RNN
-
Span Modeling for Idiomaticity and Figurative Language Detection with Span Contrastive Loss
2026-03-24 04:45:52Blake Matheny, Phuong Minh Nguyen, Minh Le NguyenAbstract
The category of figurative language contains many varieties, some of which are non-compositional in nature. This type of phrase or multi-word expression (MWE) includes idioms, which represent a single meaning that does not consist of the sum of its words. For language models, this presents a unique problem due to tokenization and adjacent contextual embeddings. Many large language models have overcome this issue with large phrase vocabulary, though immediate recognition frequently fails without one- or few-shot prompting or instruction finetuning. The best results have been achieved with BERT-based or LSTM finetuning approaches. The model in this paper contains one such variety. We propose BERT- and RoBERTa-based models finetuned with a combination of slot loss and span contrastive loss (SCL) with hard negative reweighting to improve idiomaticity detection, attaining state of the art sequence accuracy performance on existing datasets. Comparative ablation studies show the effectiveness of SCL and its generalizability. The geometric mean of F1 and sequence accuracy (SA) is also proposed to assess a model's span awareness and general performance together.
Abstract (translated)
比喻性语言包含多种变体，其中部分具有非组合性本质。这类短语或多词表达（MWE）包含习语，其整体含义并非词汇意义的简单叠加。对于语言模型而言，由于分词机制和相邻上下文嵌入的影响，这构成了独特挑战。许多大语言模型通过扩充短语词汇库克服了该问题，但若无小样本提示或指令微调，即时识别仍常会失败。目前最佳成果多基于BERT或LSTM微调方法实现。本文模型即属此类变体之一。我们提出基于BERT和RoBERTa的模型，通过结合槽位损失与带困难负样本重加权的跨度对比损失（SCL）进行微调，以提升习语性检测能力，并在现有数据集上达到最优序列准确率性能。对比消融实验验证了SCL的有效性及其泛化能力。此外，我们提出采用F1值与序列准确率（SA）的几何平均数，以综合评估模型的跨度感知能力与整体性能。
URL
https://arxiv.org/abs/2603.22799
PDF
-
An Intelligent Framework for Real-Time Yoga Pose Detection and Posture Correction
2026-03-23 17:37:59Chandramouli HaldarAbstract
Yoga is widely recognized for improving physical fitness, flexibility, and mental well being. However, these benefits depend strongly on correct posture execution. Improper alignment during yoga practice can reduce effectiveness and increase the risk of musculoskeletal injuries, especially in self guided or online training environments. This paper presents a hybrid Edge AI based framework for real time yoga pose detection and posture correction. The proposed system integrates lightweight human pose estimation models with biomechanical feature extraction and a CNN LSTM based temporal learning architecture to recognize yoga poses and analyze motion dynamics. Joint angles and skeletal features are computed from detected keypoints and compared with reference pose configurations to evaluate posture correctness. A quantitative scoring mechanism is introduced to measure alignment deviations and generate real time corrective feedback through visual, text based, and voice based guidance. In addition, Edge AI optimization techniques such as model quantization and pruning are applied to enable low latency performance on resource constrained devices. The proposed framework provides an intelligent and scalable digital yoga assistant that can improve user safety and training effectiveness in modern fitness applications.
Abstract (translated)
瑜伽被广泛认可能够提升体能、柔韧性和心理健康。然而，这些益处很大程度上取决于正确的姿势执行。在瑜伽练习中，若身体排列不当，不仅会降低练习效果，还会增加肌肉骨骼损伤的风险，尤其在自主练习或在线训练环境中更为明显。本文提出一种基于混合边缘AI的实时瑜伽姿势检测与矫正框架。该系统融合轻量级人体姿态估计模型、生物力学特征提取以及基于CNN-LSTM的时序学习架构，用于识别瑜伽姿势并分析动作动态。通过从检测到的关键点计算关节角度与骨骼特征，并与标准姿势配置进行对比，从而评估姿势正确性。研究引入定量评分机制，通过测量对齐偏差，并借助视觉、文本及语音引导生成实时矫正反馈。此外，系统应用模型量化与剪枝等边缘AI优化技术，实现在资源受限设备上的低延迟运行。该框架可作为智能且可扩展的数字瑜伽助手，提升现代健身应用中的用户安全与训练效果。
URL
https://arxiv.org/abs/2603.26760
PDF
-
When and Where: A Model Hippocampal Network Unifies Formation of Time Cells and Place Cells
2026-03-22 22:52:27Qiaorong S. Yu, Zhaoze Wang, Vijay BalasubramanianAbstract
Hippocampal place and time cells encode spatial and temporal aspects of experience. Both have the same neural substrate, but have been modeled as having different functions and mechanistic origins, place cells as continuous attractors, and time cells as leaky integrators. Here, we show that both types emerge from two dynamical regimes of a single recurrent network (RNN) modeling hippocampal CA3 as a predictive autoencoder. The network receives simulated, partially occluded ``experience vectors" containing spatial patterns (location-specific activity sampled during environmental traversal) and/or temporal patterns (correlated activity pairs separated by ``void" intervals), and is trained to reconstruct missing input. During spatial navigation, the network generates stable attractor-like place fields. But trained on temporally structured inputs, the network produces sequentially broadened fields, recapitulating time cells. By varying spatio-temporal input patterning, we observe hidden units transition smoothly between time cell-like and place cell-like representations. These results suggest a shared origin, but task-driven difference, between place and time cells.
