{"total":23,"items":[{"citing_arxiv_id":"2605.21882","ref_index":50,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Thermo-VL: Extending Vision-Language Models to Thermal Infrared Perception","primary_cat":"cs.CV","submitted_at":"2026-05-21T01:43:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Thermo-VL augments a frozen Molmo-7B VLM with a trainable thermal encoder and prompt-conditioned dual-attention fusion to improve cross-spectrum visual reasoning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.19366","ref_index":85,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Accurate, Efficient, and Explainable Deep Learning Approaches for Environmental Science Problems","primary_cat":"cs.LG","submitted_at":"2026-05-19T04:58:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"The work introduces WaLeF/FIDLAr for flood forecasting, CoDiCast for probabilistic weather, and Hypercube-RAG for explainable environmental QA, claiming superior accuracy, efficiency, and interpretability over baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17684","ref_index":25,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"EGI: A Multimodal Emotional AI Framework for Enhancing Scrum Master Real-time Self-Awareness","primary_cat":"cs.AI","submitted_at":"2026-05-17T22:55:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"EGI integrates four existing AI components for real-time multimodal emotion monitoring and feedback in simulated agile meetings, reporting 10% WER and improved self-awareness for Scrum Masters.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16570","ref_index":242,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"A Cubing Strategy for Identifying Stable Hyperparameter Regions for Uncertainty Quantification in Spatial Deep Learning","primary_cat":"stat.CO","submitted_at":"2026-05-15T19:18:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A recursive cubing framework identifies stable hyperparameter regions for MC dropout uncertainty quantification in spatial deep learning and produces competitive or superior predictive intervals versus a statistical baseline on simulations and land-surface temperature data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10359","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning-Based Spectrum Cartography in Low Earth Orbit Satellite Networks: An Overview","primary_cat":"cs.NI","submitted_at":"2026-05-11T11:05:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"The paper overviews attention-based learning methods for spectrum cartography in LEO satellite networks to enable adaptive fusion of heterogeneous measurements for inference and resource allocation.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"spatial-inference problems, requiring adaptive, context-aware mechanisms for information selection and fusion. However, the irregular and reliability-varying nature of measurements, driven by orbital geometry and propagation conditions [25], [26], poses challenges for both model-driven methods and learning architectures with predefined structures, such as con- volutional neural networks (CNNs) [27] and graph neural net- works (GNNs) [28]. This motivates learning-based approaches that operate directly on unstructured measurement sets, en- abling adaptive inference beyond grid- or graph-constrained representations. arXiv:2605.10359v1 [cs.NI] 11 May 2026 JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 2 SC in LEO Satellite Networks"},{"citing_arxiv_id":"2605.08196","ref_index":134,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Survey on Disaster Management Datasets for Remote Sensing Based Emergency Applications","primary_cat":"cs.CV","submitted_at":"2026-05-05T19:05:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"A survey providing an overview of publicly available image-based datasets for ML/DL-based disaster management pipelines covering pre-disaster, during, and post-disaster phases.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Simulations:Obtaining sufficient real-world data for model- ing certain disaster scenarios can be challenging. For instance, tasks such as building damage assessment or flood mapping often require bi-temporal satellite imagery which may not always be available. Simulated data becomes particularly valuable in these contexts where real-world labeled data is scarce. Ou et al. [134] demonstrated a method for generating synthetic remote sensing images of disaster zones using natural language descriptions, leveraging pre-trained large language models (GPT-4) for captioning and Stable Diffusion for text- 4https://www.goes-r.gov/products/baseline-fire-hot-spot.html 5https://modis-land.gsfc.nasa.gov/burn.html 6https://www.mtbs.gov/"},{"citing_arxiv_id":"2605.02558","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TemPose-TF-ASF: Two-Stage Bidirectional Stroke Context Fusion for Badminton Stroke Classification","primary_cat":"cs.CV","submitted_at":"2026-05-04T13:09:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"TemPose-TF-ASF fuses bidirectional stroke context in two stages to raise accuracy and Macro-F1 for badminton stroke classification over baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.13567","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Comparison of window shapes and lengths in short-time feature extraction for classification of heart sound signals","primary_cat":"cs.SD","submitted_at":"2026-04-15T07:28:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"A 75 ms Gaussian window for segmenting phonocardiography signals yields the highest biLSTM classification accuracy among tested shapes and lengths, outperforming rectangular windows and a baseline method.