Transfer_Learning
-
EVA: Towards a universal model of the immune system
2026-02-10 13:51:09Ethan Bandasack, Vincent Bouget, Apolline Bruley, Yannis Cattan, Charlotte Claye, Matthew Corney, Julien Duquesne, Karim El Kanbi, Aziz Fouch\'e, Pierre Marschall, Francesco StrozziAbstract
The effective application of foundation models to translational research in immune-mediated diseases requires multimodal patient-level representations that can capture complex phenotypes emerging from multicellular interactions. Yet most current biological foundation models focus only on single-cell resolution and are evaluated on technical metrics often disconnected from actual drug development tasks and challenges. Here, we introduce EVA, the first cross-species, multimodal foundation model of immunology and inflammation, a therapeutic area where shared pathogenic mechanisms create unique opportunities for transfer learning. EVA harmonizes transcriptomics data across species, platforms, and resolutions, and integrates histology data to produce rich, unified patient representations. We establish clear scaling laws, demonstrating that increasing model size and compute translates to improvements in both pretraining and downstream tasks performance. We introduce a comprehensive evaluation suite of 39 tasks spanning the drug development pipeline: zero-shot target efficacy and gene function prediction for discovery, cross-species or cross-diseases molecular perturbations for preclinical development, and patient stratification with treatment response prediction or disease activity prediction for clinical trials applications. We benchmark EVA against several state-of-the-art biological foundation models and baselines on these tasks, and demonstrate state-of-the-art results on each task category. Using mechanistic interpretability, we further identify biological meaningful features, revealing intertwined representations across species and technologies. We release an open version of EVA for transcriptomics to accelerate research on immune-mediated diseases.
Abstract (translated)
将基础模型有效应用于自身免疫性疾病转化研究，需要多模态的患者层面表示，这些表示能够捕捉到复杂表型，而后者是由多细胞相互作用产生的。然而，目前大多数生物基础模型仅专注于单细胞解析，并且其评估指标通常与实际药物开发任务和挑战脱节。在这里，我们介绍了EVA——首个跨物种、多模态的免疫学和炎症基础模型，在这种治疗领域中共享的致病机制创造了独特的迁移学习机会。 EVA 跨越物种、平台和分辨率对转录组数据进行协调，并整合组织病理学数据以生成丰富统一的患者表示。我们确立了明确的扩展规律，表明增加模型大小和计算量可以提升预训练及下游任务性能。我们还提出了一套全面的任务评估工具集，涵盖药物开发流程中的39项任务：包括发现阶段的零样本靶点功效与基因功能预测、临床前研发阶段跨物种或跨疾病的分子扰动实验以及用于临床试验应用患者的分层治疗反应和疾病活动性预测。 我们在这些任务上对EVA与其他最先进的生物基础模型及基准进行了对比测试，并在每个任务类别中展示了最优结果。通过机制解释，我们进一步识别出具有生物学意义的特征，揭示了跨物种和技术交织表示的特点。我们将发布一个公开版本的EVA转录组学以加速自身免疫性疾病研究进程。
URL
https://arxiv.org/abs/2602.10168
PDF
-
Sim2Radar: Toward Bridging the Radar Sim-to-Real Gap with VLM-Guided Scene Reconstruction
2026-02-10 10:56:47Emily Bejerano, Federico Tondolo, Aayan Qayyum, Xiaofan Yu, Xiaofan JiangAbstract
Millimeter-wave (mmWave) radar provides reliable perception in visually degraded indoor environments (e.g., smoke, dust, and low light), but learning-based radar perception is bottlenecked by the scarcity and cost of collecting and annotating large-scale radar datasets. We present Sim2Radar, an end-to-end framework that synthesizes training radar data directly from single-view RGB images, enabling scalable data generation without manual scene modeling. Sim2Radar reconstructs a material-aware 3D scene by combining monocular depth estimation, segmentation, and vision-language reasoning to infer object materials, then simulates mmWave propagation with a configurable physics-based ray tracer using Fresnel reflection models parameterized by ITU-R electromagnetic properties. Evaluated on real-world indoor scenes, Sim2Radar improves downstream 3D radar perception via transfer learning: pre-training a radar point-cloud object detection model on synthetic data and fine-tuning on real radar yields up to +3.7 3D AP (IoU 0.3), with gains driven primarily by improved spatial localization. These results suggest that physics-based, vision-driven radar simulation can provide effective geometric priors for radar learning and measurably improve performance under limited real-data supervision.
Abstract (translated)
URL
https://arxiv.org/abs/2602.13314
PDF
-
A Deep Multi-Modal Method for Patient Wound Healing Assessment
2026-02-10 01:21:32Subba Reddy Oota, Vijay Rowtula, Shahid Mohammed, Jeffrey Galitz, Minghsun Liu, Manish GuptaAbstract
Hospitalization of patients is one of the major factors for high wound care costs. Most patients do not acquire a wound which needs immediate hospitalization. However, due to factors such as delay in treatment, patient's non-compliance or existing co-morbid conditions, an injury can deteriorate and ultimately lead to patient hospitalization. In this paper, we propose a deep multi-modal method to predict the patient's risk of hospitalization. Our goal is to predict the risk confidently by collectively using the wound variables and wound images of the patient. Existing works in this domain have mainly focused on healing trajectories based on distinct wound types. We developed a transfer learning-based wound assessment solution, which can predict both wound variables from wound images and their healing trajectories, which is our primary contribution. We argue that the development of a novel model can help in early detection of the complexities in the wound, which might affect the healing process and also reduce the time spent by a clinician to diagnose the wound.
