Transfer_Learning
-
HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet
2026-04-16 07:33:47Badri N. Patro, Vijay S. AgneeswaranAbstract
Vision State Space Models (SSMs) like Vim, VMamba, and SiMBA rely on complex scanning strategies to adapt sequential SSMs to process 2D images, introducing computational overhead and architectural complexity. We propose HAMSA, a scanning-free SSM operating directly in the spectral domain. HAMSA introduces three key innovations: (1) simplified kernel parameterization-a single Gaussian-initialized complex kernel replacing traditional (A, B, C) matrices, eliminating discretization instabilities; (2) SpectralPulseNet (SPN)-an input-dependent frequency gating mechanism enabling adaptive spectral modulation; and (3) Spectral Adaptive Gating Unit (SAGU)-magnitude-based gating for stable gradient flow in the frequency domain. By leveraging FFT-based convolution, HAMSA eliminates sequential scanning while achieving O(L log L) complexity with superior simplicity and efficiency. On ImageNet-1K, HAMSA reaches 85.7% top-1 accuracy (state-of-the-art among SSMs), with 2.2 X faster inference than transformers (4.2ms vs 9.2ms for DeiT-S) and 1.4-1.9X speedup over scanning-based SSMs, while using less memory (2.1GB vs 3.2-4.5GB) and energy (12.5J vs 18-25J). HAMSA demonstrates strong generalization across transfer learning and dense prediction tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14724
PDF
-
Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents
2026-04-15 15:50:29Kangsan Kim, Minki Kang, Taeil Kim, Yanlai Yang, Mengye Ren, Sung Ju HwangAbstract
Memory-based self-evolution has emerged as a promising paradigm for coding agents. However, existing approaches typically restrict memory utilization to homogeneous task domains, failing to leverage the shared infrastructural foundations, such as runtime environments and programming languages, that exist across diverse real-world coding problems. To address this limitation, we investigate \textbf{Memory Transfer Learning} (MTL) by harnessing a unified memory pool from heterogeneous domains. We evaluate performance across 6 coding benchmarks using four memory representations, ranging from concrete traces to abstract insights. Our experiments demonstrate that cross-domain memory improves average performance by 3.7\%, primarily by transferring meta-knowledge, such as validation routines, rather than task-specific code. Importantly, we find that abstraction dictates transferability; high-level insights generalize well, whereas low-level traces often induce negative transfer due to excessive specificity. Furthermore, we show that transfer effectiveness scales with the size of the memory pool, and memory can be transferred even between different models. Our work establishes empirical design principles for expanding memory utilization beyond single-domain silos. Project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2604.14004
PDF
-
AI Powered Image Analysis for Phishing Detection
2026-04-15 07:04:02K. Acharya, S. Ale, R. KadelAbstract
Phishing websites now rely heavily on visual imitation-copied logos, similar layouts, and matching colours-to avoid detection by text- and URL-based systems. This paper presents a deep learning approach that uses webpage screenshots for image-based phishing detection. Two vision models, ConvNeXt-Tiny and Vision Transformer (ViT-Base), were tested to see how well they handle visually deceptive phishing pages. The framework covers dataset creation, preprocessing, transfer learning with ImageNet weights, and evaluation using different decision thresholds. The results show that ConvNeXt-Tiny performs the best overall, achieving the highest F1-score at the optimised threshold and running more efficiently than ViT-Base. This highlights the strength of convolutional models for visual phishing detection and shows why threshold tuning is important for real-world deployment. As future work, the curated dataset used in this study will be released to support reproducibility and encourage further research in this area. Unlike many existing studies that primarily report accuracy, this work places greater emphasis on threshold-aware evaluation to better reflect real-world deployment conditions. By examining precision, recall, and F1-score across different decision thresholds, the study identifies operating points that balance detection performance and false-alarm control. In addition, the side-by-side comparison of ConvNeXt-Tiny and ViT-Base under the same experimental setup offers practical insights into how convolutional and transformer-based architectures differ in robustness and computational efficiency for visual phishing detection.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13555
PDF
-
Representation geometry shapes task performance in vision-language modeling for CT enterography
2026-04-14 17:56:23Cristian Minoccheri, Emily Wittrup, Kayvan Najarian, Ryan StidhamAbstract
Computed tomography (CT) enterography is a primary imaging modality for assessing inflammatory bowel disease (IBD), yet the representational choices that best support automated analysis of this modality are unknown. We present the first study of vision-language transfer learning on abdominal CT enterography and identify two main findings. First, mean pooling of slice embeddings gives better categorical disease assessment (59.2\% three-class accuracy), whereas attention pooling gives better cross-modal retrieval (0.235 text-to-image MRR). This pattern holds across all LoRA configurations tested and suggests that the two aggregators emphasize different properties of the learned representation. Second, per-slice tissue contrast matters more than broader spatial coverage: multi-window RGB encoding, which maps complementary Hounsfield Unit windows to RGB channels, outperforms all strategies that increase spatial coverage through multiplanar sampling, and in this setting adding coronal and sagittal views reduces classification performance. For report generation, fine-tuning without retrieval context yields within-1 severity accuracy at the prevalence-matched chance level (70.4\% vs.