RNN
-
Not All News Is Equal: Topic- and Event-Conditional Sentiment from Finetuned LLMs for Aluminum Price Forecasting
2026-03-10 01:54:12Alvaro Paredes Amorin, Andre Python, Christoph WeisserAbstract
By capturing the prevailing sentiment and market mood, textual data has become increasingly vital for forecasting commodity prices, particularly in metal markets. However, the effectiveness of lightweight, finetuned large language models (LLMs) in extracting predictive signals for aluminum prices, and the specific market conditions under which these signals are most informative, remains under-explored. This study generates monthly sentiment scores from English and Chinese news headlines (Reuters, Dow Jones Newswires, and China News Service) and integrates them with traditional tabular data, including base metal indices, exchange rates, inflation rates, and energy prices. We evaluate the predictive performance and economic utility of these models through long-short simulations on the Shanghai Metal Exchange from 2007 to 2024. Our results demonstrate that during periods of high volatility, Long Short-Term Memory (LSTM) models incorporating sentiment data from a finetuned Qwen3 model (Sharpe ratio 1.04) significantly outperform baseline models using tabular data alone (Sharpe ratio 0.23). Subsequent analysis elucidates the nuanced roles of news sources, topics, and event types in aluminum price forecasting.
Abstract (translated)
通过捕捉当前的情绪和市场氛围，文本数据在预测商品价格方面变得越来越重要，特别是在金属市场上。然而，轻量级微调的大规模语言模型（LLMs）提取铝价的预测信号的有效性以及这些信号在特定市场条件下的信息价值仍然没有得到充分探索。这项研究生成了来自英文和中文新闻标题（路透社、道琼斯通讯社和中国新闻社）的月度情绪评分，并将它们与传统的表格数据集（包括基础金属指数、汇率、通胀率和能源价格）相结合。我们通过2007年至2024年在上海金属交易所进行的长短交易模拟来评估这些模型的预测性能和经济效用。我们的结果表明，在高波动性时期，结合来自微调后的Qwen3模型的情绪数据的长短时记忆（LSTM）模型表现显著优于仅使用表格数据作为基础的基准模型（夏普比率分别为1.04和0.23）。后续分析进一步阐明了新闻来源、主题和事件类型在铝价预测中的复杂作用。
URL
https://arxiv.org/abs/2603.09085
PDF
-
Beyond Amplitude: Channel State Information Phase-Aware Deep Fusion for Robotic Activity Recognition
2026-03-10 00:36:45Rojin Zandi, Hojjat Salehinejad, Milad SiamiAbstract
Wi-Fi Channel State Information (CSI) has emerged as a promising non-line-of-sight sensing modality for human and robotic activity recognition. However, prior work has predominantly relied on CSI amplitude while underutilizing phase information, particularly in robotic arm activity recognition. In this paper, we present GateFusion-Bidirectional Long Short-Term Memory network (GF-BiLSTM) for WiFi sensing in robotic activity recognition. GF-BiLSTM is a two-stream gated fusion network that encodes amplitude and phase separately and adaptively integrates per-time features through a learned gating mechanism. We systematically evaluate state-of-the-art deep learning models under a Leave-One-Velocity-Out (LOVO) protocol across four input configurations: amplitude only, phase only, amplitude + unwrapped phase, and amplitude + sanitized phase. Experimental results demonstrate that incorporating phase alongside amplitude consistently improves recognition accuracy and cross-speed robustness, with GF-BiLSTM achieving the best performance. To the best of our knowledge, this work provides the first systematic exploration of CSI phase for robotic activity recognition, establishing its critical role in Wi-Fi-based sensing.
Abstract (translated)
Wi-Fi 信道状态信息（CSI）已成为非直视线感知模式中用于人类和机器人活动识别的有前途的技术。然而，先前的工作主要依赖于CSI幅度信息，而忽视了相位信息的应用，尤其是在机器人手臂活动识别方面。本文提出了一种基于双流门控融合网络的GateFusion-Bidirectional Long Short-Term Memory (GF-BiLSTM)模型，用于通过Wi-Fi传感进行机器人活动识别。GF-BiLSTM将幅度和相位分别编码，并通过学习到的门机制自适应地集成每个时间点上的特征。我们在四种输入配置下对最先进的深度学习模型进行了系统的评估：仅幅度、仅相位、幅度+未展开相位，以及幅度+净化后的相位。实验结果表明，在所有情况下，结合使用幅度和相位信息都能持续提高识别准确性和跨速度的鲁棒性，其中GF-BiLSTM的表现最佳。据我们所知，这项工作首次系统地探索了CSI相位在机器人活动识别中的作用，并确立了它在基于Wi-Fi感知中的关键角色。
URL
https://arxiv.org/abs/2603.09047
PDF
-
Don't Look Back in Anger: MAGIC Net for Streaming Continual Learning with Temporal Dependence
2026-03-09 16:49:04Federico Giannini, Sandro D'Andrea, Emanuele Della ValleAbstract
Concept drift, temporal dependence, and catastrophic forgetting represent major challenges when learning from data streams. While Streaming Machine Learning and Continual Learning (CL) address these issues separately, recent efforts in Streaming Continual Learning (SCL) aim to unify them. In this work, we introduce MAGIC Net, a novel SCL approach that integrates CL-inspired architectural strategies with recurrent neural networks to tame temporal dependence. MAGIC Net continuously learns, looks back at past knowledge by applying learnable masks over frozen weights, and expands its architecture when necessary. It performs all operations online, ensuring inference availability at all times. Experiments on synthetic and real-world streams show that it improves adaptation to new concepts, limits memory usage, and mitigates forgetting.
Abstract (translated)
概念漂移、时间依赖性和灾难性遗忘是处理数据流学习时面临的重大挑战。尽管流式机器学习和连续学习（CL）分别解决了这些问题，但最近的Streaming Continual Learning（SCL）努力旨在将它们统一起来。在这项工作中，我们介绍了MAGIC Net，这是一种新颖的SCL方法，它结合了受CL启发的架构策略与循环神经网络来处理时间依赖性问题。MAGIC Net持续学习，并通过在冻结权重上应用可学习的掩码来回溯过去的知识，在必要时扩展其架构。该模型的所有操作都在线进行，确保始终可以进行推断。实验结果表明，无论是在合成数据流还是现实世界的数据流中，MAGIC Net都能改善对新概念的适应性、限制内存使用，并减轻遗忘现象。
URL
https://arxiv.org/abs/2603.08600
PDF
-
Multimodal Deep Learning for Dynamic and Static Neuroimaging: Integrating MRI and fMRI for Alzheimer Disease Analysis
2026-03-09 12:58:45Anima Kujur, Zahra MonfaredAbstract
Magnetic Resonance Imaging (MRI) provides detailed structural information, while functional MRI (fMRI) captures temporal brain activity. In this work, we present a multimodal deep learning framework that integrates MRI and fMRI for multi-class classification of Alzheimer Disease (AD), Mild Cognitive Impairment, and Normal Cognitive State. Structural features are extracted from MRI using 3D convolutional neural networks, while temporal features are learned from fMRI sequences using recurrent architectures. These representations are fused to enable joint spatial-temporal learning. Experiments were conducted on a small paired MRI-fMRI dataset (29 subjects), both with and without data augmentation. Results show that data augmentation substantially improves classification stability and generalization, particularly for the multimodal 3DCNN-LSTM model. In contrast, augmentation was found to be ineffective for a large-scale single-modality MRI dataset. These findings highlight the importance of dataset size and modality when designing augmentation strategies for neuroimaging-based AD classification.
