methods. This paper presents a new Single-Image Face Morphing Attack Detection (S-MAD) framework that integrates high-frequency Laplacian residual statistics with representations from a frozen, foundation-scale vision transformer. The approach employs residual-statistic-gated low-rank adapters (R-FLoRA) and feature-wise residual fusion (Res-FiLM) to enhance sensitivity to local morphing artefacts while preserving the semantic context of the backbone. A novel residual-contrastive alignment loss further regularises the fused token space, improving discrimination under unseen morphing conditions. Comprehensive experiments on four ICAO-compliant datasets, encompassing seven morph generation techniques, demonstrate that the proposed method consistently surpasses nine recent state-of-the-art S-MAD algorithms in detection accuracy and cross-domain (or dataset) generalisation. With a frozen backbone and minimal trainable parameters, the model achieves real-time efficiency and interpretability, making it suitable for real-life scenarios in biometric verification systems.

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.

Large pre-trained language models are increasingly adapted to downstream tasks using parameter-efficient fine-tuning (PEFT), but existing PEFT methods are typically deterministic and unimodal, making them poorly suited for low-resource multimodal settings where predictive uncertainty and cross-modal reliability both matter. We introduce CALIBER (Context-Aware Low-rank Inference with Bayesian Embedding Regularization), a multimodal uncertainty-aware PEFT framework for audio-text learning. CALIBER extends Bayesian low-rank adaptation by conditioning the variational posterior in the adapter space on per-layer, token-level text-audio cross-attention. Specifically, text-derived low-rank features attend to frame-level audio embeddings to produce localized acoustic context, which then modulates the mean and variance of a compact stochastic latent matrix within the rank-$r$ adapter space. This design treats audio not only as an additional feature source, but as a contextual reliability signal that shapes both adaptation and confidence. By confining stochasticity to a low-dimensional latent component, CALIBER retains the computational efficiency and scalability of PEFT while enabling heteroscedastic multimodal uncertainty estimation. Experimental results across diverse text and audio backbones show that CALIBER consistently matches or improves upon text-only Bayesian PEFT and conventional multimodal transfer-learning baselines, with token-level cross-attention yielding the most consistent gains. Our findings demonstrate that localized cross-modal conditioning is an effective and lightweight mechanism for uncertainty-aware multimodal adaptation.

Adapter-based methods have become a cost-effective approach to continual learning (CL) for Large Language Models (LLMs), by sequentially learning a low-rank update matrix for each task. To mitigate catastrophic forgetting, state-of-the-art approaches impose constraints on new adapters with respect to the previous ones, by targeting either subspace or coordinate-wise interference. In this paper, we propose JumpLoRA, a novel framework to adaptively induce sparsity in the Low-Rank Adaptation (LoRA) blocks through the use of JumpReLU gating. The method achieves dynamic parameter isolation, which helps prevent task interference. We demonstrate that our method is highly modular and compatible with LoRA-based CL approaches. Specifically, it significantly boosts the performance of IncLoRA and outperforms the leading state-of-the-art CL method, ELLA.

Edge deployment of large language models (LLMs) increasingly relies on libraries of lightweight LoRA adapters, yet GPU/DRAM can keep only a small resident subset at a time. Serving a request through a non-resident adapter requires paging its weights from storage, incurring measurable latency. This creates a two-timescale online control problem: on a slow timescale, the system selects which adapters remain resident in fast memory, while on a fast timescale it routes each request to an adapter whose context-dependent utility is unknown a priori. The two decisions are tightly coupled: the cache determines the cost of exploration, and the router determines which adapters receive informative feedback. We formulate this joint caching-and-routing problem as a two-timescale contextual bandit and propose POLAR (Paging and Online Learning for Adapter Routing). POLAR pairs a cache-aware LinUCB router with an epoch-based cache controller. We study two variants. A fixed-epoch version provides a robust baseline with worst-case regret guarantees under arbitrary contexts. An epoch-doubling version, POLAR+, adds forced exploration and improved cache optimization to achieve $\widetilde{\mathcal{O}}(d\sqrt{NT}+\sqrt{KT})$ sublinear regret under stochastic regularity and cacheability conditions, where $N$ is the adapter count, $K$ the cache size, $d$ the context dimension, and $T$ the horizon. The routing term matches the standard contextual-bandit rate up to logarithmic factors, showing that the memory hierarchy does not fundamentally slow routing learning. Experiments using 15 real LoRA adapters for Qwen2.5-7B together with measured GPU paging latencies show that adaptive cache control substantially outperforms non-adaptive baselines and exhibits scaling trends consistent with the theory.