Abstract (translated)
住院是导致伤口护理成本高昂的主要因素之一。大多数患者受伤后不需要立即住院治疗，但因延误治疗、患者的不依从性或现有合并症等因素，伤情可能会恶化并最终导致病人入院。本文提出了一种深度多模态方法来预测病人的住院风险。我们的目标是通过综合使用伤口变量和伤口图像信息，准确地预测住院的风险。 在该领域现有的研究大多集中在基于不同类型伤口的愈合轨迹上。我们开发了一种基于迁移学习的伤口评估解决方案，能够从伤口图像中预测伤口变量及其愈合轨迹，这是本文的主要贡献。我们认为，新型模型的发展可以帮助及早发现可能影响愈合过程的伤口复杂性，并减少临床医生诊断伤口所需的时间。
URL
https://arxiv.org/abs/2602.09315
PDF
-
The Influence of Iconicity in Transfer Learning for Sign Language Recognition
2026-02-09 17:26:15Keren Artiaga, Conor Lynch, Haithem Afli, Mohammed HasanuzzamanAbstract
Most sign language recognition research relies on Transfer Learning (TL) from vision-based datasets such as ImageNet. Some extend this to alternatively available language datasets, often focusing on signs with cross-linguistic similarities. This body of work examines the necessity of these likenesses on effective knowledge transfer by comparing TL performance between iconic signs of two different sign language pairs: Chinese to Arabic and Greek to Flemish. Google Mediapipe was utilised as an input feature extractor, enabling spatial information of these signs to be processed with a Multilayer Perceptron architecture and the temporal information with a Gated Recurrent Unit. Experimental results showed a 7.02% improvement for Arabic and 1.07% for Flemish when conducting iconic TL from Chinese and Greek respectively.
Abstract (translated)
大多数手语识别研究依赖于从基于视觉的数据集（如ImageNet）进行迁移学习（TL）。有些研究则扩展到使用其他可用的语言数据集，通常关注具有跨语言相似性的手势。这项工作通过比较两种不同手语对之间标志性手势的迁移学习性能来探讨这些相似性在有效知识转移中的必要性：中文至阿拉伯文和希腊文至弗拉芒语（比利时荷兰语）。谷歌Mediapipe被用作输入特征提取器，使得这些手势的空间信息可以通过多层感知机架构进行处理，时间信息则通过门控循环单元进行处理。实验结果显示，在从中文和希腊语分别进行标志性迁移学习时，阿拉伯文手语识别准确率提高了7.02%，弗拉芒语文本提高1.07%。
URL
https://arxiv.org/abs/2603.03316
PDF
-
Enhanced Food Category Recognition under Illumination-Induced Domain Shift
2026-02-09 10:43:51Keonvin Park, Aditya Pal, Jin Hong MokAbstract
Visual food recognition systems deployed in real-world environments, such as automated conveyor-belt inspection, are highly sensitive to domain shifts caused by illumination changes. While recent studies have shown that lighting variations can significantly distort food perception by both humans and AI, existing works are often limited to single food categories or controlled settings, and most public food datasets lack explicit illumination annotations. In this work, we investigate illumination-induced domain shift in multi-class food category recognition using two widely adopted datasets, Food-101 and Fruits-360. We demonstrate substantial accuracy degradation under cross-dataset evaluation due to mismatched visual conditions. To address this challenge, we construct synthetic illumination-augmented datasets by systematically varying light temperature and intensity, enabling controlled robustness analysis without additional labels. We further evaluate cross-dataset transfer learning and domain generalization, with a focus on illumination-sensitive target categories such as apple-based classes. Experimental results show that illumination-aware augmentation significantly improves recognition robustness under domain shift while preserving real-time performance. Our findings highlight the importance of illumination robustness and provide practical insights for deploying reliable food recognition systems in real-world inspection scenarios.