Abstract (translated)
URL
https://arxiv.org/abs/2603.13367
PDF
-
TA-RNN-Medical-Hybrid: A Time-Aware and Interpretable Framework for Mortality Risk Prediction
2026-03-09 11:49:42Zahra Jafari, Azadeh Zamanifar, Amirfarhad FarhadiAbstract
Accurate and interpretable mortality risk prediction in intensive care units (ICUs) remains a critical challenge due to the irregular temporal structure of electronic health records (EHRs), the complexity of longitudinal disease trajectories, and the lack of clinically grounded explanations in many data-driven models. To address these challenges, we propose \textit{TA-RNN-Medical-Hybrid}, a time-aware and knowledge-enriched deep learning framework that jointly models longitudinal clinical sequences and irregular temporal dynamics through explicit continuous-time encoding, along with standardized medical concept representations. The proposed framework extends time-aware recurrent modeling by integrating explicit continuous-time embeddings that operate independently of visit indexing, SNOMED-based disease representations, and a hierarchical dual-level attention mechanism that captures both visit-level temporal importance and feature/concept-level clinical relevance. This design enables accurate mortality risk estimation while providing transparent and clinically meaningful explanations aligned with established medical knowledge. We evaluate the proposed approach on the MIMIC-III critical care dataset and compare it against strong time-aware and sequential baselines. Experimental results demonstrate that TA-RNN-Medical-Hybrid consistently improves predictive performance in terms of AUC, accuracy, and recall-oriented F$_2$-score. Moreover, qualitative analysis shows that the model effectively decomposes mortality risk across time and clinical concepts, yielding interpretable insights into disease severity, chronicity, and temporal progression. Overall, the proposed framework bridges the gap between predictive accuracy and clinical interpretability, offering a scalable and transparent solution for high-stakes ICU decision support systems.
Abstract (translated)
重症监护病房（ICUs）中准确且可解释的死亡风险预测仍然是一个关键挑战，原因在于电子健康记录（EHRs）的不规则时间结构、纵向疾病轨迹的复杂性以及许多基于数据驱动模型缺乏临床基础解释。为了解决这些挑战，我们提出了**TA-RNN-Medical-Hybrid**，这是一种时间感知且知识丰富的深度学习框架，它通过显式的连续时间编码同时建模纵向临床序列和不规则的时间动态，并使用标准化的医疗概念表示。该框架通过整合独立于访问索引操作的明确连续时间嵌入、基于SNOMED的疾病表示以及一个分层双层级注意力机制（能够捕捉到就诊级别的时间重要性和特征/概念级别的临床相关性）扩展了时间感知递归建模方法。这种设计不仅实现了准确的风险评估，还提供了与已建立的医学知识一致的透明且具有临床意义的解释。 我们使用MIMIC-III重症监护数据集对所提出的方法进行了评估，并将其与强大的时间感知和顺序基线模型进行了比较。实验结果表明，在AUC、精度和召回导向F$_2$得分方面，TA-RNN-Medical-Hybrid在预测性能上持续改进。此外，定性分析显示该模型能够有效分解死亡风险的时间分布和临床概念，从而为疾病的严重程度、慢性病程以及时间进展提供了可解释的见解。 总的来说，所提出的框架填补了预测准确性和临床解释之间的空白，并为高风险ICU决策支持系统提供了一种具有扩展性和透明度的解决方案。
URL
https://arxiv.org/abs/2603.08278
PDF
-
Generalized Stock Price Prediction for Multiple Stocks Combined with News Fusion
2026-03-08 09:05:10Pei-Jun Liao, Hung-Shin Lee, Yao-Fei Cheng, Li-Wei Chen, Hung-yi Lee, Hsin-Min WangAbstract
Predicting stock prices presents challenges in financial forecasting. While traditional approaches such as ARIMA and RNNs are prevalent, recent developments in Large Language Models (LLMs) offer alternative methodologies. This paper introduces an approach that integrates LLMs with daily financial news for stock price prediction. To address the challenge of processing news data and identifying relevant content, we utilize stock name embeddings within attention mechanisms. Specifically, we encode news articles using a pre-trained LLM and implement three attention-based pooling techniques -- self-attentive, cross-attentive, and position-aware self-attentive pooling -- to filter news based on stock relevance. The filtered news embeddings, combined with historical stock prices, serve as inputs to the prediction model. Unlike prior studies that focus on individual stocks, our method trains a single generalized model applicable across multiple stocks. Experimental results demonstrate a 7.11% reduction in Mean Absolute Error (MAE) compared to the baseline, indicating the utility of stock name embeddings for news filtering and price forecasting within a generalized framework.