With the rapid advancement of deep generative models, realistic fake images have become increasingly accessible, yet existing localization methods rely on complex designs and still struggle to generalize across manipulation types and imaging conditions. We present a simple but strong baseline based on DINOv3 with LoRA adaptation and a lightweight convolutional decoder. Under the CAT-Net protocol, our best model improves average pixel-level F1 by 17.0 points over the previous state of the art on four standard benchmarks using only 9.1,M trainable parameters on top of a frozen ViT-L backbone, and even our smallest variant surpasses all prior specialized methods. LoRA consistently outperforms full fine-tuning across all backbone scales. Under the data-scarce MVSS-Net protocol, LoRA reaches an average F1 of 0.774 versus 0.530 for the strongest prior method, while full fine-tuning becomes highly unstable, suggesting that pre-trained representations encode forensic information that is better preserved than overwritten. The baseline also exhibits strong robustness to Gaussian noise, JPEG re-compression, and Gaussian blur. We hope this work can serve as a reliable baseline for the research community and a practical starting point for future image-forensic applications. Code is available at https://github.com/Irennnne/DINOv3-IML.

While large language models (LLMs) show strong performance in natural language understanding and generation, their evaluation and adaptation to domain-specific constraints in telecommunications customer support remain limited. In addition, data sovereignty, regulatory constraints, and the handling of sensitive customer and network information complicate the use of externally hosted foundation models in this domain. We present a systematic study of parameter-efficient fine-tuning (PEFT) using Low-Rank Adaptation (LoRA) applied to Qwen2.5-3B to build a domain-specific conversational assistant. We introduce a combinatorial synthetic data generation approach based on a glossary of 52 industry-specific terms, producing approximately 30,000 training examples across 1,560 distinct problem scenarios via a generative pipeline powered by Gemini 2.0 Flash. We evaluate 16 LoRA configurations by varying hyperparameters and target modules. Our evaluation extends beyond standard metrics by incorporating energy consumption analysis and qualitative assessment using an LLM-as-a-judge framework with GPT-5.2 and Claude 4.5 Sonnet. Results show a clear divergence between quantitative and qualitative performance: models achieving the lowest validation loss do not necessarily obtain the best human-aligned rankings. The best validation loss (0.5024) ranks only 6th-7th in qualitative evaluation, while the worst loss (0.6807) ranks first according to both judges. This work contributes (1) a combinatorial method for synthetic dataset construction, (2) insights into the impact of target module selection for LoRA injection, (3) evidence that validation loss alone is insufficient for selecting fine-tuning configurations in conversational AI, and (4) an energy-performance trade-off analysis for sustainable LLM deployment.

Foundation models have revolutionized AI, but adapting them efficiently for multimodal tasks, particularly in dual-stream architectures composed of unimodal encoders, such as DINO and BERT, remains a significant challenge. ParameterEfficient Fine-Tuning (PEFT) methods like LowRank Adaptation (LoRA) enable lightweight adaptation, yet they operate in isolation within each modality, limiting their ability in capturing cross-modal interactions. In this paper, we take a step in bridging this gap with Cross-Modal LowRank Adaptation (CoLA), a novel PEFT framework that extends LoRA by introducing a dedicated inter-modal adaptation pathway alongside the standard intra-modal one. This dual-path design enables CoLA to adapt unimodal foundation models to multimodal tasks effectively, without interference between modality-specific and crossmodal learning. We evaluate CoLA across a range of vision-language (RefCOCO, RefCOCO+, RefCOCOg) and audio-visual (AVE, AVS) benchmarks, where it consistently outperforms LORA, achieving a relative gain of around 3% and 2%, respectively, while maintaining parameter efficiency. Notably, CoLA enables the first multitask PEFT framework for visual grounding, bridging a key gap in efficient multimodal adaptation. Code is available at https://github.com/peterwisu/CoLA

