The study introduces a leakage‑safe evaluation protocol for detecting hydrogen embrittlement in 316L stainless steel using SEM micrographs. By employing a Leave‑One‑Region‑Out cross‑validation over 14 spatial regions, the authors compare six feature‑classifier combinations, finding that a simple local binary pattern (LBP) with a support vector machine (SVM) achieves the best performance (balanced accuracy 0.79, H2 recall 0.69, H2 precision 0.82). The results are statistically significant (p = 0.008) and suggest that texture descriptors can reliably recover hydrogen‑charging signatures even with limited data.
By Muhammad Awais, Muhammad Yaseen, Abdul Shakoor, Niaz Ahmed Niaz, Huria Zia, Muhammad Zain Shakoor
GOMA (Graph-Optimized Multimodal Alignment) introduces a dual-embedding approach for multimodal retrieval, separating content embeddings supervised for paired identity from semantic embeddings trained with cross-modal pairs and observed relationships. The method fuses these embeddings, applies semantic agreement to weight graph edges, and uses restart graph propagation to reinforce the initial signal, enabling both single-modality and dual-attribute retrieval. Across six datasets and four tasks, GOMA outperforms 14 external methods on 14 primary metrics, with controlled experiments highlighting the impact of separate supervision, graph regularization, and semantic-guided propagation.
By Xu Wang, Xunkai Li, Yinlin Zhu, Rong-Hua Li, Guoren Wang
The paper introduces a self‑localizing MIMO beam‑mapping framework that builds a hierarchical wireless memory using sparse channel state information (CSI) without explicit location labels. It employs beam‑domain RSS as compact inputs, a dual‑scale extractor for angular and temporal dependencies, and a hybrid temporal encoder to infer physical anchors that index a structured radio map. The radio‑map embedding enables continuous updates and full‑CSI reconstruction, yielding over 30% better anchor recovery and more than 20% channel‑capacity gains in NLOS beam tracking compared to Kalman‑filter methods.
By Wangqian Chen, Junting Chen, Shuguang Cui
arXiv:2602. 06699v2 Announce Type: replace-cross Abstract: We propose a variational quantum implementation of self-attention (QSA)-the core operation in transformers and large language models-which predicts future elements of a sequence by forming overlap-weighted combinations of past data.
By Alessio Pecilli, Matteo Rosati
The study evaluates whether Earth‑observation foundation models encode geographic location information by attempting to predict coordinates from their embeddings. Using 284 verified European solar farms, the authors tested Tessera v1, Tessera v1.1, and AlphaEarth, finding that all three models contain recoverable geographic data. AlphaEarth showed the strongest correlation between embedding distance and geographic distance, while both Tessera variants outperformed Sentinel‑2 controls, suggesting that geographic information should be considered when auditing such models.
By Peiwen Zhang, Kristie Hu, Jovana Knezevic, Shunde Yin, Kyle Gao
The paper presents a hybrid CNN–state‑space–attention backbone designed for 12‑lead ECG classification, combining early waveform tokenization, mixed temporal dynamics modeling, and late global attention. It introduces an ECG‑oriented Joint‑Embedding Predictive Pretraining (JEPA) that samples span masks at latent resolution and predicts clean latent targets via a momentum encoder, avoiding waveform reconstruction. Experiments on CPSC2018, Chapman‑Shaoxing, and PTB‑XL, with pretraining on ~350K unlabeled CODE‑15 recordings, demonstrate strong supervised baselines and improved transfer, especially in low‑label scenarios and with LoRA adaptation.
By Yakoub Bazi, Sarah Aljuhani, Mohamad M. Al Rahhal, Mansour Zuair, Naif Alajlan
SALI (Shot-Aware Late Interaction) is a new method for text-to-video retrieval that addresses the loss of relational information when videos are represented by a single embedding. It extracts the subject and object from a query sentence and matches their text embeddings against each visual shot embedding of a video clip using a greedy max or optimal transport operator, with a film-grammar penalty added during fine‑tuning. Built on CLIP4Clip‑meanP, SALI maintains overall recall on Condensed Movies and ActivityNet while significantly improving R@1 for multi‑shot relation queries, achieving the largest gains among compared methods and modestly improving performance on MSR‑VTT.