Abstract (translated)
股票价格预测在金融预测领域面临挑战。尽管ARIMA和RNN等传统方法应用广泛，但大语言模型（LLMs）的最新进展提供了替代方案。本文提出一种将LLM与每日财经新闻相结合用于股价预测的方法。为应对新闻数据处理及识别相关内容的挑战，我们在注意力机制中引入股票名称嵌入。具体而言，我们使用预训练LLM编码新闻文章，并实施三种基于注意力的池化技术——自注意力池化、交叉注意力池化及位置感知自注意力池化——依据股票相关性过滤新闻。经筛选的新闻嵌入与历史股价共同作为预测模型输入。与以往聚焦个股的研究不同，我们的方法训练出适用于多支股票的单一个体化通用模型。实验结果显示，相比基线方法，平均绝对误差（MAE）降低7.11%，表明在通用框架中，股票名称嵌入对新闻筛选与价格预测具有实用价值。
URL
https://arxiv.org/abs/2603.19286
PDF
-
Enhancing the Detection of Coronary Artery Disease Using Machine Learning
2026-03-06 21:11:24Karan Kumar Singh, Nikita Gajbhiye, Gouri Sankar MishraAbstract
Coronary Artery Disease (CAD) remains a leading cause of morbidity and mortality worldwide. Early detection is critical to recover patient outcomes and decrease healthcare costs. In recent years, machine learning (ML) advancements have shown significant potential in enhancing the accuracy of CAD diagnosis. This study investigates the application of ML algorithms to improve the detection of CAD by analyzing patient data, including clinical features, imaging, and biomarker profiles. Bi-directional Long Short-Term Memory (Bi-LSTM), Gated Recurrent Units (GRU), and a hybrid of Bi-LSTM+GRU were trained on large datasets to predict the presence of CAD. Results demonstrated that these ML models outperformed traditional diagnostic methods in sensitivity and specificity, offering a robust tool for clinicians to make more informed decisions. The experimental results show that the hybrid model achieved an accuracy of 97.07%. By integrating advanced data preprocessing techniques and feature selection, this study ensures optimal learning and model performance, setting a benchmark for the application of ML in CAD diagnosis. The integration of ML into CAD detection presents a promising avenue for personalized healthcare and could play a pivotal role in the future of cardiovascular disease management.
Abstract (translated)
冠状动脉疾病（CAD）仍然是全球发病率和死亡率的主要原因。早期检测对于改善患者预后和降低医疗成本至关重要。近年来，机器学习（ML）的进步在提高CAD诊断准确性方面显示出巨大潜力。本研究探讨了应用机器学习算法通过分析包括临床特征、影像学和生物标志物在内的患者数据来改进CAD检测的方法。双向长短期记忆网络（Bi-LSTM）、门控循环单元（GRU）以及Bi-LSTM与GRU的混合模型被训练在大规模数据集上预测CAD的存在情况。结果显示，这些机器学习模型在敏感性和特异性方面优于传统诊断方法，为临床医生提供了更有力的决策工具。实验结果表明，混合模型实现了97.07%的准确性。通过整合先进的数据预处理技术和特征选择技术，本研究确保了最佳的学习效果和模型性能，为机器学习在CAD诊断中的应用设立了新的标准。将机器学习集成到CAD检测中为个性化医疗提供了有前景的方向，并可能在未来心血管疾病的管理中发挥关键作用。
URL
https://arxiv.org/abs/2603.06888
PDF
-
A Hybrid Machine Learning Model for Cerebral Palsy Detection
2026-03-06 19:11:24Karan Kumar Singh, Nikita Gajbhiye, Gouri Sankar MishraAbstract
The development of effective treatments for Cerebral Palsy (CP) can begin with the early identification of affected children while they are still in the early stages of the disorder. Pathological issues in the brain can be better diagnosed with the use of one of many medical imaging techniques. Magnetic Resonance Imaging (MRI) has revolutionized medical imaging with its unparalleled image resolution. A unique Machine Learning (ML) model that was built to identify CP disorder is presented in this paper. The model is intended to assist in the early diagnosis of CP in newborns. In this study, the brain MRI images dataset was first collected, and then the preprocessing techniques were applied to this dataset to make it ready for use in the proposed model. Following this, the proposed model was constructed by combining three CNN models, specifically VGG 19, Efficient-Net, and the ResNet50 model, to extract features from the image. Following this, a Bi-LSTM was utilized as a classifier to determine whether or not CP was present, and finally, the proposed model was employed for training and testing. The results show that the proposed model achieved an accuracy of 98.83%, which is higher than VGG-19 (96.79%), Efficient-Net (97.29%), and VGG-16 (97.50%).. When the suggested model is compared to other models that have been pre-trained in the past, the accuracy scores seem to be much higher.
Abstract (translated)
针对脑性瘫痪（CP）的有效治疗可以从早期识别患病儿童开始，特别是在疾病初期阶段。利用多种医学成像技术之一可以更准确地诊断大脑中的病理问题。磁共振成像（MRI）以其无与伦比的图像分辨率彻底革新了医学影像领域。本文介绍了一种专门用于识别脑性瘫痪的独特机器学习（ML）模型，旨在帮助早期诊断新生儿CP。 在这项研究中，首先收集了脑部MRI图像数据集，并对这些数据应用预处理技术以使其适合在提议的模型中使用。接下来，构建了一个由三种卷积神经网络（CNN）模型组合而成的建议模型，具体为VGG19、Efficient-Net和ResNet50，用于从图像中提取特征。随后，采用双向长短时记忆网络（Bi-LSTM）作为分类器来判断是否患有CP，并最终使用该提议模型进行训练与测试。 研究结果表明，所提出的模型达到了98.83%的准确率，这一成绩高于VGG-19（96.79%）、Efficient-Net（97.29%）和VGG-16（97.50%）。当将建议模型与其他先前预训练过的模型进行比较时，其准确性得分明显更高。
URL
https://arxiv.org/abs/2603.06803
PDF
-
Stock Market Prediction Using Node Transformer Architecture Integrated with BERT Sentiment Analysis
2026-03-06 05:15:22Mohammad Al Ridhawi, Mahtab Haj Ali, Hussein Al OsmanAbstract
Stock market prediction presents considerable challenges for investors, financial institutions, and policymakers operating in complex market environments characterized by noise, non-stationarity, and behavioral dynamics. Traditional forecasting methods often fail to capture the intricate patterns and cross-sectional dependencies inherent in financial markets. This paper presents an integrated framework combining a node transformer architecture with BERT-based sentiment analysis for stock price forecasting. The proposed model represents the stock market as a graph structure where individual stocks form nodes and edges capture relationships including sectoral affiliations, correlated price movements, and supply chain connections. A fine-tuned BERT model extracts sentiment from social media posts and combines it with quantitative market features through attention-based fusion. The node transformer processes historical market data while capturing both temporal evolution and cross-sectional dependencies among stocks. Experiments on 20 S&P 500 stocks spanning January 1982 to March 2025 demonstrate that the integrated model achieves a mean absolute percentage error (MAPE) of 0.80% for one-day-ahead predictions, compared to 1.20% for ARIMA and 1.00% for LSTM. Sentiment analysis reduces prediction error by 10% overall and 25% during earnings announcements, while graph-based modeling contributes an additional 15% improvement by capturing inter-stock dependencies. Directional accuracy reaches 65% for one-day forecasts. Statistical validation through paired t-tests confirms these improvements (p < 0.05 for all comparisons). The model maintains MAPE below 1.5% during high-volatility periods where baseline models exceed 2%.