Routing has emerged as a promising strategy for balancing performance and cost in large language model (LLM) systems that combine lightweight models with powerful but expensive large models. Recent studies show that \emph{probe routing}, which predicts the correctness of a small model using its hidden states, provides an effective solution in text-only LLMs. However, we observe that these probes degrade substantially when applied to multimodal LLMs (MLLMs). Through empirical analysis, we find that the presence of visual inputs weakens the separability of correctness signals in hidden states, making them harder to extract using standard probe designs. To address this challenge, we introduce two complementary approaches for improving probe routing in MLLMs. First, we propose the \emph{Attention Probe}, which aggregates hidden states from the preceding layer based on attention scores to recover distributed correctness signals. Second, we present the \emph{KL-Regularized LoRA Probe (ReLope)}, which inserts a lightweight LoRA adapter and applies a KL regularizer to learn routing-aware representations. Comprehensive experiments show that our methods consistently outperform baselines, suggesting that improving the quality of hidden states is key to effective routing in MLLMs. Our code is available at https://github.com/Spinozaaa/ReLope.

Continuous knowledge updating for pre-trained large language models (LLMs) is increasingly necessary yet remains challenging. Although inference-time methods like In-Context Learning (ICL) and Retrieval-Augmented Generation (RAG) are popular, they face constraints in context budgets, costs, and retrieval fragmentation. Departing from these context-dependent paradigms, this work investigates a parametric approach using Low-Rank Adaptation (LoRA) as a modular knowledge memory. Although few recent works examine this concept, the fundamental mechanics governing its capacity and composability remain largely unexplored. We bridge this gap through the first systematic empirical study mapping the design space of LoRA-based memory, ranging from characterizing storage capacity and optimizing internalization to scaling multi-module systems and evaluating long-context reasoning. Rather than proposing a single architecture, we provide practical guidance on the operational boundaries of LoRA memory. Overall, our findings position LoRA as the complementary axis of memory alongside RAG and ICL, offering distinct advantages.

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.

Visual analogy learning enables image editing via demonstration rather than textual description, allowing users to specify complex transformations difficult to articulate in words. Given a triplet $\{\mathbf{a}$, $\mathbf{a}'$, $\mathbf{b}\}$, the goal is to generate $\mathbf{b}'$ such that $\mathbf{a} : \mathbf{a}' :: \mathbf{b} : \mathbf{b}'$. Recent methods adapt text-to-image models with a single Low-Rank Adaptation (LoRA) module, but they face a fundamental limitation: attempting to capture the diverse space of visual transformations within a fixed module constrains generalization. Inspired by recent work showing that LoRAs in constrained domains span meaningful, interpolatable semantic spaces, we propose LoRWeB, which specializes the model for each analogy task in a single inference pass. LoRWeB dynamically composes learned transformation primitives, informally, choosing a point in a "space of LoRAs". We introduce two key components: (1) a learnable basis of LoRAs to span the space of different visual transformations, and (2) a lightweight encoder that dynamically weighs these basis LoRAs given the input analogy pair. Comprehensive evaluations demonstrate state-of-the-art performance and significantly improved generalization to unseen transformations. Our findings suggest LoRA basis decompositions are a promising direction for flexible visual manipulation tasks. See https://research.nvidia.com/labs/par/lorweb for code.

The widespread availability of fine-tuned LoRA modules for open pre-trained models has led to an interest in methods that can adaptively merge LoRAs to improve performance. These methods typically include some way of selecting LoRAs from a pool and tune merging coefficients based on a task-specific dataset. While adaptive merging methods have demonstrated improvements in some settings, no past work has attempted to recycle LoRAs found "in the wild" on model repositories like the Hugging Face Hub. To address this gap, we consider recycling from a pool of nearly 1,000 user-contributed LoRAs trained from the Llama 3.1 8B-Instruct language model. Our empirical study includes a range of adaptive and non-adaptive merging methods in addition to a new method designed via a wide search over the methodological design space. We demonstrate that adaptive merging methods can improve performance over the base model but provide limited benefit over training a new LoRA on the same data used to set merging coefficients. We additionally find not only that the specific choice of LoRAs to merge has little importance, but that using LoRAs with randomly initialized parameter values yields similar performance. This raises the possibility that adaptive merging from recycled LoRAs primarily works via some kind of regularization effect, rather than by enabling positive cross-task transfer. To better understand why past work has proven successful, we confirm that positive transfer is indeed possible when there are highly relevant LoRAs in the pool. We release the model checkpoints and code online.