By Toya Oyama, Rainer Lienhart, Shin'ichi Satoh
LeafTrackNet is a deep learning framework that combines a YOLOv10-based leaf detector with a MobileNetV3-based embedding network to track individual leaves over time. The authors introduce CanolaTrack, a large benchmark dataset of 5,704 RGB images with 31,840 annotated leaf instances from 184 canola plants. When evaluated without prior fine‑tuning, LeafTrackNet outperforms existing methods on CanolaTrack, KOMATSUNA, and MSU‑PID datasets, achieving HOTA scores of 88.03, 87.33, and 74.20 respectively.
By Shanghua Liu, Majharulislam Babor, Christoph Verduyn, Breght Vandenberghe, Bruno Betoni Parodi, Cornelia Weltzien, Marina M. -C. H\"ohne
The paper introduces the Generalized Graph Variational Autoencoder (GGVA), which replaces the Kullback–Leibler divergence in the standard variational graph autoencoder with any member of the Rényi–Tsallis family of order $q$. The authors show that for $q<1$ the Tsallis divergence is bounded, whereas the KL and Rényi divergences are unbounded, and that this boundedness can significantly increase the amount of posterior information retained—up to 49× more than the VGAE on several benchmark graphs. Experiments demonstrate that the GGVA’s retained information improves node classification performance, though it does not improve link‑prediction accuracy and only delays, rather than prevents, posterior collapse.
By Kleyton da Costa, Bernardo Modenesi, Ivan F. M. Menezes, Helio Lopes
The study investigates how behavioural biometric templates degrade over time by collecting a longitudinal dataset of 40 fixed passwords typed weekly for eight weeks. Four matching mechanisms—scaled-Manhattan, gradient-boosted classifier, recurrent embedding, and Transformer—were evaluated under a subject-disjoint protocol, revealing that error rates increase steadily with the enrolment-to-query gap, yet the choice of mechanism has a larger impact on accuracy than the ageing rate. The results show that while ageing is systematic, it does not reorder the relative performance of the mechanisms, suggesting that re-enrolment scheduling rather than matcher selection should manage ageing.
By Simon Parkinson, Saad Khan, Na Liu, Qing Xu
The paper presents a new computational framework for modelling organisation-level semantic identity using longitudinal textual data. It combines semantic representation learning, graph-based modelling, and temporal analysis to create interpretable semantic fingerprints that capture diversity, concentration, connectivity, novelty, and community composition. The framework is validated on a corpus of K‑pop lyrics from major South Korean entertainment companies, revealing distinct, evolving semantic identities that are statistically robust and reproducible.
By Brinda Murali Krishna, Oktay Karaku\c{s}, Can Eyupoglu
The paper introduces a coupled query‑key transformation that jointly evolves queries and keys via an invertible coupling before the standard dot‑product scoring in attention mechanisms. Implemented as a lightweight alternating affine map, the coupling is added on top of existing attention methods and preserves the original softmax and architecture. Experiments on WikiText‑103 show that coupling improves performance when combined with Differential Attention, query‑key normalization, and Multi‑Token Attention, especially at larger model scales, while its standalone benefit diminishes with size.
By Barak Gahtan, Alex M. Bronstein
The study introduces TRACER, a Transformer-based model that uses contrastive event representation to predict timelines leading to heart failure hospitalizations from low-resolution, irregularly sampled telemonitoring data. TRACER incorporates time-aware embeddings, contrastive pre‑training for anomaly detection, and independent binary classifiers, and was evaluated on biomarker sequences from 276 heart failure patients. The model achieved 66.7% accuracy in predicting hospitalization timelines with a 7.9% overestimation, outperforming other tested models by reformulating training as an event detection problem.