Abstract (translated)
海马体的位置细胞和时间细胞分别编码经验的时空方面。两者具有相同的神经基质，但传统上被建模为具有不同的功能和机制起源：位置细胞作为连续吸引子，时间细胞作为渗漏积分器。在此，我们证明这两种细胞类型均源于一个单一循环神经网络（RNN）的两种动态机制，该网络将海马CA3区建模为预测自编码器。该网络接收模拟的、部分遮挡的“经验向量”，其中包含空间模式（环境遍历期间采样的位置特异性活动）和/或时间模式（由“空隔”间隔分隔的相关活动对），并被训练以重建缺失的输入。在空间导航过程中，网络产生稳定的类吸引子位置场。但在接受时间结构输入训练后，网络产生序列展宽的场，重现了时间细胞特征。通过改变时空输入模式，我们观察到隐藏单元在时间细胞样与位置细胞样表征之间平滑过渡。这些结果提示位置细胞和时间细胞具有共同起源，但受任务驱动产生差异。
URL
https://arxiv.org/abs/2604.00036
PDF
-
Fusing Memory and Attention: A study on LSTM, Transformer and Hybrid Architectures for Symbolic Music Generation
2026-03-22 15:14:17Soudeep Ghoshal, Sandipan Chakraborty, Pradipto Chowdhury, Himanshu BuckchashAbstract
Machine learning techniques, such as Transformers and Long Short-Term Memory (LSTM) networks, play a crucial role in Symbolic Music Generation (SMG). Existing literature indicates a difference between LSTMs and Transformers regarding their ability to model local melodic continuity versus maintaining global structural coherence. However, their specific properties within the context of SMG have not been systematically studied. This paper addresses this gap by providing a fine-grained comparative analysis of LSTMs versus Transformers for SMG, examining local and global properties in detail using 17 musical quality metrics on the Deutschl dataset. We find that LSTM networks excel at capturing local patterns but fail to preserve long-range dependencies, while Transformers model global structure effectively but tend to produce irregular phrasing. Based on this analysis and leveraging their respective strengths, we propose a Hybrid architecture combining a Transformer Encoder with an LSTM Decoder and evaluate it against both baselines. We evaluated 1,000 generated melodies from each of the three architectures on the Deutschl dataset. The results show that the hybrid method achieves better local and global continuity and coherence compared to the baselines. Our work highlights the key characteristics of these models and demonstrates how their properties can be leveraged to design superior models. We also supported the experiments with ablation studies and human perceptual evaluations, which statistically support the findings and provide robust validation for this work.
Abstract (translated)
在符号音乐生成（SMG）领域，Transformer和长短期记忆（LSTM）网络等机器学习技术发挥着关键作用。现有文献表明，LSTM与Transformer在建模局部旋律连贯性与保持全局结构一致性方面存在差异，但二者在SMG场景下的具体特性尚未得到系统研究。本文通过细粒度对比分析填补这一空白，使用17项音乐质量指标在Deutschl数据集上详细检验了LSTM与Transformer的局部与全局特性。研究发现：LSTM网络擅长捕捉局部模式却难以保持长程依赖，而Transformer能有效建模全局结构但易产生不规则的乐句划分。基于此分析并融合二者优势，我们提出了结合Transformer编码器与LSTM解码器的混合架构，并与两种基线模型进行对比评估。在Deutschl数据集上对三种架构生成的1000段旋律进行评估后，结果显示混合方法在局部与全局的连贯性和一致性上均优于基线模型。本研究揭示了这些模型的关键特性，并展示了如何利用其属性设计更优模型。此外，通过消融实验和人类感知评估对实验进行了辅助验证，统计结果支持研究发现，为本工作提供了稳健的实证依据。
URL
https://arxiv.org/abs/2603.21282
PDF
-
Evaluating Factor-Wise Auxiliary Dynamics Supervision for Latent Structure and Robustness in Simulated Humanoid Locomotion
Abstract
We evaluate whether factor-wise auxiliary dynamics supervision produces useful latent structure or improved robustness in simulated humanoid locomotion. DynaMITE -- a transformer encoder with a factored 24-d latent trained by per-factor auxiliary losses during proximal policy optimization (PPO) -- is compared against Long Short-Term Memory (LSTM), plain Transformer, and Multilayer Perceptron (MLP) baselines on a Unitree G1 humanoid across four Isaac Lab tasks. The supervised latent shows no evidence of decodable or functionally separable factor structure: probe R^2 ~ 0 for all five dynamics factors, clamping any subspace changes reward by < 0.05, and standard disentanglement metrics (MIG, DCI, SAP) are near zero. An unsupervised LSTM hidden state achieves higher probe R^2 (up to 0.10). A 2x2 factorial ablation (n = 10 seeds) isolates the contributions of the tanh bottleneck and auxiliary losses: the auxiliary losses show no measurable effect on either in-distribution (ID) reward (+0.03, p = 0.732) or severe out-of-distribution (OOD) reward (+0.03, p = 0.669), while the bottleneck shows a small, consistent advantage in both regimes (ID: +0.16, p = 0.207; OOD: +0.10, p = 0.208). The bottleneck advantage persists under severe combined perturbation but does not amplify, indicating a training-time representation benefit rather than a robustness mechanism. LSTM achieves the best nominal reward on all four tasks (p < 0.03); DynaMITE degrades less under combined-shift stress (2.3% vs. 16.7%), but this difference is attributable to the bottleneck compression, not the auxiliary supervision. For locomotion practitioners: auxiliary dynamics supervision does not produce an interpretable estimator and does not measurably improve reward or robustness beyond what the bottleneck alone provides; recurrent baselines remain the stronger choice for nominal performance.