\ 71\% random), suggesting little learned ordering beyond the class distribution. Retrieval-augmented generation (RAG) improves this across all configurations, scoring 7--14 percentage points above the chance baseline and improving ordinal MAE from 0.98 to 0.80--0.89. A three-teacher pseudolabel framework enables all comparisons without expert annotations. Together, these findings provide the first baselines for this underexplored modality and offer practical guidance for building vision-language systems for volumetric medical imaging.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13021
PDF
-
Frequency-aware Decomposition Learning for Sensorless Wrench Forecasting on a Vibration-rich Hydraulic Manipulator
2026-04-14 15:54:29Hyeonbeen Lee, Min-Jae Jung, Tae-Kyeong Yeu, Jong-Boo Han, Daegil Park, Jin-Gyun KimAbstract
Force and torque (F/T) sensing is critical for robot-environment interaction, but physical F/T sensors impose constraints in size, cost, and fragility. To mitigate this, recent studies have estimated force/wrench sensorlessly from robot internal states. While existing methods generally target relatively slow interactions, tasks involving rapid interactions, such as grinding, can induce task-critical high-frequency vibrations, and estimation in such robotic settings remains underexplored. To address this gap, we propose a Frequency-aware Decomposition Network (FDN) for short-term forecasting of vibration-rich wrench from proprioceptive history. FDN predicts spectrally decomposed wrench with asymmetric deterministic and probabilistic heads, modeling the high-frequency residual as a learned conditional distribution. It further incorporates frequency-awareness to adaptively enhance input spectra with learned filtering and impose a frequency-band prior on the outputs. We pretrain FDN on a large-scale open-source robot dataset and transfer the learned proprioception-to-wrench representation to the downstream. On real-world grinding excavation data from a 6-DoF hydraulic manipulator and under a delayed estimation setting, FDN outperforms baseline estimators and forecasters in the high-frequency band and remains competitive in the low-frequency band. Transfer learning provides additional gains, suggesting the potential of large-scale pretraining and transfer learning for robotic wrench estimation. Code and data will be made available upon acceptance.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12905
PDF
-
Clustering-Enhanced Domain Adaptation for Cross-Domain Intrusion Detection in Industrial Control Systems
2026-04-14 01:25:59Luyao WangAbstract
Industrial control systems operate in dynamic environments where traffic distributions vary across scenarios, labeled samples are limited, and unknown attacks frequently emerge, posing significant challenges to cross-domain intrusion detection. To address this issue, this paper proposes a clustering-enhanced domain adaptation method for industrial control traffic. The framework contains two key components. First, a feature-based transfer learning module projects source and target domains into a shared latent subspace through spectral-transform-based feature alignment and iteratively reduces distribution discrepancies, enabling accurate cross-domain detection. Second, a clustering enhancement strategy combines K-Medoids clustering with PCA-based dimensionality reduction to improve cross-domain correlation estimation and reduce performance degradation caused by manual parameter tuning. Experimental results show that the proposed method significantly improves unknown attack detection. Compared with five baseline models, it increases detection accuracy by up to 49%, achieves larger gains in F-score, and demonstrates stronger stability. Moreover, the clustering enhancement strategy further boosts detection accuracy by up to 26% on representative tasks. These results suggest that the proposed method effectively alleviates data scarcity and domain shift, providing a practical solution for robust cross-domain intrusion detection in dynamic industrial environments.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12183
PDF
-
When Valid Signals Fail: Regime Boundaries Between LLM Features and RL Trading Policies
2026-04-13 04:53:06Zhengzhe YangAbstract
Can large language models (LLMs) generate continuous numerical features that improve reinforcement learning (RL) trading agents? We build a modular pipeline where a frozen LLM serves as a stateless feature extractor, transforming unstructured daily news and filings into a fixed-dimensional vector consumed by a downstream PPO agent. We introduce an automated prompt-optimization loop that treats the extraction prompt as a discrete hyperparameter and tunes it directly against the Information Coefficient - the Spearman rank correlation between predicted and realized returns - rather than NLP losses. The optimized prompt discovers genuinely predictive features (IC above 0.15 on held-out data). However, these valid intermediate representations do not automatically translate into downstream task performance: during a distribution shift caused by a macroeconomic shock, LLM-derived features add noise, and the augmented agent under-performs a price-only baseline. In a calmer test regime the agent recovers, yet macroeconomic state variables remain the most robust driver of policy improvement. Our findings highlight a gap between feature-level validity and policy-level robustness that parallels known challenges in transfer learning under distribution shift.