We propose SHINE (Scalable Hyper In-context NEtwork), a scalable hypernetwork that can map diverse meaningful contexts into high-quality LoRA adapters for large language models (LLMs). By reusing the frozen LLM's own parameters in an in-context hypernetwork design and introducing architectural innovations, SHINE overcomes key limitations of prior hypernetworks and achieves strong expressive power with a relatively small number of parameters. We introduce a pretraining and instruction fine-tuning pipeline, and train our hypernetwork to generate high quality LoRA adapters from diverse meaningful contexts in a single forward pass. It updates LLM parameters without any fine-tuning, and immediately enables complex question answering tasks related to the context without directly accessing the context, effectively transforming in-context knowledge to in-parameter knowledge in one pass. Our work achieves outstanding results on various tasks, greatly saves time, computation and memory costs compared to SFT-based LLM adaptation, and shows great potential for scaling. Our code is available at https://github.com/MuLabPKU/SHINE

Low-Rank Adaptation (LoRA) methods have emerged as crucial techniques for adapting large pre-trained models to downstream tasks under computational and memory constraints. However, they face a fundamental challenge in balancing task-specific performance gains against catastrophic forgetting of pre-trained knowledge, where existing methods provide inconsistent recommendations. This paper presents a comprehensive analysis of the performance-forgetting trade-offs inherent in low-rank adaptation using principal components of weight matrices as initialization. Our investigation reveals that fine-tuning intermediate components leads to better balance and robustness to high learning rates than first (PiSSA) and last (MiLoRA) components in existing work. Building on these findings, we provide practical guidelines for initialization of LoRA methods to balance the performance-forgetting trade-off. In a thorough empirical study on a variety of computer vision and NLP tasks we confirm that these guidelines achieve high accuracy and reduced forgetting.

Parameter-efficient continual learning aims to adapt pre-trained models to sequential tasks without forgetting previously acquired knowledge. Most existing approaches treat continual learning as avoiding interference with past updates, rather than considering what properties make the current task-specific update naturally preserve previously acquired knowledge. From a knowledge-decomposition perspective, we observe that low-rank adaptations exhibit highly imbalanced singular value spectra: a few dominant components absorb most of the adaptation energy, thereby (i) more likely to disrupt previously acquired knowledge and (ii) making the update more vulnerable to interference from subsequent tasks. To enable explicit balance among components, we decouple the magnitude of the task update from its directional structure and formulate it as a constrained optimization problem on a restricted Stiefel manifold. We address this problem using a projected first-order method compatible with standard deep-learning optimizers used in vision-language models. Our method mitigates both backward and forward forgetting, consistently outperforming continual learning baselines. The implementation code is available at https://github.com/haodotgu/EBLoRA.

Mixture-of-Experts (MoE) has become a prominent paradigm for scaling Large Language Models (LLMs). Parameter-efficient fine-tuning methods, such as LoRA, are widely adopted to adapt pretrained MoE LLMs to downstream tasks. However, existing approaches typically assign identical LoRA ranks to all expert modules, ignoring the heterogeneous specialization of pretrained experts. This uniform allocation leads to a resource mismatch: task-relevant experts are under-provisioned, while less relevant ones receive redundant parameters. To address this, we propose DR-LoRA, a Dynamic Rank LoRA framework for fine-tuning pretrained MoE models. Specifically, DR-LoRA initializes all expert LoRA modules with a small active rank and uses an expert saliency score, which combines routing frequency and gradient-based rank importance, to identify which experts would benefit most from additional capacity. It then periodically expands the active ranks of the task-critical expert LoRA, progressively constructing a heterogeneous rank distribution tailored to the target task. Experiments on three MoE models across six tasks show that DR-LoRA consistently outperforms LoRA and other strong baselines, demonstrating that task-adaptive heterogeneous rank allocation is an effective strategy to improve active capacity utilization in MoE fine-tuning.