Abstract (translated)
URL
https://arxiv.org/abs/2603.21268
PDF
-
GraPHFormer: A Multimodal Graph Persistent Homology Transformer for the Analysis of Neuroscience Morphologies
2026-03-21 22:47:24Uzair Shah, Marco Agus, Mahmoud Gamal, Mahmood Alzubaidi, Corrado Cali, Pierre J. Magistretti, Abdesselam Bouzerdoum, Mowafa HousehAbstract
Neuronal morphology encodes critical information about circuit function, development, and disease, yet current methods analyze topology or graph structure in isolation. We introduce GraPHFormer, a multimodal architecture that unifies these complementary views through CLIP-style contrastive learning. Our vision branch processes a novel three-channel persistence image encoding unweighted, persistence-weighted, and radius-weighted topological densities via DINOv2-ViT-S. In parallel, a TreeLSTM encoder captures geometric and radial attributes from skeleton graphs. Both project to a shared embedding space trained with symmetric InfoNCE loss, augmented by persistence-space transformations that preserve topological semantics. Evaluated on six benchmarks (BIL-6, ACT-4, JML-4, N7, M1-Cell, M1-REG) spanning self-supervised and supervised settings, GraPHFormer achieves state-of-the-art performance on five benchmarks, significantly outperforming topology-only, graph-only, and morphometrics baselines. We demonstrate practical utility by discriminating glial morphologies across cortical regions and species, and detecting signatures of developmental and degenerative processes. Code: this https URL
Abstract (translated)
神经元形态蕴含了关于神经回路功能、发育和疾病的关键信息，然而当前方法仅孤立地分析拓扑结构或图结构。我们提出了GraPHFormer，一种通过CLIP式对比学习统一这些互补视角的多模态架构。我们的视觉分支通过DINOv2-ViT-S处理一种新型的三通道持续图像，该图像编码了无权重、持续权重和半径权重的拓扑密度。同时，TreeLSTM编码器从骨架图中捕获几何和径向属性。两者均投影到一个共享的嵌入空间，该空间使用对称InfoNCE损失进行训练，并辅以保持拓扑语义的持续空间变换。在涵盖自监督和监督设置的六个基准测试（BIL-6、ACT-4、JML-4、N7、M1-Cell、M1-REG）上评估，GraPHFormer在五个基准测试中实现了最先进的性能，显著超越了仅拓扑、仅图和形态测量基线。我们通过跨皮层区域和物种区分胶质细胞形态，以及检测发育和退化过程的特征，展示了其实用价值。代码：此https URL
URL
https://arxiv.org/abs/2603.20970
PDF
-
Detecting Neurovascular Instability from Multimodal Physiological Signals Using Wearable-Compatible Edge AI: A Responsible Computational Framework
2026-03-20 19:17:46Truong Quynh Hoa, Hoang Dinh Cuong, Truong Xuan KhanhAbstract
We propose Melaguard, a multimodal ML framework (Transformer-lite, 1.2M parameters, 4-head self-attention) for detecting neurovascular instability (NVI) from wearable-compatible physiological signals prior to structural stroke pathology. The model fuses heart rate variability (HRV), peripheral perfusion index, SpO2, and bilateral phase coherence into a composite NVI Score, designed for edge inference (WCET <=4 ms on Cortex-M4). NVI - the pre-structural dysregulation of cerebrovascular autoregulation preceding overt stroke - remains undetectable by existing single-modality wearables. With 12.2 million incident strokes annually, continuous multimodal physiological monitoring offers a practical path to community-scale screening. Three-stage independent validation: (1) synthetic benchmark (n=10,000), AUC=0.88 [0.83-0.92]; (2) clinical cohort PhysioNet CVES (n=172; 84 stroke, 88 control) - Transformer-lite achieves AUC=0.755 [0.630-0.778], outperforming LSTM (0.643), Random Forest (0.665), SVM (0.472); HRV-SDNN discriminates stroke (p=0.011); (3) PPG pipeline PhysioNet BIDMC (n=53) -- pulse rate r=0.748 and HRV surrogate r=0.690 vs. ECG ground truth. Cross-modality validation on PPG-BP (n=219) confirms PPG morphology classifies cerebrovascular disease at AUC=0.923 [0.869-0.968]. Multimodal fusion consistently outperforms single-modality baselines. Code: this https URL
Abstract (translated)
我们提出Melaguard，一个专为从可穿戴兼容生理信号中检测神经血管不稳定性（NVI）而设计的多模态机器学习框架（轻量Transformer，120万参数，4头自注意力），该信号出现在结构性中风病理之前。该模型融合心率变异性（HRV）、外周灌注指数、血氧饱和度（SpO2）和双侧相位相干性，生成复合NVI评分，专为边缘推理设计（在Cortex-M4上最坏情况执行时间≤4毫秒）。NVI——即显性中风之前脑血管自动调节的结构前失调——现有单模态可穿戴设备无法检测。鉴于每年新增1220万中风病例，连续多模态生理监测为社区规模筛查提供了可行路径。三阶段独立验证：(1) 合成基准测试（n=10,000），AUC=0.88 [0.83-0.92]；(2) 临床队列PhysioNet CVES（n=172；84例中风，88例对照）——轻量Transformer达到AUC=0.755 [0.630-0.778]，优于LSTM（0.643）、随机森林（0.665）、支持向量机（0.472）；HRV-SDNN可区分中风（p=0.011）；(3) PPG流水线PhysioNet BIDMC（n=53）——脉搏率r=0.748，HRV替代指标r=0.690（相对于ECG金标准）。在PPG-BP（n=219）上的跨模态验证证实，PPG形态学可分类脑血管疾病，AUC=0.923 [0.869-0.968]。多模态融合持续优于单模态基线。代码：此https链接
URL