Abstract (translated)
URL
https://arxiv.org/abs/2604.10996
PDF
-
DSVTLA: Deep Swin Vision Transformer-Based Transfer Learning Architecture for Multi-Type Cancer Histopathological Cancer Image Classification
2026-04-10 16:25:27Muazzem Hussain Khan, Tasdid Hasnain, Md. Jamil khan, Ruhul Amin, Md. Shamim Reza, Md. Al Mehedi Hasan, Md Ashad AlamAbstract
In this study, we proposed a deep Swin-Vision Transformer-based transfer learning architecture for robust multi-cancer histopathological image classification. The proposed framework integrates a hierarchical Swin Transformer with ResNet50-based convolution features extraction, enabling the model to capture both long-range contextual dependencies and fine-grained local morphological patterns within histopathological images. To validate the efficiency of the proposed architecture, an extensive experiment was executed on a comprehensive multi-cancer dataset including Breast Cancer, Oral Cancer, Lung and Colon Cancer, Kidney Cancer, and Acute Lymphocytic Leukemia (ALL), including both original and segmented images were analyzed to assess model robustness across heterogeneous clinical imaging conditions. Our approach is benchmarked alongside several state-of-the-art CNN and transfer models, including DenseNet121, DenseNet201, InceptionV3, ResNet50, EfficientNetB3, multiple ViT variants, and Swin Transformer models. However, all models were trained and validated using a unified pipeline, incorporating balanced data preprocessing, transfer learning, and fine-tuning strategies. The experimental results demonstrated that our proposed architecture consistently gained superior performance, reaching 100% test accuracy for lung-colon cancer, segmented leukemia datasets, and up to 99.23% accuracy for breast cancer classification. The model also achieved near-perfect precision, f1 score, and recall, indicating highly stable scores across divers cancer types. Overall, the proposed model establishes a highly accurate, interpretable, and also robust multi-cancer classification system, demonstrating strong benchmark for future research and provides a unified comparative assessment useful for designing reliable AI-assisted histopathological diagnosis and clinical decision-making.
Abstract (translated)
URL
https://arxiv.org/abs/2604.09468
PDF
-
Memory-Efficient Transfer Learning with Fading Side Networks via Masked Dual Path Distillation
2026-04-10 08:16:59Yutong Zhang, Jiaxin Chen, Honglin Chen, Kaiqi Zheng, Shengcai Liao, Hanwen Zhong, Weixin Li, Yunhong WangAbstract
Memory-efficient transfer learning (METL) approaches have recently achieved promising performance in adapting pre-trained models to downstream tasks. They avoid applying gradient backpropagation in large backbones, thus significantly reducing the number of trainable parameters and high memory consumption during fine-tuning. However, since they typically employ a lightweight and learnable side network, these methods inevitably introduce additional memory and time overhead during inference, which contradicts the ultimate goal of efficient transfer learning. To address the above issue, we propose a novel approach dubbed Masked Dual Path Distillation (MDPD) to accelerate inference while retaining parameter and memory efficiency in fine-tuning with fading side networks. Specifically, MDPD develops a framework that enhances the performance by mutually distilling the frozen backbones and learnable side networks in fine-tuning, and discard the side network during inference without sacrificing accuracy. Moreover, we design a novel feature-based knowledge distillation method for the encoder structure with multiple layers. Extensive experiments on distinct backbones across vision/language-only and vision-and-language tasks demonstrate that our method not only accelerates inference by at least 25.2\% while keeping parameter and memory consumption comparable, but also remarkably promotes the accuracy compared to SOTA approaches. The source code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2604.09088
PDF
-
{sf TriDeliver}: Cooperative Air-Ground Instant Delivery with UAVs, Couriers, and Crowdsourced Ground Vehicles
2026-04-10 07:18:10Junhui Gao, Yan Pan, Qianru Wang, Wenzhe Hou, Yiqin Deng, Liangliang Jiang, Yuguang FangAbstract