Abstract (translated)
股票市场的预测对于投资者、金融机构和政策制定者来说在复杂市场环境中面临着巨大的挑战，这些环境充满了噪音、非平稳性和行为动态。传统预测方法往往无法捕捉到金融市场中固有的复杂模式和跨截面依赖性。本文提出了一种结合节点变压器架构与基于BERT的情感分析的综合框架，用于股票价格预测。 该模型将股票市场表示为图结构，在这种结构中，单个股票形成节点，边则代表包括行业关联、相关的价格变动以及供应链连接在内的关系。经过微调的BERT模型从社交媒体帖子中提取情感，并通过基于注意力机制的方法将其与定量市场特征相结合。节点变压器处理历史市场数据，同时捕捉股票之间的时序演变和跨截面依赖性。 在针对20只标普500成分股进行的实验中（涵盖1982年1月至2025年3月期间的数据），综合模型在一日前预测中的平均绝对百分比误差（MAPE）为0.80%，相比之下，ARIMA模型和LSTM模型分别为1.20%和1.00%。情感分析整体上减少了预测误差的10%，在财报发布期间减少幅度高达25%，而基于图的方法通过捕捉股票间的依赖关系贡献了额外15%的改进。方向准确性达到了65%的一日预报水平。配对t检验的统计验证证实了这些改进（所有比较中的p值均小于0.05）。在高波动性期间，模型维持MAPE低于1.5%，而基准模型则超过2%。 这一研究证明，在复杂且充满不确定性的金融市场中，综合使用先进的机器学习技术和基于图的方法可以显著提高预测准确性。
URL
https://arxiv.org/abs/2603.05917
PDF
-
MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens
2026-03-06 02:29:54Yu Chen, Runkai Chen, Sheng Yi, Xinda Zhao, Xiaohong Li, Jianjin Zhang, Jun Sun, Chuanrui Hu, Yunyun Han, Lidong Bing, Yafeng Deng, Tianqiao ChenAbstract
Long-term memory is a cornerstone of human intelligence. Enabling AI to process lifetime-scale information remains a long-standing pursuit in the field. Due to the constraints of full-attention architectures, the effective context length of large language models (LLMs) is typically limited to 1M tokens. Existing approaches, such as hybrid linear attention, fixed-size memory states (e.g., RNNs), and external storage methods like RAG or agent systems, attempt to extend this limit. However, they often suffer from severe precision degradation and rapidly increasing latency as context length grows, an inability to dynamically modify memory content, or a lack of end-to-end optimization. These bottlenecks impede complex scenarios like large-corpus summarization, Digital Twins, and long-history agent reasoning, while limiting memory capacity and slowing inference. We present Memory Sparse Attention (MSA), an end-to-end trainable, efficient, and massively scalable memory model framework. Through core innovations including scalable sparse attention and document-wise RoPE, MSA achieves linear complexity in both training and inference while maintaining exceptional stability, exhibiting less than 9% degradation when scaling from 16K to 100M tokens. Furthermore, KV cache compression, combined with Memory Parallel, enables 100M-token inference on 2xA800 GPUs. We also propose Memory Interleaving to facilitate complex multi-hop reasoning across scattered memory segments. MSA significantly surpasses frontier LLMs, state-of-the-art RAG systems, and leading memory agents in long-context benchmarks. These results demonstrate that by decoupling memory capacity from reasoning, MSA provides a scalable foundation to endow general-purpose models with intrinsic, lifetime-scale memory.
Abstract (translated)
长期记忆是人类智能的基石。让AI处理终身尺度的信息一直是该领域的长期追求。由于全注意力架构的限制，大语言模型（LLMs）的有效上下文长度通常被限制在100万token以内。现有方法如混合线性注意力、固定大小的记忆状态（如RNN）以及RAG或智能体系统等外部存储方案，试图突破这一限制。然而，它们往往存在精度严重下降、上下文增长时延迟急剧增加、无法动态修改记忆内容或缺乏端到端优化等问题。这些瓶颈阻碍了大规模语料摘要、数字孪生和长历史智能体推理等复杂场景的应用，同时限制了记忆容量并拖慢了推理速度。 我们提出记忆稀疏注意力（MSA），一个端到端可训练、高效且极具扩展性的记忆模型框架。通过可扩展稀疏注意力和文档级RoPE等核心创新，MSA在训练和推理中均实现线性复杂度，同时保持卓越稳定性——在从16K扩展到1亿token时性能衰减低于9%。此外，KV缓存压缩结合记忆并行技术，使双A800 GPU可实现1亿token推理。我们还提出内存交错机制，以支持分散记忆片段间的复杂多跳推理。 在长上下文基准测试中，MSA大幅超越前沿大语言模型、先进RAG系统和领先记忆智能体。这些结果表明，通过将记忆容量与推理能力解耦，MSA为通用模型赋予内在的终身尺度记忆提供了可扩展的基础。
URL
https://arxiv.org/abs/2603.23516
PDF
-
When Sensors Fail: Temporal Sequence Models for Robust PPO under Sensor Drift
2026-03-04 22:21:54Kevin Vogt-Lowell, Theodoros Tsiligkaridis, Rodney Lafuente-Mercado, Surabhi Ghatti, Shanghua Gao, Marinka Zitnik, Daniela RusAbstract
Real-world reinforcement learning systems must operate under distributional drift in their observation streams, yet most policy architectures implicitly assume fully observed and noise-free states. We study robustness of Proximal Policy Optimization (PPO) under temporally persistent sensor failures that induce partial observability and representation shift. To respond to this drift, we augment PPO with temporal sequence models, including Transformers and State Space Models (SSMs), to enable policies to infer missing information from history and maintain performance. Under a stochastic sensor failure process, we prove a high-probability bound on infinite-horizon reward degradation that quantifies how robustness depends on policy smoothness and failure persistence. Empirically, on MuJoCo continuous-control benchmarks with severe sensor dropout, we show Transformer-based sequence policies substantially outperform MLP, RNN, and SSM baselines in robustness, maintaining high returns even when large fractions of sensors are unavailable. These results demonstrate that temporal sequence reasoning provides a principled and practical mechanism for reliable operation under observation drift caused by sensor unreliability.