By Erik Aerts, Yinan Yu, Annika Rosengren, Michael Fu, Martin Lindgren, Falk Dippel, Martin Adiels, Helen Sj\"oland
The paper "Neuro-symbolic AI for Industrial Configuration" discusses how Large Language Models (LLMs) fall short for industrial product configuration due to their probabilistic nature, which conflicts with the need for syntactically valid, semantically consistent outputs that align with extensive feature and rule knowledge bases. It proposes Neuro-symbolic (NeSy) AI as a promising solution, outlining three integration strategies—hybrid inference, hybrid fine‑tuning, and hybrid training—and presents a taxonomy of these approaches. The authors describe their efforts to implement a NeSy-based configuration copilot, derive practical design choices for trustworthy AI deployment in engineering settings, and highlight key research challenges, especially scaling NeSy methods from academic prototypes to full‑scale industrial configurators.
By Danilo Valerio, Philipp Kogler, Stefan Bischof, Thomas Hubauer, Huzefa Rangwala
BiGraph-Diffuse is a large‑scale diffusion language model designed for mental health counseling, addressing two key limitations of existing AI dialogue systems: the lack of bidirectional understanding for progressive disclosure and the inadequate use of relational clinical knowledge. It pairs this diffusion model with BiGraph‑RAG, a graph‑structured retrieval approach that uses lightweight entity extraction and semantic linking to preserve inferential pathways from symptoms to underlying causes without incurring LLM token costs during indexing. Experiments and theoretical analysis demonstrate the effectiveness of this mutually reinforcing architecture.
By Yuxiang Cheng, Quanwei Tang, Lvhui Lu, Dong Zhang, Shoushan Li, Erik Cambria
The paper presents an explainable hate‑speech detection framework that combines DistilBERT embeddings, a Bi‑LSTM network, and an attention mechanism to capture contextual and sequential information. It uses LIME to highlight influential text features, providing transparency in predictions. Evaluated on two benchmark datasets for both binary and multi‑class tasks, the model achieves F1‑scores of 96.78%–99.53% for binary classification and 94.99%–97.00% for multi‑class classification, outperforming existing baselines.
By Rameesha Zia, Muhammad Shahid Iqbal Malik
The paper presents an inference-only pipeline that extends the frozen NER model MahaNER‑BERT to document‑level prediction using overlapping sliding windows, eliminating the need for retraining or architectural changes. The approach is evaluated on six document‑level corpora derived from the MahaNER test set, employing two repetition strategies (Normal Repeat and Random Repeat) at three length levels and various window configurations. Results show the model maintains a macro F1‑score of up to 0.8902 with minimal variation, outperforming non‑windowed methods by avoiding boundary‑fragmentation errors and achieving more stable document‑level performance.
By Hariom Ingle, Ronit Ghode, Ishwari Gondkar, Jidnyasa Harad, Ravindra Murumkar, Raviraj Joshi
The paper introduces DeepX-GAN, a deep generative model that captures spatial dependence in rare climate extremes. It can simulate statistically plausible unseen heat extremes—both direct-hit and near-miss events—beyond the observed record. Applied to the Middle East and North Africa, the model shows that unseen heat extremes disproportionately affect vulnerable countries and that future warming could create new persistent hotspots, underscoring the need for spatially adaptive resilience planning.
By Xinyue Liu, Xiao Peng, Shuyue Yan, Yuntian Chen, Dongxiao Zhang, Zhixiao Niu, Hui-Min Wang, Xiaogang He
The paper introduces RQ-Reg, a residual‑quantization framework for predicting continuous values in recommender systems. It decomposes target values into a sequence of quantization codes, autoregressively refining predictions from coarse to fine granularity, and incorporates an ordinal‑aware objective to align embeddings with target order. Experiments on watch‑time, LTV, and a large‑scale online A/B test for GMV demonstrate competitive performance and strong generalization across diverse prediction tasks.
By Runpeng Cui, Zhipeng Sun, Chi Lu, Peng Jiang
The study investigates whether documents initially classified as noise in embedding-based topic models can be identified as precursors to emerging topics. By labeling documents based on their future trajectories and measuring confidence across multiple embedding models, the authors find that anticipatory outliers are predictable at publication time, achieving an F1 score above 0.90 on high-consensus subsets and 0.76–0.80 in chronological evaluation. The predictive power largely stems from geometric features that capture each outlier’s position in embedding space.
By Evangelia Zve, Gauvain Bourgne, Jean-Gabriel Ganascia