Instant delivery, shipping items before critical deadlines, is essential in daily life. While multiple delivery agents, such as couriers, Unmanned Aerial Vehicles (UAVs), and crowdsourced agents, have been widely employed, each of them faces inherent limitations (e.g., low efficiency/labor shortages, flight control, and dynamic capabilities, respectively), preventing them from meeting the surging demands alone. This paper proposes {\sf TriDeliver}, the first hierarchical cooperative framework, integrating human couriers, UAVs, and crowdsourced ground vehicles (GVs) for efficient instant delivery. To obtain the initial scheduling knowledge for GVs and UAVs as well as improve the cooperative delivery performance, we design a Transfer Learning (TL)-based algorithm to extract delivery knowledge from couriers' behavioral history and transfer their knowledge to UAVs and GVs with fine-tunings, which is then used to dispatch parcels for efficient delivery. Evaluated on one-month real-world trajectory and delivery datasets, it has been demonstrated that 1) by integrating couriers, UAVs, and crowdsourced GVs, {\sf TriDeliver} reduces the delivery cost by $65.8\%$ versus state-of-the-art cooperative delivery by UAVs and couriers; 2) {\sf TriDeliver} achieves further improvements in terms of delivery time ($-17.7\%$), delivery cost ($-9.8\%$), and impacts on original tasks of crowdsourced GVs ($-43.6\%$), even with the representation of the transferred knowledge by simple neural networks, respectively.
Abstract (translated)
URL
https://arxiv.org/abs/2604.09049
PDF
-
When Fine-Tuning Changes the Evidence: Architecture-Dependent Semantic Drift in Chest X-Ray Explanations
2026-04-09 17:53:02Kabilan Elangovan, Daniel TingAbstract
Transfer learning followed by fine-tuning is widely adopted in medical image classification due to consistent gains in diagnostic performance. However, in multi-class settings with overlapping visual features, improvements in accuracy do not guarantee stability of the visual evidence used to support predictions. We define semantic drift as systematic changes in the attribution structure supporting a model's predictions between transfer learning and full fine-tuning, reflecting potential shifts in underlying visual reasoning despite stable classification performance. Using a five-class chest X-ray task, we evaluate DenseNet201, ResNet50V2, and InceptionV3 under a two-stage training protocol and quantify drift with reference-free metrics capturing spatial localization and structural consistency of attribution maps. Across architectures, coarse anatomical localization remains stable, while overlap IoU reveals pronounced architecture-dependent reorganization of evidential structure. Beyond single-method analysis, stability rankings can reverse across LayerCAM and GradCAM++ under converged predictive performance, establishing explanation stability as an interaction between architecture, optimization phase, and attribution objective.
Abstract (translated)
URL
https://arxiv.org/abs/2604.08513
PDF
-
Quantifying Explanation Consistency: The C-Score Metric for CAM-Based Explainability in Medical Image Classification
2026-04-09 17:47:31Kabilan Elangovan, Daniel TingAbstract
Class Activation Mapping (CAM) methods are widely used to generate visual explanations for deep learning classifiers in medical imaging. However, existing evaluation frameworks assess whether explanations are correct, measured by localisation fidelity against radiologist annotations, rather than whether they are consistent: whether the model applies the same spatial reasoning strategy across different patients with the same pathology. We propose the C-Score (Consistency Score), a confidence-weighted, annotation-free metric that quantifies intra-class explanation reproducibility via intensity-emphasised pairwise soft IoU across correctly classified instances. We evaluate six CAM techniques: GradCAM, GradCAM++, LayerCAM, EigenCAM, ScoreCAM, and MS GradCAM++ across three CNN architectures (DenseNet201, InceptionV3, ResNet50V2) over thirty training epochs on the Kermany chest X-ray dataset, covering transfer learning and fine-tuning phases. We identify three distinct mechanisms of AUC-consistency dissociation, invisible to standard classification metrics: threshold-mediated gold list collapse, technique-specific attribution collapse at peak AUC, and class-level consistency masking in global aggregation. C-Score provides an early warning signal of impending model instability. ScoreCAM deterioration on ResNet50V2 is detectable one full checkpoint before catastrophic AUC collapse and yields architecture-specific clinical deployment recommendations grounded in explanation quality rather than predictive ranking alone.