Abstract (translated)
在现实世界环境中部署的视觉食品识别系统（例如自动化传送带检查）对由于照明变化引起的领域偏移非常敏感。最近的研究表明，光照的变化会显著扭曲人类和AI对食物的感知。然而，现有的大多数研究通常仅限于单一的食物类别或受控设置，并且大多数公开的食物数据集缺乏明确的照明标注。 在这项工作中，我们使用两个广泛采用的数据集（Food-101 和 Fruits-360）来调查多类食品分类识别中的光照引起的领域偏移问题。我们在跨数据集评估中展示了由于视觉条件不匹配导致的显著准确性下降。为了解决这一挑战，我们通过系统地改变光源温度和强度构建了合成光照增强的数据集，这使我们能够在无需额外标注的情况下进行受控鲁棒性分析。此外，我们还评估了跨数据集迁移学习和领域泛化，重点关注对光照敏感的目标类别（如苹果类）。实验结果表明，在保留实时性能的同时，光照感知增强显著提高了在域偏移下的识别鲁棒性。 我们的研究强调了照明鲁棒性的关键重要性，并为部署可靠的食物识别系统于现实世界中的检查场景提供了实用见解。
URL
https://arxiv.org/abs/2602.08491
PDF
-
Optimizing Spectral Prediction in MXene-Based Metasurfaces Through Multi-Channel Spectral Refinement and Savitzky-Golay Smoothing
2026-02-09 09:09:32Shujaat Khan, Waleed Iqbal WaseerAbstract
The prediction of electromagnetic spectra for MXene-based solar absorbers is a computationally intensive task, traditionally addressed using full-wave solvers. This study introduces an efficient deep learning framework incorporating transfer learning, multi-channel spectral refinement (MCSR), and Savitzky-Golay smoothing to accelerate and enhance spectral prediction accuracy. The proposed architecture leverages a pretrained MobileNetV2 model, fine-tuned to predict 102-point absorption spectra from $64\times64$ metasurface designs. Additionally, the MCSR module processes the feature map through multi-channel convolutions, enhancing feature extraction, while Savitzky-Golay smoothing mitigates high-frequency noise. Experimental evaluations demonstrate that the proposed model significantly outperforms baseline Convolutional Neural Network (CNN) and deformable CNN models, achieving an average root mean squared error (RMSE) of 0.0245, coefficient of determination \( R^2 \) of 0.9578, and peak signal-to-noise ratio (PSNR) of 32.98 dB. The proposed framework presents a scalable and computationally efficient alternative to conventional solvers, positioning it as a viable candidate for rapid spectral prediction in nanophotonic design workflows.
Abstract (translated)
基于MXene的太阳能吸收器电磁光谱的预测是一项计算密集型任务，传统上使用全波求解器来处理。本研究提出了一种高效的深度学习框架，该框架结合了迁移学习、多通道光谱精炼（MCSR）和Savitzky-Golay平滑技术，旨在加速并提高光谱预测的准确性。所提出的架构利用了一个预训练的MobileNetV2模型，并对其进行微调以从$64\times64$元表面设计中预测102个点吸收光谱。此外，MCSR模块通过多通道卷积处理特征图，增强了特征提取过程；而Savitzky-Golay平滑则用于减少高频噪声。 实验评估表明，所提出的模型在基线卷积神经网络（CNN）和可变形CNN模型上表现出显著的性能优势，在平均均方根误差（RMSE）、决定系数 \( R^2 \) 和峰值信噪比（PSNR）方面分别达到了0.0245、0.9578和32.98 dB。所提出的框架为传统的求解器提供了一个可扩展且计算效率高的替代方案，使其成为纳米光子设计工作流程中快速光谱预测的可行候选方法。
URL
https://arxiv.org/abs/2602.08406
PDF
-
Vision Transformer Finetuning Benefits from Non-Smooth Components
2026-02-06 17:12:22Ambroise Odonnat, Laetitia Chapel, Romain Tavenard, Ievgen RedkoAbstract
The smoothness of the transformer architecture has been extensively studied in the context of generalization, training stability, and adversarial robustness. However, its role in transfer learning remains poorly understood. In this paper, we analyze the ability of vision transformer components to adapt their outputs to changes in inputs, or, in other words, their plasticity. Defined as an average rate of change, it captures the sensitivity to input perturbation; in particular, a high plasticity implies low smoothness. We demonstrate through theoretical analysis and comprehensive experiments that this perspective provides principled guidance in choosing the components to prioritize during adaptation. A key takeaway for practitioners is that the high plasticity of the attention modules and feedforward layers consistently leads to better finetuning performance. Our findings depart from the prevailing assumption that smoothness is desirable, offering a novel perspective on the functional properties of transformers. The code is available at this https URL.
Abstract (translated)
Transformer架构的平滑性在泛化、训练稳定性和对抗鲁棒性的背景下已经得到了广泛的研究。然而，它在迁移学习中的作用仍然鲜为人知。在这篇论文中，我们分析了视觉变压器组件适应输入变化的能力，或者换句话说，它们的可塑性。作为平均变化率来定义，它可以捕捉到对输入扰动的敏感度；特别是，高可塑性意味着低平滑度。通过理论分析和全面实验，我们证明这种视角为选择在适应过程中优先考虑的组件提供了原则性的指导。对于从业者而言，一个重要发现是注意力模块和前馈层的高可塑性始终导致更好的微调性能。我们的研究结果与普遍认为平滑性是有益的观点相悖，提出了关于变压器功能属性的新观点。代码可以在[此处](https://this https URL)获取。
URL
https://arxiv.org/abs/2602.06883
PDF
-
ASMa: Asymmetric Spatio-temporal Masking for Skeleton Action Representation Learning
2026-02-05 22:59:35Aman Anand, Amir Eskandari, Elyas Rahsno, Farhana ZulkernineAbstract
Self-supervised learning (SSL) has shown remarkable success in skeleton-based action recognition by leveraging data augmentations to learn meaningful representations. However, existing SSL methods rely on data augmentations that predominantly focus on masking high-motion frames and high-degree joints such as joints with degree 3 or 4. This results in biased and incomplete feature representations that struggle to generalize across varied motion patterns. To address this, we propose Asymmetric Spatio-temporal Masking (ASMa) for Skeleton Action Representation Learning, a novel combination of masking to learn a full spectrum of spatio-temporal dynamics inherent in human actions. ASMa employs two complementary masking strategies: one that selectively masks high-degree joints and low-motion, and another that masks low-degree joints and high-motion frames. These masking strategies ensure a more balanced and comprehensive skeleton representation learning. Furthermore, we introduce a learnable feature alignment module to effectively align the representations learned from both masked views. To facilitate deployment in resource-constrained settings and on low-resource devices, we compress the learned and aligned representation into a lightweight model using knowledge distillation. Extensive experiments on NTU RGB+D 60, NTU RGB+D 120, and PKU-MMD datasets demonstrate that our approach outperforms existing SSL methods with an average improvement of 2.7-4.4% in fine-tuning and up to 5.9% in transfer learning to noisy datasets and achieves competitive performance compared to fully supervised baselines. Our distilled model achieves 91.4% parameter reduction and 3x faster inference on edge devices while maintaining competitive accuracy, enabling practical deployment in resource-constrained scenarios.