Abstract (translated)
现实中的强化学习系统必须在观察流分布漂移的情况下运行，而大多数策略架构则假设完全可观察且无噪声的状态。我们研究了近端策略优化（PPO）在导致部分可观测性和表示迁移的持久传感器故障下的鲁棒性。为了应对这种变化，我们在PPO中加入了时间序列模型，包括Transformer和状态空间模型（SSMs），以使策略能够从历史记录中推断缺失的信息并保持性能。在一个随机的传感器故障过程中，我们证明了无穷时域奖励退化的高概率界，这量化了鲁棒性如何依赖于政策平滑度和失败持久性。在严重传感器丢失的情况下，我们在MuJoCo连续控制基准测试上显示基于Transformer的时间序列策略在鲁棒性方面大幅优于MLP、RNN和SSM基线，在大量传感器不可用时也能保持高回报。这些结果表明，时间序列推理提供了一种原理性和实用性的机制来确保由于传感器不准确性导致的观察漂移下的可靠操作。
URL
https://arxiv.org/abs/2603.04648
PDF
-
Digital-Twin Losses for Lane-Compliant Trajectory Prediction at Urban Intersections
2026-03-04 20:33:25Kuo-Yi Chao, Erik Leo Ha{\ss}, Melina Gegg, Jiajie Zhang, Ralph Ra{\ss}hofer, Alois Christian KnollAbstract
Accurate and safety-conscious trajectory prediction is a key technology for intelligent transportation systems, especially in V2X-enabled urban environments with complex multi-agent interactions. In this paper, we created a digital twin-driven V2X trajectory prediction pipeline that jointly leverages cooperative perception from vehicles and infrastructure to forecast multi-agent motion at signalized intersections. The proposed model combines a Bi-LSTM-based generator with a structured training objective consisting of a standard mean squared error (MSE) loss and a novel twin loss. The twin loss encodes infrastructure constraints, collision avoidance, diversity across predicted modes, and rule-based priors derived from the digital twin. While the MSE term ensures point-wise accuracy, the twin loss penalizes traffic rule violations, predicted collisions, and mode collapse, guiding the model toward scene-consistent and safety-compliant predictions. We train and evaluate our approach on real-world V2X data sent from the intersection to the vehicle and collected in urban corridors. In addition to standard trajectory metrics (ADE, FDE), we introduce ITS-relevant safety indicators, including infrastructure and rule violation rates. Experimental results demonstrate that the proposed training scheme significantly reduces critical violations while maintaining comparable prediction accuracy and real-time performance, highlighting the potential of digital twin-driven multi-loss learning for V2X-enabled intelligent transportation systems.
Abstract (translated)
准确且注重安全的轨迹预测是智能交通系统的关键技术，特别是在复杂多代理交互的V2X（车联网）增强型城市环境中。本文中，我们创建了一个数字孪生驱动的V2X轨迹预测管道，该管道结合了来自车辆和基础设施的合作感知能力，以在有信号控制的交叉路口处预测多重代理的动作。所提出的模型结合了一个基于Bi-LSTM（双向长短期记忆网络）的生成器与一个包含标准均方误差(MSE)损失及新颖孪生损失在内的结构化训练目标。该孪生损失编码了基础设施约束、碰撞避免策略、不同预测模式间的多样性以及从数字孪生中推导出的行为准则。虽然MSE项保证了点对点精度，但孪生损失惩罚违反交通规则的预测行为、预计碰撞和模式崩溃，从而引导模型做出与场景一致且符合安全规范的预测。 我们在来自城市走廊中的交叉路口传输至车辆的真实世界V2X数据上训练并评估我们的方法。除标准轨迹指标（ADE-平均位移误差、FDE-最终位移误差）外，我们还引入了适用于ITS(智能交通系统)的安全指标，包括基础设施和规则违规率。实验结果表明，所提出的培训方案在保持相当的预测准确性和实时性能的同时，显著减少了关键性的违规行为，突显了数字孪生驱动多损失学习方法在V2X增强型智能交通系统中的潜力。
URL
https://arxiv.org/abs/2603.05546
PDF
-
Towards Explainable Deep Learning for Ship Trajectory Prediction in Inland Waterways
2026-03-04 07:01:59Tom Legel, Dirk S\"offker, Roland Sch\"atzle, Kathrin DonandtAbstract
Accurate predictions of ship trajectories in crowded environments are essential to ensure safety in inland waterways traffic. Recent advances in deep learning promise increased accuracy even for complex scenarios. While the challenge of ship-to-ship awareness is being addressed with growing success, the explainability of these models is often overlooked, potentially obscuring an inaccurate logic and undermining the confidence in their reliability. This study examines an LSTM-based vessel trajectory prediction model by incorporating trained ship domain parameters that provide insight into the attention-based fusion of the interacting vessels' hidden states. This approach has previously been explored in the field of maritime shipping, yet the variety and complexity of encounters in inland waterways allow for a more profound analysis of the model's interpretability. The prediction performance of the proposed model variants are evaluated using standard displacement error statistics. Additionally, the plausibility of the generated ship domain values is analyzed. With an final displacement error of around 40 meters in a 5-minute prediction horizon, the model performs comparably to similar studies. Though the ship-to-ship attention architecture enhances prediction accuracy, the weights assigned to vessels in encounters using the learnt ship domain values deviate from the expectation. The observed accuracy improvements are thus not entirely driven by a causal relationship between a predicted trajectory and the trajectories of nearby ships. This finding underscores the model's explanatory capabilities through its intrinsically interpretable design. Future work will focus on utilizing the architecture for counterfactual analysis and on the incorporation of more sophisticated attention mechanisms.
Abstract (translated)
在拥挤环境中准确预测船舶轨迹对于确保内陆水道交通的安全至关重要。近年来，深度学习技术的进步承诺即使在复杂场景下也能提高准确性。虽然解决船只间感知的问题已经取得了不少进展，但这些模型的可解释性往往被忽视，这可能会掩盖其逻辑上的不准确，并削弱对其可靠性的信心。 这项研究考察了一种基于LSTM（长短期记忆网络）的船舶轨迹预测模型，在该模型中引入了训练过的船域参数，以提供关于相互作用船只隐藏状态的关注机制融合的见解。这种方法在海事航运领域已被探索过，但内陆水道遭遇情况的多样性和复杂性允许对模型解释性的更深层次分析。 通过使用标准位移误差统计方法评估提出的模型变体的预测性能，并进一步分析生成的船域值的合理性。最终，在5分钟预测时间范围内，该模型以约40米的平均位移误差表现出了与类似研究相当的水平。虽然船舶间注意力架构提升了预测精度，但使用学习到的船域值为遭遇中的船只分配权重时却偏离了预期。 观察到的准确性改进并非完全由预测轨迹与其附近船只轨迹之间的因果关系驱动。这一发现突显了该模型通过其固有的可解释性设计来展示其解译能力。未来的研究将侧重于利用架构进行反事实分析，并引入更复杂的注意力机制。
URL
https://arxiv.org/abs/2603.04472
PDF
-
Why Are Linear RNNs More Parallelizable?