Abstract (translated)
URL
https://arxiv.org/abs/2604.08502
PDF
-
Sustainable Transfer Learning for Adaptive Robot Skills
2026-04-08 11:06:10Khalil Abuibaid, Vinit Hegiste, Nigora Gafur, Achim Wagner, Martin RuskowskiAbstract
Learning robot skills from scratch is often time-consuming, while reusing data promotes sustainability and improves sample efficiency. This study investigates policy transfer across different robotic platforms, focusing on peg-in-hole task using reinforcement learning (RL). Policy training is carried out on two different robots. Their policies are transferred and evaluated for zero-shot, fine-tuning, and training from scratch. Results indicate that zero-shot transfer leads to lower success rates and relatively longer task execution times, while fine-tuning significantly improves performance with fewer training time-steps. These findings highlight that policy transfer with adaptation techniques improves sample efficiency and generalization, reducing the need for extensive retraining and supporting sustainable robotic learning.
Abstract (translated)
URL
https://arxiv.org/abs/2604.06943
PDF
-
A Parameter-Efficient Transfer Learning Approach through Multitask Prompt Distillation and Decomposition for Clinical NLP
2026-04-08 03:52:52Cheng Peng, Mengxian Lyu, Ziyi Chen, Yonghui WuAbstract
Existing prompt-based fine-tuning methods typically learn task-specific prompts independently, imposing significant computing and storage overhead at scale when deploying multiple clinical natural language processing (NLP) systems. We present a multitask prompt distillation and decomposition framework that learns a single shared metaprompt from 21 diverse clinical source tasks and adapts it to unseen target tasks with fewer than 0.05% trainable parameters. Evaluated across five clinical NLP task types (named entity recognition, relation extraction, question answering, natural language inference, and summarization) on 10 held-out target datasets using three backbone models (LLaMA 3.1 8B, Meditron3 8B, gpt-oss 20B), our framework consistently outperforms LoRA by 1.5~1.7% despite using orders of magnitude fewer parameters, and exceeds single-task prompt tuning by 6.1~6.6%. The gpt-oss 20B model achieves the highest overall performance, particularly on clinical reasoning tasks. The strong zero- and few-shot performance demonstrates better transferability of the shared prompt representation.
Abstract (translated)
URL
https://arxiv.org/abs/2604.06650
PDF
-
TAPE: A two-stage parameter-efficient adaptation framework for foundation models in OCT-OCTA analysis
2026-04-06 10:08:43Xiaofei Su, Zengshuo Wang, Minghe Sun, Xin Zhao, Mingzhu SunAbstract
Automated analysis of optical coherence tomography (OCT) and OCT angiography (OCTA) images is critical for robust ophthalmic diagnosis. Existing mainstream methods trained from scratch rely heavily on massive data and model scale, thereby hindering their practical deployment in resource-constrained clinical settings. Although transfer learning based on foundation models (FMs) is promising, it still faces significant challenges: domain shift and task misalignment. To address these, we propose TAPE: A Two-stage Adaptation Framework via Parameter-Efficient Fine-tuning, which strategically decouples adaptation into domain alignment and task fitting for downstream segmentation. The domain adaptation stage notably applies parameter-efficient fine-tuning (PEFT) in the context of masked image modeling for medical image domain adaptation, a novel approach to the best of our knowledge. Applying TAPE to retinal layer segmentation on both universal (masked auto-encoder, MAE) and specialized (RETFound) FMs, it demonstrates superior parameter efficiency and achieves state-of-the-art generalization performance across diverse pathologies.