https://arxiv.org/abs/2603.20442
PDF
-
Hybrid Associative Memories
2026-03-20 14:12:00Leon Lufkin, Tom\'as Figliolia, Beren Millidge, Kamesh KrishnamurthyAbstract
Recurrent neural networks (RNNs) and self-attention are both widely used sequence-mixing layers that maintain an internal memory. However, this memory is constructed using two orthogonal mechanisms: RNNs compress the entire past into a fixed-size state, whereas self-attention's state stores every past time step growing its state (the KV cache) linearly with the sequence length. This results in orthogonal strengths and weaknesses. Self-attention layers excel at retrieving information in the context but have large memory and computational costs, while RNNs are more efficient but degrade over longer contexts and underperform for precise recall tasks. Prior work combining these mechanisms has focused primarily on naively interleaving them to reduce computational cost without regard to their complementary mechanisms. We propose the Hybrid Associative Memory (HAM) layer, which combines self-attention and RNNs while leveraging their individual strengths: the RNN compresses the entire sequence, while attention supplements it *only* with information that is difficult for the RNN to predict, which is hence the most valuable information to explicitly store. HAM layers enable data-dependent growth of the KV cache, which can be precisely controlled by the user with a single, continuous threshold. We find that this fine-grained control of the KV cache growth rate has a smooth trade-off with loss and performance. Empirically, we show that our hybrid architecture offers strong, competitive performance relative to RNNs and Transformers even at substantially lower KV-cache usage.
Abstract (translated)
循环神经网络（RNN）和自注意力机制都是广泛使用的序列混合层，它们都维持着内部记忆。然而，这种记忆是通过两种正交的机制构建的：RNN将整个过去压缩为固定大小的状态，而自注意力的状态则存储每个过去的时间步，使其状态（KV缓存）随序列长度线性增长。这导致了互补的优缺点。自注意力层在从上下文中检索信息方面表现出色，但具有较大的内存和计算成本；而RNN更高效，但在更长上下文上性能会下降，且在精确回忆任务中表现不佳。先前结合这些机制的工作主要集中在简单地将它们交替使用，以减少计算成本，而忽略了它们互补的机制。我们提出了混合关联记忆（HAM）层，它结合了自注意力和RNN，同时利用它们各自的优势：RNN压缩整个序列，而注意力仅用RNN难以预测的信息来补充它，因此这是最值得显式存储的信息。HAM层实现了KV缓存的数据依赖增长，用户可以通过一个单一的连续阈值进行精确控制。我们发现，对KV缓存增长率的这种细粒度控制与损失和性能之间存在平滑的权衡。实验表明，即使在KV缓存使用率显著降低的情况下，我们的混合架构也提供了与RNN和Transformer相比强大且具有竞争力的性能。
URL
https://arxiv.org/abs/2603.22325
PDF
-
A Multi-Task Targeted Learning Framework for Lithium-Ion Battery State-of-Health and Remaining Useful Life
2026-03-20 12:22:10Chenhan Wang, Zhengyi Bao, Huipin Lin, Jiahao Nie, Chunxiang ZhuAbstract
Accurately predicting the state-of-health (SOH) and remaining useful life (RUL) of lithium-ion batteries is crucial for ensuring the safe and efficient operation of electric vehicles while minimizing associated risks. However, current deep learning methods are limited in their ability to selectively extract features and model time dependencies for these two parameters. Moreover, most existing methods rely on traditional recurrent neural networks, which have inherent shortcomings in long-term time-series modeling. To address these issues, this paper proposes a multi-task targeted learning framework for SOH and RUL prediction, which integrates multiple neural networks, including a multi-scale feature extraction module, an improved extended LSTM, and a dual-stream attention module. First, a feature extraction module with multi-scale CNNs is designed to capture detailed local battery decline patterns. Secondly, an improved extended LSTM network is employed to enhance the model's ability to retain long-term temporal information, thus improving temporal relationship modeling. Building on this, the dual-stream attention module-comprising polarized attention and sparse attention to selectively focus on key information relevant to SOH and RUL, respectively, by assigning higher weights to important features. Finally, a many-to-two mapping is achieved through the dual-task layer. To optimize the model's performance and reduce the need for manual hyperparameter tuning, the Hyperopt optimization algorithm is used. Extensive comparative experiments on battery aging datasets demonstrate that the proposed method reduces the average RMSE for SOH and RUL predictions by 111.3\% and 33.0\%, respectively, compared to traditional and state-of-the-art methods.