Abstract (translated)
自监督学习（SSL）在基于骨架的动作识别中取得了显著的成功，通过利用数据增强来学习有意义的表示。然而，现有的SSL方法依赖于主要关注遮蔽高运动帧和高阶关节（如3度或4度关节）的数据增强，这导致了有偏且不完整的特征表示，难以泛化到各种运动模式上。为了解决这个问题，我们提出了不对称时空遮蔽（ASMa），这是一种用于骨架动作表征学习的新颖组合方法，它通过一种新的掩码策略来全面学习人体动作中内在的时空动态特性。 ASMa采用两种互补的掩码策略：一是选择性地对高阶关节和低运动进行掩码处理；二是对低阶关节和高运动帧进行掩码处理。这两种掩码策略确保了更平衡和综合的骨架表示学习过程。此外，我们引入了一个可学习的功能对齐模块，以有效地将从两种被遮蔽视图中学到的表征进行对齐。 为了便于在资源受限环境及低资源设备上部署，我们将学到并对齐后的表征压缩成一个轻量级模型，并使用知识蒸馏技术来实现这一点。在NTU RGB+D 60、NTU RGB+D 120和PKU-MMD数据集上的广泛实验表明，我们的方法优于现有的SSL方法，在微调阶段平均提高了2.7-4.4%，并在迁移到嘈杂的数据集时最多提升了5.9%。此外，在与完全监督的基线相比时，我们的方法也达到了竞争性的性能。 压缩后的模型实现了高达91.4%的参数减少，并且在边缘设备上推理速度提高了3倍，同时保持了竞争力的准确性，这使得在资源受限场景下的实际部署成为可能。
URL
https://arxiv.org/abs/2602.06251
PDF
-
NanoNet: Parameter-Efficient Learning with Label-Scarce Supervision for Lightweight Text Mining Model
2026-02-05 08:31:57Qianren Mao, Yashuo Luo, Ziqi Qin, Junnan Liu, Weifeng Jiang, Zhijun Chen, Zhuoran Li, Likang Xiao, Chuou Xu, Qili Zhang, Hanwen Hao, Jingzheng Li, Chunghua Lin, Jianxin Li, Philip S. YuAbstract
The lightweight semi-supervised learning (LSL) strategy provides an effective approach of conserving labeled samples and minimizing model inference costs. Prior research has effectively applied knowledge transfer learning and co-training regularization from large to small models in LSL. However, such training strategies are computationally intensive and prone to local optima, thereby increasing the difficulty of finding the optimal solution. This has prompted us to investigate the feasibility of integrating three low-cost scenarios for text mining tasks: limited labeled supervision, lightweight fine-tuning, and rapid-inference small models. We propose NanoNet, a novel framework for lightweight text mining that implements parameter-efficient learning with limited supervision. It employs online knowledge distillation to generate multiple small models and enhances their performance through mutual learning regularization. The entire process leverages parameter-efficient learning, reducing training costs and minimizing supervision requirements, ultimately yielding a lightweight model for downstream inference.