We investigate the potential of weights to serve as effective representations, focusing on neural fields. Our key insight is that constraining the optimization space through a pre-trained base model and low-rank adaptation (LoRA) can induce structure in weight space. Across reconstruction, generation, and analysis tasks on 2D and 3D data, we find that multiplicative LoRA weights achieve high representation quality while exhibiting distinctiveness and semantic structure. When used with latent diffusion models, multiplicative LoRA weights enable higher-quality generation than existing weight-space methods.

This paper proposes FreeFuse, a training-free framework for multi-subject text-to-image generation through automatic fusion of multiple subject LoRAs. In contrast to prior studies that focus on retraining LoRAs to alleviate feature conflicts, our analysis shows that spatially routing LoRA residuals to their intended semantic regions provides an effective mechanism for suppressing direct cross-region LoRA interference while preserving the base model's global contextual reasoning. Accordingly, we implement Adaptive Token-Level Routing during the inference phase. However, obtaining reliable routing regions remains challenging. Existing methods that rely on text-image latent association, such as raw cross-attention or concept-level similarity matching, often suffer from sparse activations, hole artifacts, and unstable localization when handling visually similar subjects, leading to incomplete or ambiguous subject masks. To address these issues, we introduce FreeFuseAttn, a mechanism that exploits the flow matching model's intrinsic semantic alignment to dynamically match subject-specific tokens to their corresponding spatial regions at early denoising timesteps, thereby bypassing the need for external segmentors. FreeFuse distinguishes itself through high practicality: it necessitates no additional training, model modifications, or user-defined spatial constraints. Users need only provide subject activation words to achieve seamless integration into standard workflows. Extensive experiments validate that FreeFuse outperforms existing approaches in both identity preservation and compositional fidelity. The project page is at: https://future-item.github.io/FreeFuse/.

As increasingly large pre-trained models are released, deploying them on edge devices for privacy-preserving applications requires effective compression. Recent works combine quantization with the fine-tuning of high-precision LoRA adapters, which can substantially reduce model size while mitigating the accuracy loss from quantization. However, edge devices have inherently heterogeneous capabilities, while performing configuration-wise fine-tuning for every quantization setting is computationally prohibitive. In this paper, we propose CoA-LoRA, a method that dynamically adjusts the LoRA adapter to arbitrary quantization configurations (i.e., the per-layer bit-width choices of a pre-trained model) without requiring repeated fine-tuning. This is accomplished via a configuration-aware model that maps each configuration to its low-rank adjustments. The effectiveness of this model critically depends on the training configuration set, a collection of configurations chosen to cover different total bit-width budgets. However, constructing a high-quality configuration set is non-trivial. We therefore design a Pareto-based configuration search that iteratively optimizes the training configuration set, yielding more precise low-rank adjustments. Our experiments demonstrate that, unlike the state-of-the-art methods that require fine-tuning a separate LoRA adapter for each configuration, CoA-LoRA incurs no additional time cost while achieving comparable or even superior performance to those methods.

Parameter-Efficient Fine-Tuning (PEFT) is essential for adapting Large Language Models (LLMs) to multi-task scenarios. A prevailing trend in this field involves complex LoRA variants with multiple adapters or heads, which rely on the premise that architectural isolation of task-specific knowledge is necessary. However, this design often introduces dynamic routing, preventing weight merging and causing significant inference latency. In this work, we present a direct challenge to this paradigm. We first reveal a paradox where a simplified, router-free multi-head model with high inter-head redundancy outperforms complex, diversity-driven baselines. Furthermore, we demonstrate that a unified, single-adapter LoRA with increased rank achieves highly competitive performance, questioning the necessity of multi-component structures. Based on these findings, we propose Align-LoRA, a unified and efficient framework that shifts the focus from architectural isolation to representation alignment. Align-LoRA incorporates an explicit alignment loss to encourage the learning of task-shared representations within a shared latent space. Crucially, our method maintains the standard LoRA architecture, ensuring zero inference latency via weight merging. Theoretical analysis and extensive experiments confirm that Align-LoRA significantly surpasses prevailing approaches, establishing a simpler, more effective, and production-friendly paradigm for multi-task PEFT. The code is available at https://github.com/jinda-liu/Align-LoRA.