Abstract (translated)
准确预测锂离子电池的健康状态（SOH）和剩余使用寿命（RUL）对于确保电动汽车安全高效运行并降低相关风险至关重要。然而，当前深度学习方法在针对这两个参数选择性提取特征和建模时间依赖关系方面存在局限。此外，多数现有方法依赖传统循环神经网络，其在长期时间序列建模中存在固有缺陷。针对上述问题，本文提出一种用于SOH与RUL预测的多任务目标学习框架，该框架集成了多尺度特征提取模块、改进的扩展LSTM以及双流注意力机制等多种神经网络。首先，设计了基于多尺度CNN的特征提取模块，以捕捉电池衰减的详细局部模式。其次，采用改进的扩展LSTM网络增强模型对长期时序信息的保持能力，从而提升时序关系建模效果。在此基础上，双流注意力模块——包含极化注意力和稀疏注意力——通过为重要特征分配更高权重，分别选择性地聚焦于与SOH和RUL相关的关键信息。最后，通过双任务层实现多对二映射。为优化模型性能并减少手动超参数调优需求，采用Hyperopt优化算法。在电池老化数据集上的大量对比实验表明，相较于传统及先进方法，所提方法将SOH和RUL预测的平均RMSE分别降低了111.3%和33.0%。
URL
https://arxiv.org/abs/2603.22323
PDF
-
Beyond Quadratic: Linear-Time Change Detection with RWKV
2026-03-20 03:23:02Zhenyu Yang, Gensheng Pei, Tao Chen, Xia Yuan, Haofeng Zhang, Xiangbo Shu, Yazhou YaoAbstract
Existing paradigms for remote sensing change detection are caught in a trade-off: CNNs excel at efficiency but lack global context, while Transformers capture long-range dependencies at a prohibitive computational cost. This paper introduces ChangeRWKV, a new architecture that reconciles this conflict. By building upon the Receptance Weighted Key Value (RWKV) framework, our ChangeRWKV uniquely combines the parallelizable training of Transformers with the linear-time inference of RNNs. Our approach core features two key innovations: a hierarchical RWKV encoder that builds multi-resolution feature representation, and a novel Spatial-Temporal Fusion Module (STFM) engineered to resolve spatial misalignments across scales while distilling fine-grained temporal discrepancies. ChangeRWKV not only achieves state-of-the-art performance on the LEVIR-CD benchmark, with an 85.46% IoU and 92.16% F1 score, but does so while drastically reducing parameters and FLOPs compared to previous leading methods. This work demonstrates a new, efficient, and powerful paradigm for operational-scale change detection. Our code and model are publicly available.
Abstract (translated)
现有遥感变化检测范式陷入效率与全局信息的权衡困境：CNN效率高但缺乏全局上下文，而Transformer虽能捕捉长程依赖却计算成本高昂。本研究提出ChangeRWKV新架构以化解此矛盾，其基于Receptance Weighted Key Value（RWKV）框架，创新性地融合了Transformer的可并行训练特性与RNN的线性时间复杂度推理能力。该方法核心包含两项关键创新：一是构建多分辨率特征表征的层级化RWKV编码器；二是专为消除跨尺度空间错位并提炼细粒度时序差异而设计的新型时空融合模块（STFM）。ChangeRWKV在LEVIR-CD基准测试中取得85.46%交并比与92.16% F1分数的state-of-the-art性能，同时相较于此前领先方法大幅缩减了参数量与计算量。本研究展示了一种适用于实际应用场景的高效强大变化检测新范式，代码与模型已公开。
URL
https://arxiv.org/abs/2603.19606
PDF
-
Physics-Informed Neural Network with Adaptive Clustering Learning Mechanism for Information Popularity Prediction
2026-03-20 03:16:07Guangyin Jin, Xiaohan Ni, Yanjie Song, Kun Wei, Jie Zhao, Leiming Jia, Witold PedryczAbstract
With society entering the Internet era, the volume and speed of data and information have been increasing. Predicting the popularity of information cascades can help with high-value information delivery and public opinion monitoring on the internet platforms. The current state-of-the-art models for predicting information popularity utilize deep learning methods such as graph convolution networks (GCNs) and recurrent neural networks (RNNs) to capture early cascades and temporal features to predict their popularity increments. However, these previous methods mainly focus on the micro features of information cascades, neglecting their general macroscopic patterns. Furthermore, they also lack consideration of the impact of information heterogeneity on spread popularity. To overcome these limitations, we propose a physics-informed neural network with adaptive clustering learning mechanism, PIACN, for predicting the popularity of information cascades. Our proposed model not only models the macroscopic patterns of information dissemination through physics-informed approach for the first time but also considers the influence of information heterogeneity through an adaptive clustering learning mechanism. Extensive experimental results on three real-world datasets demonstrate that our model significantly outperforms other state-of-the-art methods in predicting information popularity.
Abstract (translated)
随着社会进入互联网时代，数据与信息的体量与传播速度持续增长。预测信息级联的流行度有助于互联网平台实现高价值信息推送与网络舆情监测。当前预测信息流行度的前沿模型多采用图卷积网络（GCNs）与循环神经网络（RNNs）等深度学习方法，通过捕捉早期级联结构与时序特征来预测流行度增量。然而，既有方法主要聚焦于信息级联的微观特征，忽视其宏观普适模式，同时缺乏对信息异质性对传播流行度影响的考量。为突破上述局限，本研究提出一种融合物理信息与自适应聚类学习机制的神经网络模型（PIACN），用于预测信息级联流行度。该模型首次通过物理信息建模方法刻画信息传播的宏观规律，并借助自适应聚类学习机制纳入信息异质性影响。基于三个真实数据集的 extensive 实验表明，本模型在信息流行度预测任务中显著优于其他前沿方法。
URL
https://arxiv.org/abs/2603.19599
PDF
-
A Multi-Modal CNN-LSTM Framework with Multi-Head Attention and Focal Loss for Real-Time Elderly Fall Detection
2026-03-20 03:04:24Lijie Zhou, Luran WangAbstract
The increasing global aging population has intensified the demand for reliable health monitoring systems, particularly those capable of detecting critical events such as falls among elderly individuals. Traditional fall detection approaches relying on single-modality acceleration data suffer from high false alarm rates, while conventional machine learning methods require extensive hand-crafted feature engineering. This paper proposes a novel multi-modal deep learning framework, MultiModalFallDetector, designed for real-time elderly fall detection using wearable sensors. Our approach integrates multiple innovations: a multi-scale CNN-based feature extractor capturing motion dynamics at varying temporal resolutions; fusion of tri-axial accelerometer, gyroscope, and four-channel physiological signals; incorporation of a multi-head self-attention mechanism for dynamic temporal weighting; adoption of Focal Loss to mitigate severe class imbalance; introduction of an auxiliary activity classification task for regularization; and implementation of transfer learning from UCI HAR to SisFall dataset. Extensive experiments on the SisFall dataset, which includes real-world simulated fall trials from elderly participants (aged 60-85), demonstrate that our framework achieves an F1-score of 98. 7, Recall of 98. 9, and AUC-ROC of 99. 4, significantly outperforming baseline methods including traditional machine learning and standard deep learning approaches. The model maintains sub- 50ms inference latency on edge devices, confirming its suitability for real-time deployment in geriatric care settings.