Abstract (translated)
轻量级半监督学习（LSL）策略提供了一种有效的方法，用于节省标注样本并最小化模型推理成本。先前的研究已经成功地将知识迁移学习和协作训练正则化从大型模型应用到小型模型中以实现LSL的目标。然而，这类训练策略计算负担较重且容易陷入局部最优解，从而增加了找到最佳解决方案的难度。这促使我们研究在文本挖掘任务中整合三种低成本场景的可能性：有限标注监督、轻量级微调和快速推理的小型模型。为此，我们提出了一种名为NanoNet的新框架，用于轻量级文本挖掘，该框架实现参数高效的有限监督学习。它使用在线知识蒸馏来生成多个小型模型，并通过相互学习正则化提高它们的性能。整个过程利用了参数高效的学习方法，从而减少了训练成本并最小化了监督需求，最终为下游推理提供了一个轻量级模型。
URL
https://arxiv.org/abs/2602.06093
PDF
-
Smart Diagnosis and Early Intervention in PCOS: A Deep Learning Approach to Women's Reproductive Health
2026-02-04 18:58:21Shayan Abrar, Samura Rahman, Ishrat Jahan Momo, Mahjabin Tasnim Samiha, B. M. Shahria Alam, Mohammad Tahmid Noor, Nishat Tasnim NiloyAbstract
Polycystic Ovary Syndrome (PCOS) is a widespread disorder in women of reproductive age, characterized by a hormonal imbalance, irregular periods, and multiple ovarian cysts. Infertility, metabolic syndrome, and cardiovascular risks are long-term complications that make early detection essential. In this paper, we design a powerful framework based on transfer learning utilizing DenseNet201 and ResNet50 for classifying ovarian ultrasound images. The model was trained on an online dataset containing 3856 ultrasound images of cyst-infected and non-infected patients. Each ultrasound frame was resized to 224x224 pixels and encoded with precise pathological indicators. The MixUp and CutMix augmentation strategies were used to improve generalization, yielding a peak validation accuracy of 99.80% by Densenet201 and a validation loss of 0.617 with alpha values of 0.25 and 0.4, respectively. We evaluated the model's interpretability using leading Explainable AI (XAI) approaches such as SHAP, Grad-CAM, and LIME, reasoning with and presenting explicit visual reasons for the model's behaviors, therefore increasing the model's transparency. This study proposes an automated system for medical picture diagnosis that may be used effectively and confidently in clinical practice.
Abstract (translated)
多囊卵巢综合症（PCOS）是育龄妇女中常见的疾病，其特征包括激素失衡、月经不规律以及多个卵巢囊肿。长期的并发症如不孕症、代谢综合征和心血管风险凸显了早期检测的重要性。本文设计了一个基于迁移学习框架的方法，利用DenseNet201和ResNet50模型对卵巢超声图像进行分类。该模型在包含3856张囊性病变患者及非病变患者的在线数据集上进行了训练。每帧超声图被调整为224x224像素，并用精确的病理指标编码。为了提高泛化能力，采用了MixUp和CutMix增强策略，使得Densenet201模型达到峰值验证准确率99.80%，同时ResNet50模型在alpha值分别为0.25和0.4时取得了0.617的验证损失。 我们使用领先的可解释性人工智能（XAI）方法如SHAP、Grad-CAM以及LIME来评估该模型的可解释性，通过提供具体的视觉理由来说明模型的行为，从而增加了模型透明度。本研究提出了一种自动化的医学影像诊断系统，可以在临床实践中有效且自信地应用。 本文的研究为基于超声图像的PCOS早期检测提供了高效、准确的方法，并进一步探讨了如何提高深度学习在医疗领域应用中的可解释性与可靠性。
URL
https://arxiv.org/abs/2602.04944
PDF
-
Multiview Self-Representation Learning across Heterogeneous Views
2026-02-04 08:45:54Jie Chen, Zhu Wang, Chuanbin Liu, Xi PengAbstract
Features of the same sample generated by different pretrained models often exhibit inherently distinct feature distributions because of discrepancies in the model pretraining objectives or architectures. Learning invariant representations from large-scale unlabeled visual data with various pretrained models in a fully unsupervised transfer manner remains a significant challenge. In this paper, we propose a multiview self-representation learning (MSRL) method in which invariant representations are learned by exploiting the self-representation property of features across heterogeneous views. The features are derived from large-scale unlabeled visual data through transfer learning with various pretrained models and are referred to as heterogeneous multiview data. An individual linear model is stacked on top of its corresponding frozen pretrained backbone. We introduce an information-passing mechanism that relies on self-representation learning to support feature aggregation over the outputs of the linear model. Moreover, an assignment probability distribution consistency scheme is presented to guide multiview self-representation learning by exploiting complementary information across different views. Consequently, representation invariance across different linear models is enforced through this scheme. In addition, we provide a theoretical analysis of the information-passing mechanism, the assignment probability distribution consistency and the incremental views. Extensive experiments with multiple benchmark visual datasets demonstrate that the proposed MSRL method consistently outperforms several state-of-the-art approaches.