2026-03-04 00:51:08William Merrill, Hongjian Jiang, Yanhong Li, Ashish SabharwalAbstract
The community is increasingly exploring linear RNNs (LRNNs) as language models, motivated by their expressive power and parallelizability. While prior work establishes the expressivity benefits of LRNNs over transformers, it is unclear what makes LRNNs -- but not traditional, nonlinear RNNs -- as easy to parallelize in practice as transformers. We answer this question by providing a tight connection between types of RNNs and standard complexity classes. We show that LRNNs can be viewed as log-depth (bounded fan-in) arithmetic circuits, which represents only a slight depth overhead relative to log-depth boolean circuits that transformers admit. Furthermore, we show that nonlinear RNNs can solve $\mathsf{L}$-complete problems (and even $\mathsf{P}$-complete ones, under polynomial precision), revealing a fundamental barrier to parallelizing them as efficiently as transformers. Our theory also identifies fine-grained expressivity differences between recent popular LRNN variants: permutation-diagonal LRNNs are $\mathsf{NC}^1$-complete whereas diagonal-plus-low-rank LRNNs are more expressive ($\mathsf{PNC}^1$-complete). We provide further insight by associating each type of RNN with a corresponding automata-theoretic model that it can simulate. Together, our results reveal fundamental tradeoffs between nonlinear RNNs and different variants of LRNNs, providing a foundation for designing LLM architectures that achieve an optimal balance between expressivity and parallelism.
Abstract (translated)
社区越来越多地探索将线性递归神经网络（LRNN）作为语言模型，这一趋势受到其表达能力和并行化潜力的驱动。尽管先前的研究已经证明了LRNN在表达能力上优于转换器模型，但尚不清楚是什么原因使得LRNN能够在实践中像转换器一样易于并行化，而传统的非线性RNN则不能。 我们通过将不同类型的RNN与标准复杂度类紧密联系起来回答了这个问题。研究表明，LRNN可以被视作对数深度（有界扇入）算术电路，这仅相对于转换器模型所允许的对数深度布尔电路带来微小的深度开销。此外，我们还证明了非线性RNN能够解决$\mathsf{L}$-完全问题（甚至在多项式精度下可以解决$\mathsf{P}$-完全问题），揭示了它们实现与转换器同等高效并行化的根本障碍。 我们的理论也区分出了近期流行的LRNN变体之间细微的表达能力差异：排列对角线LRNN是$\mathsf{NC}^1$-完全，而对角加低秩LRNN则更为复杂（$\mathsf{PNC}^1$-完全）。我们通过将每种RNN类型与它可以模拟的自动机理论模型关联起来进一步提供了见解。 综上所述，我们的研究成果揭示了非线性RNN和不同变体的LRNN之间在表达能力和并行化之间的根本权衡，并为设计实现两者最优平衡的语言模型（LLM）架构奠定了基础。
URL
https://arxiv.org/abs/2603.03612
PDF
-
Learning Therapist Policy from Therapist-Exoskeleton-Patient Interaction
2026-03-02 22:58:34Grayson Snyder, Lorenzo Vianello, Levi Hargrove, Matthew L. Elwin, Jose PonsAbstract
Post-stroke rehabilitation is often necessary for patients to regain proper walking gait. However, the typical therapy process can be exhausting and physically demanding for therapists, potentially reducing therapy intensity, duration, and consistency over time. We propose a Patient-Therapist Force Field (PTFF) to visualize therapist responses to patient kinematics and a Synthetic Therapist (ST) machine learning model to support the therapist in dyadic robot-mediated physical interaction therapy. The first encodes patient and therapist stride kinematics into a shared low-dimensional latent manifold using a Variational Autoencoder (VAE) and models their interaction through a Gaussian Mixture Model (GMM), which learns a probabilistic vector field mapping patient latent states to therapist responses. This representation visualizes patient-therapist interaction dynamics to inform therapy strategies and robot controller design. The latter is implemented as a Long Short-Term Memory (LSTM) network trained on patient-therapist interaction data to predict therapist-applied joint torques from patient kinematics. Trained and validated using leave-one-out cross-validation across eight post-stroke patients, the model was integrated into a ROS-based exoskeleton controller to generate real-time torque assistance based on predicted therapist responses. Offline results and preliminary testing indicate the potential of their use as an alternative approach to post-stroke exoskeleton therapy. The PTFF provides understanding of the therapist's actions while the ST frees the human therapist from the exoskeleton, allowing them to continuously monitor the patient's nuanced condition.
Abstract (translated)
中风后的康复通常需要患者重新获得正常的行走步态。然而，传统的治疗过程可能对理疗师来说既疲惫又体力消耗大，这可能会随着时间的推移减少治疗强度、时长和一致性。为此，我们提出了一种患者-理疗师力场（PTFF）可视化方法来展示理疗师对患者运动学特征的响应，并开发了一个合成理疗师（ST）机器学习模型以支持机器人介导物理互动疗法中的人机协作。前者通过变分自动编码器（VAE）将患者的步态和理疗师的动作映射到共享低维潜在流形，然后使用高斯混合模型（GMM）建模患者与理疗师之间的交互过程，并学习一种概率向量场以从患者的状态预测理疗师的反应。这种表示法可以可视化患者-理疗师互动的动力学情况，从而帮助制定治疗策略和机器人控制器的设计。后者则采用长短期记忆网络（LSTM），利用患者-理疗师互动数据来根据患者的运动学特征预测理疗师所施加的关节扭矩。 该模型通过八名中风后病人的留一交叉验证法进行训练和验证，并被集成到基于ROS的外骨骼控制器中，以根据预测出的理疗师反应生成实时力矩辅助。离线结果和初步测试表明了这种方法在替代中风后外骨骼疗法中的潜力。PTFF能够揭示理疗师的行为模式，而ST模型则使人类理疗师从外骨骼设备解脱出来，使其可以持续监测患者的细微状况变化。
URL
https://arxiv.org/abs/2603.02458
PDF
-
VietSuperSpeech: A Large-Scale Vietnamese Conversational Speech Dataset for ASR Fine-Tuning in Chatbot, Customer Support, and Call Center Applications
2026-03-02 14:13:57Loan Do, Thanh Ngoc Nguyen, Thanh Pham, Vinh Do, Hien Nguyen, Charlotte NguyenAbstract
We introduce VietSuperSpeech, a large-scale Vietnamese automatic speech recognition (ASR) dataset of 52,023 audio-text pairs totaling 267.39 hours, with a distinctive focus on casual conversational speech. Unlike existing Vietnamese ASR corpora that predominantly feature read speech, news narration, or audiobook content, VietSuperSpeech is sourced from four publicly accessible YouTube channels spanning everyday conversation, personal vlogging, overseas Vietnamese community dialogue, and informal commentary - the very speech styles encountered in real-world chatbot, customer support, call center, and hotline deployments. All audio is standardized to 16 kHz mono PCM WAV and segmented into 3-30 second utterances. Transcriptions are generated via pseudo-labeling using the Zipformer-30M-RNNT-6000h model (Nguyen, 2025) deployed through Sherpa-ONNX, pre-trained on 6,000 hours of Vietnamese speech. After quality filtering, the dataset is split into 46,822 training samples (240.67 hours) and 5,201 development/test samples (26.72 hours) with a fixed random seed. The text averages 266 characters per utterance, totaling 13.8 million fully diacritically marked Vietnamese characters. We demonstrate that VietSuperSpeech fills a critical gap in the Vietnamese ASR ecosystem: while corpora such as VLSP2020, VIET_BUD500, VietSpeech, FLEURS, VietMed, Sub-GigaSpeech2-Vi, viVoice, and Sub-PhoAudioBook provide broad coverage of formal and read speech, none specifically targets the casual, spontaneous register indispensable for conversational AI applications. VietSuperSpeech is publicly released at this https URL.