Low-Rank Adaptation (LoRA) has gained popularity as a fine-tuning approach for Large Language Models (LLMs) due to its low resource requirements and good performance. While numerous studies have investigated ways to improve LoRA serving efficiency by serving multiple LoRAs concurrently, existing methods assume that a wide range of LoRA adapters are available for serving. In our work, we conduct extensive empirical studies to show that current LoRA training paradigms do not efficiently utilize hardware resources and incur high overhead to obtain a performant LoRA adapter. Leveraging these insights, we propose PLoRA, which automatically orchestrates concurrent LoRA fine-tuning jobs under given hardware and model constraints and develops performant kernels to improve training efficiency. Across a range of LLMs and LoRA configurations, PLoRA improves training throughput by up to 12.8x and reduces the overall fine-tuning makespan by up to 7.52x compared to existing approaches.

The proliferation of Low-Rank Adaptation (LoRA) models has democratized personalized text-to-image generation, enabling users to share lightweight models (e.g., personal portraits) on platforms like Civitai and Liblib. However, this "share-and-play" ecosystem introduces critical risks: benign LoRAs can be weaponized by adversaries to generate harmful content (e.g., political, defamatory imagery), undermining creator rights and platform safety. Existing defenses like concept-erasure methods focus on full diffusion models (DMs), neglecting LoRA's unique role as a modular adapter and its vulnerability to adversarial prompt engineering. To bridge this gap, we propose LoRAShield, the first data-free editing framework for securing LoRA models against misuse. Our platform-driven approach dynamically edits and realigns LoRA's weight subspace via adversarial optimization and semantic augmentation. Experimental results demonstrate that LoRAShield achieves remarkable effectiveness, efficiency, and robustness in blocking malicious generations without sacrificing the functionality of the benign task. By shifting the defense to platforms, LoRAShield enables secure, scalable sharing of personalized models, a critical step toward trustworthy generative ecosystems.

Adapting large pretrained vision models to medical image classification is often limited by memory, computation, and task-specific specializations. Parameter-efficient fine-tuning (PEFT) methods like LoRA reduce this cost by learning low-rank updates, but operating directly in feature space can struggle to capture the localized, multi-scale features common in medical imaging. We propose WaRA, a wavelet-structured adaptation module that performs low-rank adaptation in a wavelet domain. WaRA reshapes patch tokens into a spatial grid, applies a fixed discrete wavelet transform, updates subband coefficients using a shared low-rank adapter, and reconstructs the additive update through an inverse wavelet transform. This design provides a compact trainable interface while biasing the update toward both coarse structure and fine detail. For extremely low-resource settings, we introduce Tiny-WaRA, which further reduces trainable parameters by learning only a small set of coefficients in a fixed basis derived from the pretrained weights through a truncated SVD. Experiments on medical image classification across four modalities and datasets demonstrate that WaRA consistently improves performance over strong PEFT baselines, while retaining a favorable efficiency profile. Our code is publicly available at https://github.com/moeinheidari7829/WaRA.

Many real-world applications collect data in a streaming environment, where learning tasks are encountered sequentially. This necessitates continual learning (CL) to update models online, enabling adaptation to new tasks while preserving past knowledge to prevent catastrophic forgetting. Nowadays, with the flourish of large pre-trained models (LPMs), efficiency has become increasingly critical for CL, due to their substantial computational demands and growing parameter sizes. In this paper, we introduce TreeLoRA (K-D Tree of Low-Rank Adapters), a novel approach that constructs layer-wise adapters by leveraging hierarchical gradient similarity to enable efficient CL, particularly for LPMs. To reduce the computational burden of task similarity estimation, we employ bandit techniques to develop an algorithm based on lower confidence bounds to efficiently explore the task structure. Furthermore, we use sparse gradient updates to facilitate parameter optimization, making the approach better suited for LPMs. Theoretical analysis is provided to justify the rationale behind our approach, and experiments on both vision transformers (ViTs) and large language models (LLMs) demonstrate the effectiveness and efficiency of our approach across various domains, including vision and natural language processing tasks.