Abstract (translated)
全球老龄化人口的增长加剧了对可靠健康监测系统的需求，尤其是能够检测老年人跌倒等关键事件的系统。传统依赖单一模态加速度数据的跌倒检测方法误报率较高，而常规机器学习方法则需要大量手工特征工程。本研究提出一种新颖的多模态深度学习框架MultiModalFallDetector，专为使用可穿戴传感器进行实时老年人跌倒检测而设计。该方法整合了多项创新：基于多尺度CNN的特征提取器，可捕获不同时间分辨率的运动动态；融合三轴加速度计、陀螺仪和四通道生理信号；引入多头自注意力机制实现动态时间加权；采用Focal Loss缓解严重的类别不平衡问题；引入辅助活动分类任务进行正则化；并实施从UCI HAR数据集到SisFall数据集的迁移学习。在包含60-85岁老年参与者真实模拟跌倒试验的SisFall数据集上进行的大量实验表明，本框架的F1分数达98.7，召回率达98.9，AUC-ROC值达99.4，显著优于包括传统机器学习和标准深度学习方法在内的基线方案。该模型在边缘设备上保持低于50毫秒的推理延迟，证实其适用于老年护理场景的实时部署。
URL
https://arxiv.org/abs/2603.22313
PDF
-
myMNIST: Benchmark of PETNN, KAN, and Classical Deep Learning Models for Burmese Handwritten Digit Recognition
2026-03-19 08:10:41Ye Kyaw Thu, Thazin Myint Oo, Thepchai SupnithiAbstract
We present the first systematic benchmark on myMNIST (formerly BHDD), a publicly available Burmese handwritten digit dataset important for Myanmar NLP/AI research. We evaluate eleven architectures spanning classical deep learning models (Multi-Layer Perceptron, Convolutional Neural Network, Long Short-Term Memory, Gated Recurrent Unit, Transformer), recent alternatives (FastKAN, EfficientKAN), an energy-based model (JEM), and physics-inspired PETNN variants (Sigmoid, GELU, SiLU). Using Precision, Recall, F1-Score, and Accuracy as evaluation metrics, our results show that the CNN remains a strong baseline, achieving the best overall scores (F1 = 0.9959, Accuracy = 0.9970). The PETNN (GELU) model closely follows (F1 = 0.9955, Accuracy = 0.9966), outperforming LSTM, GRU, Transformer, and KAN variants. JEM, representing energy-based modeling, performs competitively (F1 = 0.9944, Accuracy = 0.9958). KAN-based models (FastKAN, EfficientKAN) trail the top performers but provide a meaningful alternative baseline (Accuracy ~0.992). These findings (i) establish reproducible baselines for myMNIST across diverse modeling paradigms, (ii) highlight PETNN's strong performance relative to classical and Transformer-based models, and (iii) quantify the gap between energy-inspired PETNNs and a true energy-based model (JEM). We release this benchmark to facilitate future research on Myanmar digit recognition and to encourage broader evaluation of emerging architectures on regional scripts.
Abstract (translated)
URL
https://arxiv.org/abs/2603.18597
PDF
-
HEP Statistical Inference for UAV Fault Detection: CLs, LRT, and SBI Applied to Blade Damage
Abstract
This paper transfers three statistical methods from particle physics to multirotor propeller fault detection: the likelihood ratio test (LRT) for binary detection, the CLs modified frequentist method for false alarm rate control, and sequential neural posterior estimation (SNPE) for quantitative fault characterization. Operating on spectral features tied to rotor harmonic physics, the system returns three outputs: binary detection, controlled false alarm rates, and calibrated posteriors over fault severity and motor location. On UAV-FD, a hexarotor dataset of 18 real flights with 5% and 10% blade damage, leave-one-flight-out cross-validation gives AUC 0.862 +/- 0.007 (95% CI: 0.849--0.876), outperforming CUSUM (0.708 +/- 0.010), autoencoder (0.753 +/- 0.009), and LSTM autoencoder (0.551). At 5% false alarm rate the system detects 93% of significant and 81% of subtle blade damage. On PADRE, a quadrotor platform, AUC reaches 0.986 after refitting only the generative models. SNPE gives a full posterior over fault severity (90% credible interval coverage 92--100%, MAE 0.012), so the output includes uncertainty rather than just a point estimate or fault flag. Per-flight sequential detection achieves 100% fault detection with 94% overall accuracy.