Abstract (translated)
光学相干断层扫描（OCT）与OCT血管成像（OCTA）图像的自动化分析对于稳健的眼科诊断至关重要。现有从零训练的主流方法严重依赖大规模数据与模型参数，从而阻碍了其在资源受限临床环境中的实际部署。尽管基于基础模型（FMs）的迁移学习前景可观，但仍面临领域偏移与任务错位两大挑战。针对这些问题，我们提出TAPE：一种通过参数高效微调实现的两阶段适应框架，该框架将下游分割任务的适应过程策略性地解耦为领域对齐与任务拟合两个阶段。领域适应阶段创新性地在掩码图像建模的医学图像领域适应场景中应用参数高效微调（PEFT），据我们所知此为首次提出。将TAPE应用于视网膜层分割任务时，无论在通用基础模型（掩码自编码器MAE）还是专业基础模型（RETFound）上，均展现出卓越的参数效率，并在多种病理条件下达到最先进的泛化性能。
URL
https://arxiv.org/abs/2604.04571
PDF
-
Learning Robust Visual Features in Computed Tomography Enables Efficient Transfer Learning for Clinical Tasks
2026-04-05 14:29:35Rub\'en Moreno-Aguado, Alba Magall\'on, Victor Moreno, Yingying Fang, Guang YangAbstract
There is substantial interest in developing artificial intelligence systems to support radiologists across tasks ranging from segmentation to report generation. Existing computed tomography (CT) foundation models have largely focused on building generalist vision-language systems capable of tasks such as question answering and report generation. However, training reliable vision-language systems requires paired image-text data at a scale that remains unavailable in CT. Moreover, adapting the underlying visual representations to downstream tasks typically requires partial or full backbone fine-tuning, a computationally demanding process inaccessible to many research groups. Instead, foundation models should prioritise learning robust visual representations that enable efficient transfer to new tasks with minimal labelled data and without backbone fine-tuning. We present VoxelFM, a 3D CT foundation model trained with self-distillation using the DINO framework, which learns semantically rich features without language supervision. We evaluated VoxelFM across seven categories of clinically relevant downstream tasks using frozen backbone representations with lightweight probes: classification, regression, survival analysis, instance retrieval, localisation, segmentation, and report generation. VoxelFM matched or outperformed four existing CT foundation models across all task categories. Despite receiving no language supervision during pre-training, VoxelFM surpassed models explicitly trained with language-alignment objectives, including on report generation. Our results indicate that current CT foundation models perform significantly better as feature extractors for lightweight probes rather than as vision encoders for vision-language models. Model weights and training code are publicly available.
Abstract (translated)
目前，医学界对开发人工智能系统以辅助放射科医生完成从分割到报告生成等任务抱有浓厚兴趣。现有的计算机断层扫描（CT）基础模型大多致力于构建能够执行问答和报告生成等任务的通用视觉-语言系统。然而，训练可靠的视觉-语言系统需要大规模配对的图像-文本数据，而CT领域目前仍缺乏此类数据。此外，将底层视觉表征适配到下游任务通常需要对主干网络进行部分或全部微调，这一计算密集型过程令许多研究团队难以企及。因此，基础模型应优先学习鲁棒的视觉表征，使其能够在无需微调主干网络、仅需少量标注数据的情况下高效迁移至新任务。本文提出VoxelFM，一个基于DINO框架通过自蒸馏训练的3D CT基础模型，可在无语言监督的情况下学习语义丰富的特征。我们使用冻结主干网络的特征表示结合轻量级探测头，在七个类别的临床相关下游任务上评估了VoxelFM：分类、回归、生存分析、实例检索、定位、分割和报告生成。结果显示，VoxelFM在所有任务类别中均达到或超越了四个现有CT基础模型的性能。尽管预训练阶段未接受语言监督，VoxelFM在报告生成等任务上仍超越了明确采用语言对齐目标训练的模型。我们的研究表明，当前CT基础模型作为轻量级探测头的特征提取器，其表现显著优于作为视觉-语言模型的视觉编码器。模型权重与训练代码已公开。
URL
https://arxiv.org/abs/2604.04133
PDF
-
Transfer learning for nonparametric Bayesian networks
2026-04-01 15:25:46Rafael Sojo, Pedro Larra\~naga, Concha BielzaAbstract
This paper introduces two transfer learning methodologies for estimating nonparametric Bayesian networks under scarce data. We propose two algorithms, a constraint-based structure learning method, called PC-stable-transfer learning (PCS-TL), and a score-based method, called hill climbing transfer learning (HC-TL). We also define particular metrics to tackle the negative transfer problem in each of them, a situation in which transfer learning has a negative impact on the model's performance. Then, for the parameters, we propose a log-linear pooling approach. For the evaluation, we learn kernel density estimation Bayesian networks, a type of nonparametric Bayesian network, and compare their transfer learning performance with the models alone. To do so, we sample data from small, medium and large-sized synthetic networks and datasets from the UCI Machine Learning repository. Then, we add noise and modifications to these datasets to test their ability to avoid negative transfer. To conclude, we perform a Friedman test with a Bergmann-Hommel post-hoc analysis to show statistical proof of the enhanced experimental behavior of our methods. Thus, PCS-TL and HC-TL demonstrate to be reliable algorithms for improving the learning performance of a nonparametric Bayesian network with scarce data, which in real industrial environments implies a reduction in the required time to deploy the network.