Abstract (translated)
不同预训练模型生成的同一样本特征通常会表现出固有的分布差异，这是由于这些模型在预训练目标或架构上的不同。从大规模未标记视觉数据中使用各种预训练模型通过完全无监督的方式学习不变表示仍然是一项重大挑战。在这篇论文中，我们提出了一种多视图自表征学习（MSRL）方法，在这种方法中，通过利用异构视角下特征的自表征特性来学习不变表示。这些特征是从大规模未标记视觉数据中通过对不同预训练模型进行迁移学习得到，并被称作异构多视角数据。在其对应的冻结的预训练骨干网络之上堆叠一个独立的线性模型。我们引入了一种基于自表征学习的信息传递机制，通过该机制支持在线性模型输出上的特征聚合。此外，还提出了一种分配概率分布一致性方案，利用不同视图间的互补信息来指导多视角自表征学习，并且通过这种方案强制执行不同线性模型之间的表示不变性。另外，我们提供了关于信息传递机制、分配概率分布一致性和增量视图的理论分析。 在多个基准视觉数据集上的广泛实验表明，所提出的MSRL方法始终优于几种最先进的方法。
URL
https://arxiv.org/abs/2602.04328
PDF
-
Entropy Reveals Block Importance in Masked Self-Supervised Vision Transformers
2026-02-03 18:27:24Peihao Xiang, Kaida Wu, Ou BaiAbstract
Masked self-supervised vision transformers have become a dominant pretraining paradigm, yet their substantial model size poses significant challenges for resource-constrained deployment and efficient transfer learning. A fundamental question remains: are all transformer blocks equally important for downstream performance? In this paper, we show that block importance in masked self-supervised vision transformers can be accurately estimated without access to any data. Our key finding is that the information entropy of pretrained block weights strongly correlates with oracle sensitivity obtained via iterative block removal and finetuning. This observation enables Gardener, a data-free, one-shot, block-level pruning principle that identifies redundant blocks through simple information-theoretic measurements. We evaluate Gardener on VideoMAE-B across multiple pruning ratios and downstream video recognition benchmarks. Despite its negligible computational overhead, Gardener consistently matches or outperforms existing data-free pruning baselines and closely approaches sensitivity-based pruning. Remarkably, even after pruning up to 91.7\% of blocks, the pruned model retains competitive transfer performance. Our results reveal substantial block-level redundancy in masked self-supervised vision transformers and demonstrate that information-theoretic analysis offers a principled and efficient pathway for model compression and resource-efficient transfer learning.
Abstract (translated)
遮蔽自监督视觉变压器已成为预训练的主导范式，但其巨大的模型规模对资源受限部署和高效迁移学习带来了重大挑战。一个基本的问题是：所有的Transformer块对于下游任务的表现都是同样重要的吗？在本文中，我们展示了可以在没有任何数据访问的情况下准确估计遮蔽自监督视觉变压器中的块重要性。我们的关键发现是，预训练的块权重的信息熵与通过迭代删除块和微调获得的Oracle敏感度有着强烈的关联。这一观察结果使Gardener成为可能——这是一种无数据、一次性、基于块级别的剪枝原则，它通过简单的信息理论测量来识别冗余的块。我们在VideoMAE-B上评估了Gardener，在多个剪枝比例和下游视频识别基准测试中进行了测试。尽管其计算开销几乎可以忽略不计，但Gardener在与现有的无数据剪枝基线相匹配或超越它们的同时，也接近基于敏感度的剪枝方法的表现。值得注意的是，即使是在修剪掉高达91.7%块之后，被剪枝后的模型仍能保持有竞争力的迁移性能。 我们的结果揭示了遮蔽自监督视觉Transformer中大量的块级别冗余，并且展示了信息理论分析提供了一条原则性和高效的方法来压缩模型并实现资源高效的迁移学习。
URL
https://arxiv.org/abs/2602.03918
PDF
-
Lagged backward-compatible physics-informed neural networks for unsaturated soil consolidation analysis
2026-02-03 04:31:21Dong Li (Department of Civil, Environmental, and Infrastructure Engineering, George Mason University, Fairfax, VA, USA), Shuai Huang (National Institute of Natural Hazards, Ministry of Emergency Management, Beijing, China), Yapeng Cao (State Key Laboratory of Cryospheric Science and Frozen Soil Engineering, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou, China, Navier Laboratory, \'Ecole Nationale des Ponts et Chauss\'ees, Marne-la-Vall\'ee Cedex 2, France), Yujun Cui (Navier Laboratory, \'Ecole Nationale des Ponts et Chauss\'ees, Marne-la-Vall\'ee Cedex 2, France), Xiaobin Wei (School of Civil Engineering, Hebei University of Engineering, Handan, China), Hongtao Cao (College of Civil Engineering, Zhejiang University of Technology, Hangzhou, China)Abstract
This study develops a Lagged Backward-Compatible Physics-Informed Neural Network (LBC-PINN) for simulating and inverting one-dimensional unsaturated soil consolidation under long-term loading. To address the challenges of coupled air and water pressure dissipation across multi-scale time domains, the framework integrates logarithmic time segmentation, lagged compatibility loss enforcement, and segment-wise transfer learning. In forward analysis, the LBC-PINN with recommended segmentation schemes accurately predicts pore air and pore water pressure evolution. Model predictions are validated against finite element method (FEM) results, with mean absolute errors below 1e-2 for time durations up to 1e10 seconds. A simplified segmentation strategy based on the characteristic air-phase dissipation time improves computational efficiency while preserving predictive accuracy. Sensitivity analyses confirm the robustness of the framework across air-to-water permeability ratios ranging from 1e-3 to 1e3.
Abstract (translated)
这项研究开发了一种滞后兼容的物理信息神经网络（LBC-PINN），用于模拟和反演长期加载条件下的单相非饱和土体固结过程。为了应对跨多尺度时间域内的气水压力消散耦合挑战，该框架集成了对数时间分割、滞后一致性损失强制执行以及分段式迁移学习技术。在正向分析中，推荐的分割方案下LBC-PINN能够准确预测孔隙空气和孔隙水压力的变化过程。模型预测结果通过有限元方法（FEM）验证，在长达1e10秒的时间范围内平均绝对误差小于1e-2。基于特征气相消散时间的一种简化分割策略提高了计算效率，同时保持了预测准确性。敏感性分析证实该框架在空气与水渗透率比值范围从1e-3到1e3的情况下具有鲁棒性。
URL
https://arxiv.org/abs/2602.07031
PDF
-
AR-MAP: Are Autoregressive Large Language Models Implicit Teachers for Diffusion Large Language Models?