Abstract (translated)
本文将粒子物理学中的三种统计方法迁移至多旋翼无人机螺旋桨故障检测：用于二元检测的似然比检验（LRT）、用于虚警率控制的CLs修正频率主义方法，以及用于定量故障表征的序列神经后验估计（SNPE）。系统基于与旋翼谐波物理相关的频谱特征运行，输出三个结果：二元检测、可控虚警率以及关于故障严重程度和电机位置的校准后验分布。在UAV-FD（包含18次真实飞行、5%和10%桨叶损伤的六旋翼数据集）上，采用留一飞行交叉验证，AUC达到0.862±0.007（95%置信区间：0.849–0.876），优于CUSUM（0.708±0.010）、自编码器（0.753±0.009）和LSTM自编码器（0.551）。在5%虚警率下，系统可检测到93%的显著桨叶损伤和81%的细微桨叶损伤。在四旋翼平台PADRE上，仅需重新拟合生成模型后，AUC即可达到0.986。SNPE提供了关于故障严重程度的完整后验分布（90%可信区间覆盖率为92%–100%，平均绝对误差0.012），因此输出包含不确定性信息，而不仅仅是点估计或故障标志。逐飞行序列检测实现了100%的故障检测率，整体准确率达94%。
URL
https://arxiv.org/abs/2603.18546
PDF
-
PAI: Fast, Accurate, and Full Benchmark Performance Projection with AI
2026-03-18 19:34:32Avery Johnson, Mohammad Majharul Islam, Riad Akram, Abdullah MuzahidAbstract
The exponential increase in complex IPs within modern SoCs, driven by Moore's Law, has created a pressing need for fast and accurate hardware-software power-performance analysis. Traditional performance simulators (such as cycle accurate simulators) are often too slow to simulate full benchmarks within a reasonable timeframe; require considerable effort for development, maintenance, and extensions; and are prone to errors, making pre-silicon performance projections and competitive analysis increasingly challenging. Prior attempts in addressing this challenge using machine learning fall short as they are either slow, inaccurate or unable to predict the performance of full benchmarks. To address these limitations, we present PAI, the first technique to accurately predict full benchmark performance without relying on detailed simulation or instruction-wise encoding. At the heart of PAI is a hierarchical Long Short Term Memory (LSTM)-based model that takes a trace of microarchitecture independent features from a program execution and predicts performance metrics. We present the detailed design, implementation and evaluation of PAI. Our initial experiments showed that PAI can achieve an average IPC prediction error of 9.35% for SPEC CPU 2017 benchmark suite while taking only 2 min 57 sec for the entire suite. This prediction error is comparable to prior state-of-the-art techniques while requiring 3 orders of magnitude less time.
Abstract (translated)
摩尔定律推动下现代SoC中复杂IP数量的指数级增长，催生了快速精准的软硬件功耗性能分析需求。传统性能模拟器（如周期精确模拟器）往往因模拟完整基准测试耗时过长而难以在合理时间内完成；其开发、维护与扩展需要大量投入，且容易产生误差，使得硅前性能预测与竞品分析愈发困难。此前尝试用机器学习解决该挑战的方法均存在不足：要么速度慢，要么精度低，要么无法预测完整基准测试性能。为突破这些限制，本文提出PAI——首个无需依赖详细模拟或指令级编码即可准确预测完整基准测试性能的技术。PAI的核心是一个基于分层长短期记忆网络（LSTM）的模型，该模型通过提取程序执行中与微架构无关的特征轨迹来预测性能指标。本文详细阐述了PAI的设计、实现与评估过程。初步实验表明，PAI在SPEC CPU 2017基准测试套件上平均IPC预测误差仅为9.35%，而处理整个套件仅需2分57秒。该预测误差与现有顶尖技术相当，但耗时减少了三个数量级。
URL
https://arxiv.org/abs/2603.19330
PDF
-
Consistency-Driven Dual LSTM Models for Kinematic Control of a Wearable Soft Robotic Arm
Abstract
In this paper, we introduce a consistency-driven dual LSTM framework for accurately learning both the forward and inverse kinematics of a pneumatically actuated soft robotic arm integrated into a wearable device. This approach effectively captures the nonlinear and hysteretic behaviors of soft pneumatic actuators while addressing the one-to-many mapping challenge between actuation inputs and end-effector positions. By incorporating a cycle consistency loss, we enhance physical realism and improve the stability of inverse predictions. Extensive experiments-including trajectory tracking, ablation studies, and wearable demonstrations-confirm the effectiveness of our method. Results indicate that the inclusion of the consistency loss significantly boosts prediction accuracy and promotes physical consistency over conventional approaches. Moreover, the wearable soft robotic arm demonstrates strong human-robot collaboration capabilities and adaptability in everyday tasks such as object handover, obstacle-aware pick-and-place, and drawer operation. This work underscores the promising potential of learning-based kinematic models for human-centric, wearable robotic systems.