Abstract (translated)
本文介绍了两种在数据稀缺条件下用于估计非参数贝叶斯网络的迁移学习方法。我们提出了两种算法：一种是基于约束的结构学习方法，称为PC稳定迁移学习（PCS-TL）；另一种是基于评分的方法，称为爬山迁移学习（HC-TL）。同时，我们为每种方法定义了特定指标以解决负迁移问题——即迁移学习对模型性能产生负面影响的情况。对于参数估计，我们提出了一种对数线性池化方法。在评估阶段，我们学习了核密度估计贝叶斯网络（一种非参数贝叶斯网络），并将其迁移学习性能与单独模型进行比较。为此，我们从小型、中型和大型合成网络以及UCI机器学习库的数据集中采样数据，并通过对这些数据集添加噪声和修改来测试其避免负迁移的能力。最后，我们进行了弗里德曼检验并结合伯格曼-霍梅尔事后分析，以统计学证明我们方法的实验性能提升。因此，PCS-TL和HC-TL证明是可靠的算法，能够改善数据稀缺条件下非参数贝叶斯网络的学习性能，这在真实工业环境中意味着减少网络部署所需的时间。
URL
https://arxiv.org/abs/2604.01021
PDF
-
Bridging Structured Knowledge and Data: A Unified Framework with Finance Applications
2026-04-01 14:51:08Yi Cao, Zexun Chen, Lin William Cong, Heqing ShiAbstract
We develop Structured-Knowledge-Informed Neural Networks (SKINNs), a unified estimation framework that embeds theoretical, simulated, previously learned, or cross-domain insights as differentiable constraints within flexible neural function approximation. SKINNs jointly estimate neural network parameters and economically meaningful structural parameters in a single optimization problem, enforcing theoretical consistency not only on observed data but over a broader input domain through collocation, and therefore nesting approaches such as functional GMM, Bayesian updating, transfer learning, PINNs, and surrogate modeling. SKINNs define a class of M-estimators that are consistent and asymptotically normal with root-N convergence, sandwich covariance, and recovery of pseudo-true parameters under misspecification. We establish identification of structural parameters under joint flexibility, derive generalization and target-risk bounds under distributional shift in a convex proxy, and provide a restricted-optimal characterization of the weighting parameter that governs the bias-variance tradeoff. In an illustrative financial application to option pricing, SKINNs improve out-of-sample valuation and hedging performance, particularly at longer horizons and during high-volatility regimes, while recovering economically interpretable structural parameters with improved stability relative to conventional calibration. More broadly, SKINNs provide a general econometric framework for combining model-based reasoning with high-dimensional, data-driven estimation.