This paper investigates how diffusion generative models leverage (unknown) low-dimensional structure to accelerate sampling. Focusing on two mainstream samplers -- the denoising diffusion implicit model (DDIM) and the denoising diffusion probabilistic model (DDPM), we prove that their iteration complexities under exact score functions are at most the order of $k/\varepsilon$ (up to log factor), where $\varepsilon$ is the precision in total variation distance and $k$ is some intrinsic dimension of the target distribution. We further extend these convergence guarantees to the setting in which the score functions are learned from data rather than known exactly, showing that the convergence performance degrades gracefully under suitable score estimation assumptions. We then show that these assumptions are attainable via kernel-based score estimators with finite-sample guarantees that also adapt to the low-dimensional structure. Our results apply to a broad family of target distributions without requiring smoothness or log-concavity. Our findings provide the first rigorous evidence for the adaptivity of the DDIM-type samplers to unknown low-dimensional structure, and improve over the state-of-the-art DDPM theory regarding total variation convergence.

Parameter-efficient fine-tuning (PEFT) has become a de facto standard for adapting large language models (LLMs). However, we identify a critical vulnerability within popular low-rank adaptation methods such as LoRA: they can exacerbate "Catastrophic Inheritance" - the unchecked propagation of biases, noise, and data imbalances from pre-training. This phenomenon can degrade model robustness and fairness, undermining the benefits of efficient adaptation. To address this, we introduce Bias-Alleviating Low-Rank Adaptation (BA-LoRA). Our approach is founded on a principled decomposition of Catastrophic Inheritance into three core challenges: Knowledge Drift, Representation Collapse, and Overfitting to Noise. BA-LoRA systematically mitigates these issues by incorporating a trio of targeted regularizers: consistency, diversity, and an SVD-based term, designed to preserve core knowledge, promote representational richness, and encourage robust, low-rank output representations, respectively. We conduct comprehensive evaluations on a suite of Natural Language Generation (NLG) and Natural Language Understanding (NLU) tasks using diverse, prominent open-source language models (e.g., LLaMA-2-7B and DeBERTa-v3-base). Our results show that BA-LoRA not only outperforms state-of-the-art LoRA variants in terms of performance and stability, but also demonstrates superior robustness and bias mitigation on targeted evaluations. These results provide evidence that BA-LoRA can counteract the adverse effects of Catastrophic Inheritance.

Geospatial foundation models (GeoFMs), pretrained on large-scale geospatial data such as Earth observation (EO), climate, and weather data, have shown promising performance when fine-tuned on diverse downstream tasks. However, there are two challenges of adapting EO-pretrained GeoFMs to practical downstream datasets. The first challenge is how to handle spectral mismatch: pretrained patch embeddings expect a fixed set of input bands, whereas downstream sensors may provide different channels. The second challenge is how to reduce fine-tuning cost and make it efficient. While existing work has made efforts on these challenges individually, jointly improving fine-tuning performance under spectral mismatch while reducing adaptation cost remains underexplored. We propose SPECTRA, a parameter-efficient fine-tuning framework that addresses both spectral mismatch and adaptation cost. To handle spectral mismatch, SPECTRA introduces Band-Routed Embedding (BRE), which maps all available downstream bands into the band space expected by the pretrained GeoFM. By using BRE, all available bands in the downstream dataset are utilized to improve the selected-band input without changing the pretrained patch embedding interface. To reduce adaptation cost, SPECTRA further introduces a Stage-wise Transferability-aware LoRA (ST-LoRA) fine-tuning. ST-LoRA estimates stage-wise transferability before fine-tuning and assigns stage-specific LoRA ranks, concentrating trainable parameters on the stages with high transferability for the target task. Across three EO-pretrained GeoFMs and four downstream segmentation datasets, experiments show that BRE improves performance by utilizing all spectral bands, while ST-LoRA reduces trainable parameters compared with full fine-tuning and standard LoRA. Code is available at https://github.com/big-data-lab-umbc/SPECTRA.