Abstract (translated)
URL
https://arxiv.org/abs/2603.17672
PDF
-
Unifying Optimization and Dynamics to Parallelize Sequential Computation: A Guide to Parallel Newton Methods for Breaking Sequential Bottlenecks
Abstract
Massively parallel hardware (GPUs) and long sequence data have made parallel algorithms essential for machine learning at scale. Yet dynamical systems, like recurrent neural networks and Markov chain Monte Carlo, were thought to suffer from sequential bottlenecks. Recent work showed that dynamical systems can in fact be parallelized across the sequence length by reframing their evaluation as a system of nonlinear equations, which can be solved with Newton's method using a parallel associative scan. However, these parallel Newton methods struggled with limitations, primarily inefficiency, instability, and lack of convergence guarantees. This thesis addresses these limitations with methodological and theoretical contributions, drawing particularly from optimization. Methodologically, we develop scalable and stable parallel Newton methods, based on quasi-Newton and trust-region approaches. The quasi-Newton methods are faster and more memory efficient, while the trust-region approaches are significantly more stable. Theoretically, we unify many fixed-point methods into our parallel Newton framework, including Picard and Jacobi iterations. We establish a linear convergence rate for these techniques that depends on the method's approximation accuracy and stability. Moreover, we give a precise condition, rooted in dynamical stability, that characterizes when parallelization provably accelerates a dynamical system and when it cannot. Specifically, the sign of the Largest Lyapunov Exponent of a dynamical system determines whether or not parallel Newton methods converge quickly. In sum, this thesis unlocks scalable and stable methods for parallelizing sequential computation, and provides a firm theoretical basis for when such techniques will and will not work. This thesis also serves as a guide to parallel Newton methods for researchers who want to write the next chapter in this ongoing story.
Abstract (translated)
URL
https://arxiv.org/abs/2603.16850
PDF
-
Beyond Accuracy: Evaluating Forecasting Models by Multi-Echelon Inventory Cost
2026-03-17 17:19:34Swata Marik, Swayamjit Saha, Garga ChatterjeeAbstract
This study develops a digitalized forecasting-inventory optimization pipeline integrating traditional forecasting models, machine learning regressors, and deep sequence models within a unified inventory simulation framework. Using the M5 Walmart dataset, we evaluate seven forecasting approaches and assess their operational impact under single- and two-echelon newsvendor systems. Results indicate that Temporal CNN and LSTM models significantly reduce inventory costs and improve fill rates compared to statistical baselines. Sensitivity and multi-echelon analyses demonstrate robustness and scalability, offering a data-driven decision-support tool for modern supply chains.
Abstract (translated)
URL
https://arxiv.org/abs/2603.16815
PDF
-
LenghuSky-8: An 8-Year All-Sky Cloud Dataset with Star-Aware Masks and Alt-Az Calibration for Segmentation and Nowcasting
2026-03-17 12:05:21Yicheng Rui, Xiao-Wei Duan, Licai Deng, Fan Yang, Zhengming Dang, Zhengjun Du, Junhao Peng, Wenhao Chu, Umut Mahmut, Kexin Li, Yiyun Wu, Fabo FengAbstract
Ground-based time-domain observatories require minute-by-minute, site-scale awareness of cloud cover, yet existing all-sky datasets are short, daylight-biased, or lack astrometric calibration. We present LenghuSky-8, an eight-year (2018-2025) all-sky imaging dataset from a premier astronomical site, comprising 429,620 $512 \times 512$ frames with 81.2% night-time coverage, star-aware cloud masks, background masks, and per-pixel altitude-azimuth (Alt-Az) calibration. For robust cloud segmentation across day, night, and lunar phases, we train a linear probe on DINOv3 local features and obtain 93.3% $\pm$ 1.1% overall accuracy on a balanced, manually labeled set of 1,111 images. Using stellar astrometry, we map each pixel to local alt-az coordinates and measure calibration uncertainties of approximately 0.37 deg at zenith and approximately 1.34 deg at 30 deg altitude, sufficient for integration with telescope schedulers. Beyond segmentation, we introduce a short-horizon nowcasting benchmark over per-pixel three-class logits (sky/cloud/contamination) with four baselines: persistence (copying the last frame), optical flow, ConvLSTM, and VideoGPT. ConvLSTM performs best but yields only limited gains over persistence, underscoring the difficulty of near-term cloud evolution. We release the dataset, calibrations, and an open-source toolkit for loading, evaluation, and scheduler-ready alt-az maps to boost research in segmentation, nowcasting, and autonomous observatory operations.
Abstract (translated)
URL
https://arxiv.org/abs/2603.16429
PDF
-
Detecting Sentiment Steering Attacks on RAG-enabled Large Language Models
2026-03-17 10:18:47Isha Andrade, Shalaka S Mahadik, Mithun Mukherjee, Pranav M Pawar, Raja MuthalaguAbstract
The proliferation of large-scale IoT networks has been both a blessing and a curse. Not only has it revolutionized the way organizations operate by increasing the efficiency of automated procedures, but it has also simplified our daily lives. However, while IoT networks have improved convenience and connectivity, they have also increased security risk due to unauthorized devices gaining access to these networks and exploiting existing weaknesses with specific attack types. The research proposes two lightweight deep learning (DL)-based intelligent intrusion detection systems (IDS). to enhance the security of IoT networks: the proposed convolutional neural network (CNN)-based IDS and the proposed long short-term memory (LSTM)-based IDS. The research evaluated the performance of both intelligent IDSs based on DL using the CICIoT2023 dataset. DL-based intelligent IDSs successfully identify and classify various cyber threats using binary, grouped, and multi-class classification. The proposed CNN-based IDS achieves an accuracy of 99.34%, 99.02% and 98.6%, while the proposed LSTM-based IDS achieves an accuracy of 99.42%, 99.13%, and 98.68% for binary, grouped, and multi-class classification, respectively.
Abstract (translated)
URL
https://arxiv.org/abs/2603.16342
PDF