2026-02-02 14:48:40Liang Lin, Feng Xiong, Zengbin Wang, Kun Wang, Junhao Dong, Xuecai Hu, Yong Wang, Xiangxiang ChuAbstract
Diffusion Large Language Models (DLLMs) have emerged as a powerful alternative to autoregressive models, enabling parallel token generation across multiple positions. However, preference alignment of DLLMs remains challenging due to high variance introduced by Evidence Lower Bound (ELBO)-based likelihood estimation. In this work, we propose AR-MAP, a novel transfer learning framework that leverages preference-aligned autoregressive LLMs (AR-LLMs) as implicit teachers for DLLM alignment. We reveal that DLLMs can effectively absorb alignment knowledge from AR-LLMs through simple weight scaling, exploiting the shared architectural structure between these divergent generation paradigms. Crucially, our approach circumvents the high variance and computational overhead of direct DLLM alignment and comprehensive experiments across diverse preference alignment tasks demonstrate that AR-MAP achieves competitive or superior performance compared to existing DLLM-specific alignment methods, achieving 69.08\% average score across all tasks and models. Our Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2602.02178
PDF
-
PIMCST: Physics-Informed Multi-Phase Consensus and Spatio-Temporal Few-Shot Learning for Traffic Flow Forecasting
2026-02-02 10:40:07Abdul Joseph Fofanah, Lian Wen, David ChenAbstract
Accurate traffic flow prediction remains a fundamental challenge in intelligent transportation systems, particularly in cross-domain, data-scarce scenarios where limited historical data hinders model training and generalisation. The complex spatio-temporal dependencies and nonlinear dynamics of urban mobility networks further complicate few-shot learning across different cities. This paper proposes MCPST, a novel Multi-phase Consensus Spatio-Temporal framework for few-shot traffic forecasting that reconceptualises traffic prediction as a multi-phase consensus learning problem. Our framework introduces three core innovations: (1) a multi-phase engine that models traffic dynamics through diffusion, synchronisation, and spectral embeddings for comprehensive dynamic characterisation; (2) an adaptive consensus mechanism that dynamically fuses phase-specific predictions while enforcing consistency; and (3) a structured meta-learning strategy for rapid adaptation to new cities with minimal data. We establish extensive theoretical guarantees, including representation theorems with bounded approximation errors and generalisation bounds for few-shot adaptation. Through experiments on four real-world datasets, MCPST outperforms fourteen state-of-the-art methods in spatio-temporal graph learning methods, dynamic graph transfer learning methods, prompt-based spatio-temporal prediction methods and cross-domain few-shot settings, improving prediction accuracy while reducing required training data and providing interpretable insights. The implementation code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2602.01936
PDF
-
AgroFlux: A Spatial-Temporal Benchmark for Carbon and Nitrogen Flux Prediction in Agricultural Ecosystems
2026-02-02 04:04:07Qi Cheng, Licheng Liu, Yao Zhang, Mu Hong, Yiqun Xie, Xiaowei JiaAbstract
Agroecosystem, which heavily influenced by human actions and accounts for a quarter of global greenhouse gas emissions (GHGs), plays a crucial role in mitigating global climate change and securing environmental sustainability. However, we can't manage what we can't measure. Accurately quantifying the pools and fluxes in the carbon, nutrient, and water nexus of the agroecosystem is therefore essential for understanding the underlying drivers of GHG and developing effective mitigation strategies. Conventional approaches like soil sampling, process-based models, and black-box machine learning models are facing challenges such as data sparsity, high spatiotemporal heterogeneity, and complex subsurface biogeochemical and physical processes. Developing new trustworthy approaches such as AI-empowered models, will require the AI-ready benchmark dataset and outlined protocols, which unfortunately do not exist. In this work, we introduce a first-of-its-kind spatial-temporal agroecosystem GHG benchmark dataset that integrates physics-based model simulations from Ecosys and DayCent with real-world observations from eddy covariance flux towers and controlled-environment facilities. We evaluate the performance of various sequential deep learning models on carbon and nitrogen flux prediction, including LSTM-based models, temporal CNN-based model, and Transformer-based models. Furthermore, we explored transfer learning to leverage simulated data to improve the generalization of deep learning models on real-world observations. Our benchmark dataset and evaluation framework contribute to the development of more accurate and scalable AI-driven agroecosystem models, advancing our understanding of ecosystem-climate interactions.