Abstract (translated)
我们开发了结构化知识感知神经网络（SKINNs），这是一种统一的估计框架，可将理论、模拟、先验学习或跨领域洞见作为可微约束嵌入到灵活的神经函数逼近器中。SKINNs在单一优化问题中联合估计神经网络参数与经济意义明确的结构参数，不仅通过配点法在观测数据上，更在更广泛的输入域内 enforce 理论一致性，从而统一了函数型GMM、贝叶斯更新、迁移学习、物理信息神经网络及代理模型等方法。SKINNs定义了一类M估计量，在设定错误时仍具有一致性、渐近正态性、根N收敛率、三明治协方差估计及伪真值参数恢复等性质。我们证明了在联合灵活性下结构参数的可识别性，在凸代理中推导了分布偏移下的泛化与目标风险界，并提供了控制偏差-方差权衡的加权参数的受限最优刻画。在期权定价的金融应用示例中，SKINNs提升了样本外估值与对冲表现，尤其在长期预测与高波动 regimes 中，同时相比传统校准方法能恢复更具经济解释性且稳定性更高的结构参数。更广泛地，SKINNs为结合基于模型的推理与高维数据驱动估计提供了通用计量框架。
URL
https://arxiv.org/abs/2604.00987
PDF
-
COTTA: Context-Aware Transfer Adaptation for Trajectory Prediction in Autonomous Driving
2026-04-01 02:36:28Seohyoung Park, Jaeyeol Lim, Seoyoung Ju, Kyeonghun Kim, Nam-Joon Kim, Hyuk-Jae LeeAbstract
Developing robust models to accurately predict the trajectories of surrounding agents is fundamental to autonomous driving safety. However, most public datasets, such as the Waymo Open Motion Dataset and Argoverse, are collected in Western road environments and do not reflect the unique traffic patterns, infrastructure, and driving behaviors of other regions, including South Korea. This domain discrepancy leads to performance degradation when state-of-the-art models trained on Western data are deployed in different geographic contexts. In this work, we investigate the adaptability of Query-Centric Trajectory Prediction (QCNet) when transferred from U.S.-based data to Korean road environments. Using a Korean autonomous driving dataset, we compare four training strategies: zero-shot transfer, training from scratch, full fine-tuning, and encoder freezing. Experimental results demonstrate that leveraging pretrained knowledge significantly improves prediction performance. Specifically, selectively fine-tuning the decoder while freezing the encoder yields the best trade-off between accuracy and training efficiency, reducing prediction error by over 66% compared to training from scratch. This study provides practical insights into effective transfer learning strategies for deploying trajectory prediction models in new geographic domains.
Abstract (translated)
开发稳健模型以准确预测周围智能体的轨迹，是实现自动驾驶安全的基础。然而，包括Waymo开放运动数据集和Argoverse在内的大多数公开数据集均采集于西方道路环境，未能反映韩国等其他地区独特的交通模式、基础设施和驾驶行为。这种领域差异导致在西方数据上训练的先进模型部署到不同地理环境时性能下降。本研究探讨了以查询为中心的轨迹预测模型（QCNet）从美国数据向韩国道路环境迁移的适应性。利用韩国自动驾驶数据集，我们对比了四种训练策略：零样本迁移、从头训练、全参数微调以及编码器冻结。实验结果表明，利用预训练知识可显著提升预测性能。具体而言，在冻结编码器的情况下选择性微调解码器，实现了精度与训练效率的最佳平衡，相较于从头训练将预测误差降低了超过66%。本研究为在新地理领域部署轨迹预测模型提供了有效的迁移学习策略实践见解。
URL
https://arxiv.org/abs/2604.00402
PDF
-
Q-DIVER: Integrated Quantum Transfer Learning and Differentiable Quantum Architecture Search with EEG Data
2026-03-30 07:37:53Junghoon Justin Park, Yeonghyeon Park, Jiook ChaAbstract
Integrating quantum circuits into deep learning pipelines remains challenging due to heuristic design limitations. We propose Q-DIVER, a hybrid framework combining a large-scale pretrained EEG encoder (DIVER-1) with a differentiable quantum classifier. Unlike fixed-ansatz approaches, we employ Differentiable Quantum Architecture Search to autonomously discover task-optimal circuit topologies during end-to-end fine-tuning. On the PhysioNet Motor Imagery dataset, our quantum classifier achieves predictive performance comparable to classical multi-layer perceptrons (Test F1: 63.49\%) while using approximately \textbf{50$\times$ fewer task-specific head parameters} (2.10M vs. 105.02M). These results validate quantum transfer learning as a parameter-efficient strategy for high-dimensional biological signal processing.
Abstract (translated)
将量子电路集成到深度学习流程中仍受限于启发式设计的局限性。我们提出Q-DIVER混合框架，该框架结合大规模预训练脑电图编码器（DIVER-1）与可微分量子分类器。不同于固定架构方法，我们采用可微分量子架构搜索，在端到端微调过程中自主发现任务最优电路拓扑结构。在PhysioNet运动想象数据集上，我们的量子分类器实现了与经典多层感知器相当的预测性能（测试F1值：63.49%），同时任务特定头部参数使用量减少约\textbf{50倍}（2.10M vs. 105.02M）。这些结果验证了量子迁移学习作为高维生物信号处理中参数高效策略的可行性。
URL
https://arxiv.org/abs/2603.28122
PDF