Abstract (translated)
我们介绍了VietSuperSpeech，这是一个包含52,023对音频文本数据、总计267.39小时的大型越南语自动语音识别（ASR）数据集，特别侧重于日常对话中的非正式会话内容。与现有主要收录朗读、新闻播报或有声书内容的越南语ASR语料库不同，VietSuperSpeech的数据来源于四个公开访问的YouTube频道，这些渠道涵盖了日常生活对话、个人博客视频、海外越南社区对话以及非正式评论——这些都是实际应用中聊天机器人、客户支持和呼叫中心会遇到的真实语音风格。所有音频统一标准化为16 kHz单声道PCM WAV格式，并被分割成3到30秒长的片段。 转录文本是通过使用Zipformer-30M-RNNT-6000h模型（Nguyen, 2025）进行伪标签生成，该模型在经过6,000小时越南语语音预训练后部署于Sherpa-ONNX平台。质量过滤之后，数据集被分为46,822个用于训练的样本（总计240.67小时）和5,201个开发/测试样本（共计26.72小时），并采用固定随机种子进行划分。每个语音片段的文本平均长度为266字符，整个数据集包含约1380万完全带音标符号的越南语字符。 我们展示了VietSuperSpeech填补了越南语ASR生态系统中的关键空白：虽然诸如VLSP2020、VIET_BUD500、VietSpeech、FLEURS、VietMed、Sub-GigaSpeech2-Vi、viVoice和Sub-PhoAudioBook等数据集广泛涵盖了正式及朗读语音，但没有一个专门针对非正式、即兴的日常会话场景，而这对于对话型AI应用至关重要。VietSuperSpeech可以在[这里](https://this-url.com)公开获取（原文链接处应填写具体网址）。
URL
https://arxiv.org/abs/2603.01894
PDF
-
CHLU: The Causal Hamiltonian Learning Unit as a Symplectic Primitive for Deep Learning
Abstract
Current deep learning primitives dealing with temporal dynamics suffer from a fundamental dichotomy: they are either discrete and unstable (LSTMs) \citep{pascanu_difficulty_2013}, leading to exploding or vanishing gradients; or they are continuous and dissipative (Neural ODEs) \citep{dupont_augmented_2019}, which destroy information over time to ensure stability. We propose the \textbf{Causal Hamiltonian Learning Unit} (pronounced: \textit{clue}), a novel Physics-grounded computational learning primitive. By enforcing a Relativistic Hamiltonian structure and utilizing symplectic integration, a CHLU strictly conserves phase-space volume, as an attempt to solve the memory-stability trade-off. We show that the CHLU is designed for infinite-horizon stability, as well as controllable noise filtering. We then demonstrate a CHLU's generative ability using the MNIST dataset as a proof-of-principle.
Abstract (translated)
当前用于处理时间动态的深度学习基本构建块面临着一个根本性的二难困境：它们要么是离散且不稳定的（如LSTM）\citep{pascanu_difficulty_2013}，导致梯度爆炸或消失；要么是连续但耗散的（如神经ODE）\citep{dupont_augmented_2019}，这会导致信息随时间流逝而被破坏以确保稳定性。我们提出了**因果哈密顿学习单元**（发音为：clue），这是一个新型基于物理原理的计算学习基本构建块。通过强制执行相对论哈密顿结构并利用辛积分法，CHLU 严格地保持相空间体积不变，试图解决内存和稳定性的权衡问题。我们展示了 CHLU 设计用于无限时间范围内的稳定性以及可控噪声过滤能力。然后，我们将使用 MNIST 数据集展示 CHLU 的生成能力作为证明概念的实例。
URL
https://arxiv.org/abs/2603.01768
PDF
-
TacMamba: A Tactile History Compression Adapter Bridging Fast Reflexes and Slow VLA Reasoning
2026-03-02 10:26:54Zhenan Wang, Yanzhe Wang, Meixuan Ren, Peng Li, Yang Liu, Yifei Nie, Limin Long, Yun Ye, Xiaofeng Wang, Zhen Zhu, Huixu DongAbstract
In visually ambiguous manipulation such as detecting button click tactile feedback is often the sole source of ground truth. However, fusing tactile data poses a significant challenge due to a spatiotemporal mismatch: tactile perception requires high-frequency processing with long-horizon memory (System 1), whereas visual policies operate at low control frequencies (System 2). Existing architectures struggle to bridge this gap: Transformers are computationally prohibitive for high-frequency loops (>100Hz), while LSTMs suffer from forgetting over extended interaction histories. In this paper, we introduce TacMamba, a hierarchical architecture that aligns high-bandwidth tactile reflexes with low-frequency visual planning. Our approach comprises three core contributions: (1) a custom high-frequency tactile interface designed for flexible integration; (2) a Mamba-based Tactile History Compressor that encodes continuous force history into a compact state with O(1) inference latency (0.45 ms), enabling plug-and-play fusion with VLA models without joint pre-training and (3) a Tactile-Guided Dual-Stage Training strategy that leverages temporal discrimination for self-supervised representation learning and phase-uniform sampling to mitigate data sparsity. Experiments on discrete counting and implicit state switching demonstrate that TacMamba achieves 100% success rates, significantly outperforming the visual-only pi_0.5 baseline, while strictly satisfying hard real-time constraints.