Abstract (translated)
URL
https://arxiv.org/abs/2602.01614
PDF
-
Hybrid Topological and Deep Feature Fusion for Accurate MRI-Based Alzheimer's Disease Severity Classification
2026-02-01 01:28:17Faisal AhmedAbstract
Early and accurate diagnosis of Alzheimer's disease (AD) remains a critical challenge in neuroimaging-based clinical decision support systems. In this work, we propose a novel hybrid deep learning framework that integrates Topological Data Analysis (TDA) with a DenseNet121 backbone for four-class Alzheimer's disease classification using structural MRI data from the OASIS dataset. TDA is employed to capture complementary topological characteristics of brain structures that are often overlooked by conventional neural networks, while DenseNet121 efficiently learns hierarchical spatial features from MRI slices. The extracted deep and topological features are fused to enhance class separability across the four AD stages. Extensive experiments conducted on the OASIS-1 Kaggle MRI dataset demonstrate that the proposed TDA+DenseNet121 model significantly outperforms existing state-of-the-art approaches. The model achieves an accuracy of 99.93% and an AUC of 100%, surpassing recently published CNN-based, transfer learning, ensemble, and multi-scale architectures. These results confirm the effectiveness of incorporating topological insights into deep learning pipelines and highlight the potential of the proposed framework as a robust and highly accurate tool for automated Alzheimer's disease diagnosis.
Abstract (translated)
URL
https://arxiv.org/abs/2602.00956
PDF
-
ILSIC: Corpora for Identifying Indian Legal Statutes from Queries by Laypeople
2026-01-31 20:05:48Shounak Paul, Raghav Dogra, Pawan Goyal, Saptarshi GhoshAbstract
Legal Statute Identification (LSI) for a given situation is one of the most fundamental tasks in Legal NLP. This task has traditionally been modeled using facts from court judgments as input queries, due to their abundance. However, in practical settings, the input queries are likely to be informal and asked by laypersons, or non-professionals. While a few laypeople LSI datasets exist, there has been little research to explore the differences between court and laypeople data for LSI. In this work, we create ILSIC, a corpus of laypeople queries covering 500+ statutes from Indian law. Additionally, the corpus also contains court case judgements to enable researchers to effectively compare between court and laypeople data for LSI. We conducted extensive experiments on our corpus, including benchmarking over the laypeople dataset using zero and few-shot inference, retrieval-augmented generation and supervised fine-tuning. We observe that models trained purely on court judgements are ineffective during test on laypeople queries, while transfer learning from court to laypeople data can be beneficial in certain scenarios. We also conducted fine-grained analyses of our results in terms of categories of queries and frequency of statutes.
Abstract (translated)
URL
https://arxiv.org/abs/2602.00881
PDF
-
Disentangling multispecific antibody function with graph neural networks
2026-01-30 17:36:19Joshua Southern, Changpeng Lu, Santrupti Nerli, Samuel D. Stanton, Andrew M. Watkins, Franziska Seeger, Fr\'ed\'eric A. DreyerAbstract
Multispecific antibodies offer transformative therapeutic potential by engaging multiple epitopes simultaneously, yet their efficacy is an emergent property governed by complex molecular architectures. Rational design is often bottlenecked by the inability to predict how subtle changes in domain topology influence functional outcomes, a challenge exacerbated by the scarcity of comprehensive experimental data. Here, we introduce a computational framework to address part of this gap. First, we present a generative method for creating large-scale, realistic synthetic functional landscapes that capture non-linear interactions where biological activity depends on domain connectivity. Second, we propose a graph neural network architecture that explicitly encodes these topological constraints, distinguishing between format configurations that appear identical to sequence-only models. We demonstrate that this model, trained on synthetic landscapes, recapitulates complex functional properties and, via transfer learning, has the potential to achieve high predictive accuracy on limited biological datasets. We showcase the model's utility by optimizing trade-offs between efficacy and toxicity in trispecific T-cell engagers and retrieving optimal common light chains. This work provides a robust benchmarking environment for disentangling the combinatorial complexity of multispecifics, accelerating the design of next-generation therapeutics.
Abstract (translated)
URL
https://arxiv.org/abs/2601.23212
PDF
-
Deep Learning Based CNN Model for Automated Detection of Pneumonia from Chest XRay Images
2026-01-30 15:05:40Sathish Krishna Anumula, Vetrivelan Tamilmani, Aniruddha Arjun Singh, Dinesh Rajendran, Venkata Deepak NamburiAbstract
Pneumonia has been one of the major causes of morbidities and mortality in the world and the prevalence of this disease is disproportionately high among the pediatric and elderly populations especially in resources trained areas Fast and precise diagnosis is a prerequisite for successful clinical intervention but due to inter observer variation fatigue among experts and a shortage of qualified radiologists traditional approaches that rely on manual interpretation of chest radiographs are frequently constrained To address these problems this paper introduces a unified automated diagnostic model using a custom Convolutional Neural Network CNN that can recognize pneumonia in chest Xray images with high precision and at minimal computational expense In contrast like other generic transfer learning based models which often possess redundant parameters the offered architecture uses a tailor made depth wise separable convolutional design which is optimized towards textural characteristics of grayscale medical images Contrast Limited Adaptive Histogram Equalization CLAHE and geometric augmentation are two significant preprocessing techniques used to ensure that the system does not experience class imbalance and is more likely to generalize The system is tested using a dataset of 5863 anterior posterior chest Xrays.
Abstract (translated)
URL
https://arxiv.org/abs/2602.00212
PDF