Abstract (translated)
在视觉模棱两可的操作中，如检测按钮点击时，触觉反馈通常是唯一的真实来源。然而，融合触觉数据面临着显著挑战，因为存在时空不匹配的问题：触觉感知需要高频处理和长时间记忆（系统1），而视觉策略则以低控制频率运行（系统2）。现有的架构难以弥合这一差距：Transformer对于高频率循环（>100Hz）来说计算成本过高，而LSTM在长交互历史中会遗忘信息。 在这篇论文中，我们引入了TacMamba，这是一种层次化架构，将高频触觉反射与低频视觉规划对齐。我们的方法包含三个核心贡献： 1. 设计了一种定制的高频率触觉接口，以实现灵活集成； 2. 一个基于Mamba的触觉历史压缩器，它能将连续力的历史编码为具有O(1)推理延迟（0.45毫秒）的小型状态，使得无需联合预训练即可与视觉语言动作(VLA)模型无缝融合； 3. 触觉引导的双阶段训练策略，利用时间区分进行自监督表示学习，并采用相位均匀采样来缓解数据稀疏性。 在离散计数和隐式状态切换实验中显示，TacMamba能够实现100%的成功率，显著优于仅基于视觉的pi_0.5基准模型，同时严格满足硬实时约束。
URL
https://arxiv.org/abs/2603.01700
PDF
-
ConVibNet: Needle Detection during Continuous Insertion via Frequency-Inspired Features
2026-03-01 15:16:25Jiamei Guo, Zhehao Duan, Maria Neiiendam, Dianye Huang, Nassir Navab, Zhongliang JiangAbstract
Purpose: Ultrasound-guided needle interventions are widely used in clinical practice, but their success critically depends on accurate needle placement, which is frequently hindered by the poor and intermittent visibility of needles in ultrasound images. Existing approaches remain limited by artifacts, occlusions, and low contrast, and often fail to support real-time continuous insertion. To overcome these challenges, this study introduces a robust real-time framework for continuous needle detection. Methods: We present ConVibNet, an extension of VibNet for detecting needles with significantly reduced visibility, addressing real-time, continuous needle tracking during insertion. ConVibNet leverages temporal dependencies across successive ultrasound frames to enable continuous estimation of both needle tip position and shaft angle in dynamic scenarios. To strengthen temporal awareness of needle-tip motion, we introduce a novel intersection-and-difference loss that explicitly leverages motion correlations across consecutive frames. In addition, we curated a dedicated dataset for model development and evaluation. Results: The performance of the proposed ConVibNet model was evaluated on our dataset, demonstrating superior accuracy compared to the baseline VibNet and UNet-LSTM models. Specifically, ConVibNet achieved a tip error of 2.80+-2.42 mm and an angle error of 1.69+-2.00 deg. These results represent a 0.75 mm improvement in tip localization accuracy over the best-performing baseline, while preserving real-time inference capability. Conclusion: ConVibNet advances real-time needle detection in ultrasound-guided interventions by integrating temporal correlation modeling with a novel intersection-and-difference loss, thereby improving accuracy and robustness and demonstrating high potential for integration into autonomous insertion systems.
Abstract (translated)
目的：超声引导下的针刺干预在临床上被广泛使用，但其成功与否严重依赖于准确的针头定位，而这一点常因超声图像中针头可见度差且不连续而受阻。现有的方法仍然受限于伪影、遮挡和低对比度问题，并常常无法支持实时连续插入操作。为克服这些挑战，本研究引入了一种稳健的实时框架以实现连续针检测。 方法：我们介绍了ConVibNet，这是VibNet的一种扩展形式，专门用于在显著降低可见性的条件下检测针头，在针刺过程中实现了对针头实时、连续追踪的能力。ConVibNet利用了连续超声帧之间的时序依赖关系来实现在动态场景下同时估计针尖位置和针身角度的持续性计算。为了增强针对针尖运动的时间意识，我们引入了一种新颖的交差损失（intersection-and-difference loss），该方法明确地利用了连续帧间的运动相关性。此外，我们还为模型的发展和评估整理了一个专门的数据集。 结果：我们在我们的数据集上对所提出的ConVibNet模型进行了性能测试，显示其与基准模型VibNet及UNet-LSTM相比具有优越的准确性。具体来说，ConVibNet实现了针尖误差2.80±2.42毫米和角度误差1.69±2.00度的成绩。这些结果在最佳基础线定位精度上提高了0.75毫米，并同时保持了实时推理能力。 结论：通过将时序相关性建模与新颖的交差损失结合，ConVibNet推动了超声引导针刺干预中实时针检测的进步，从而提高了准确性及鲁棒性，并展示了在自主插入系统集成中的高潜力。
URL
https://arxiv.org/abs/2603.01147
PDF
-
Hybrid Neural-LLM Pipeline for Morphological Glossing in Endangered Language Documentation: A Case Study of Jungar Tuvan
2026-03-01 05:03:11Siyu Liang, Talant Mawkanuli, Gina-Anne LevowAbstract
Interlinear glossed text (IGT) creation remains a major bottleneck in linguistic documentation and fieldwork, particularly for low-resource morphologically rich languages. We present a hybrid automatic glossing pipeline that combines neural sequence labeling with large language model (LLM) post-correction, evaluated on Jungar Tuvan, a low-resource Turkic language. Through systematic ablation studies, we show that retrieval-augmented prompting provides substantial gains over random example selection. We further find that morpheme dictionaries paradoxically hurt performance compared to providing no dictionary at all in most cases, and that performance scales approximately logarithmically with the number of few-shot examples. Most significantly, our two-stage pipeline combining a BiLSTM-CRF model with LLM post-correction yields substantial gains for most models, achieving meaningful reductions in annotation workload. Drawing on these findings, we establish concrete design principles for integrating structured prediction models with LLM reasoning in morphologically complex fieldwork contexts. These principles demonstrate that hybrid architectures offer a promising direction for computationally light solutions to automatic linguistic annotation in endangered language documentation.
Abstract (translated)
交叉线注释文本（IGT）的创建仍然是语言记录和实地研究中的一个主要瓶颈，尤其是在资源较少、形态丰富的语言中。我们提出了一种结合神经序列标注与大型语言模型（LLM）后校正的混合自动注解管道，并在一种低资源突厥语——楚瓦什图瓦尼语上对其进行了评估。通过系统的消融研究，我们发现检索增强提示比随机示例选择提供了显著的优势。此外，我们发现在大多数情况下，形态词典反而会损害性能，相比于不提供任何字典的情况。同时，我们还发现性能随着少量样本数量的增加近似对数增长。 最重要的是，我们的两阶段管道将BiLSTM-CRF模型与LLM后校正结合使用，在大多数模型中产生了显著的效果提升，实现了注释工作量的实质性减少。基于这些发现，我们在形态复杂的实地研究环境中建立了结构化预测模型和LLM推理集成的具体设计原则。这些原则表明，混合架构为濒危语言文档自动语言注解提供了有希望的方向，并且可以实现计算负担较轻的解决方案。
URL
https://arxiv.org/abs/2603.00923
PDF