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"principal component analysis and the wavelet decomposition are exploited for extr action of distinct features from PCG signals in [23], [24]. In [25], short-time features of the wavelet analysis and the time-frequency representation of PCG signals were evaluated independently using a multilayer perceptr on composed of either a single hidden layer or a couple of hidden layers. The feedforward neural network is used in [26], [27] to classify PCG signals using features computed from the temporal, spectral, and spectro-temporal representations of the signals. The convolutional neural networks (CNNs) have made a rap id progress in the classification of PCG signals [28], [29]. PCG signals are classified using CNNs with featur es of wavelet coefficients in [30], and of MFCCs in [31]."},{"citing_arxiv_id":"2604.11817","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"QMC-Net: Data-Aware Quantum Representations for Remote Sensing Image Classification","primary_cat":"quant-ph","submitted_at":"2026-04-10T19:28:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"QMC-Net maps per-band statistics to customized quantum circuit hyperparameters and achieves 93.80% and 99.34% accuracy on EuroSAT and SAT-6, outperforming classical and monolithic quantum baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08461","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"OVS-DINO: Open-Vocabulary Segmentation via Structure-Aligned SAM-DINO with Language Guidance","primary_cat":"cs.CV","submitted_at":"2026-04-09T16:57:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"OVS-DINO structurally aligns DINO with SAM to revitalize attenuated boundary features, achieving SOTA gains of 2.1% average and 6.3% on Cityscapes in weakly-supervised open-vocabulary segmentation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.03764","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Automated Attention Pattern Discovery at Scale in Large Language Models","primary_cat":"cs.LG","submitted_at":"2026-04-04T15:32:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AP-MAE reconstructs masked attention patterns in LLMs with high accuracy, generalizes across models, predicts generation correctness at 55-70%, and enables 13.6% accuracy gains via targeted interventions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.03637","ref_index":17,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SAGE-GAN: Towards Realistic and Robust Segmentation of Spatially Ordered Nanoparticles via Attention-Guided GANs","primary_cat":"cs.CV","submitted_at":"2026-04-04T08:27:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"SAGE-GAN integrates a self-attention U-Net into a CycleGAN framework to generate realistic synthetic electron microscopy image-mask pairs that augment training data for nanoparticle segmentation without human labeling.","context_count":1,"top_context_role":"background","top_context_polarity":"unclear","context_text":"instance segmentation of titanium dioxide particles in the form of agglomerates in scanning electron microscopy. Nanomaterials11(4), 968 (2021) [16] Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Hein- rich, M., Misawa, K., Mori, K., McDonagh, S., Ham- merla, N.Y., Kainz, B., Glocker, B., Rueckert, D.: At- tention u-net: Learning where to look for the pancreas (2018), https://arxiv.org/abs/1804.03999 [17] O'Shea, K., Nash, R.: An introduction to convolu- tional neural networks (2015), https://arxiv.org/abs/ 1511.08458 [18] Ronneberger, O., Fischer, P., Brox, T.: U-net: Con- volutional networks for biomedical image segmentation (2015), https://arxiv.org/abs/1505.04597 [19] Shah, A., Schiller, J.A., Ramos, I., Serrano, J., Adams, D.K., Tawfick, S., Ertekin, E."},{"citing_arxiv_id":"2604.00809","ref_index":25,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Revisiting Human-in-the-Loop Object Retrieval with Pre-Trained Vision Transformers","primary_cat":"cs.CV","submitted_at":"2026-04-01T12:18:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Pre-trained ViT representations combined with active learning and targeted design choices for annotations and selection improve object class retrieval in multi-object scenes.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"concept, emphasizing retrieval over classification. Multi-Object Image Understanding in the Context of Self-supervised Image Retrieval.Retrieving a specific object from multi-object images with Revisiting Human-in-the-Loop Object Retrieval with Pre-Trained ViTs 5 cluttered backgrounds requires selecting an appropriate representation. Global descriptors [30], obtained from CNN [25] or ViTs [12] last layers, compress the entire image into a single vector, capturing overall scene context efficiently but often including irrelevant background and other objects, overlooking small or occluded objects of interest. Local descriptors, derived from CNN activations or ViT patch tokens, focus on specific regions or patches, retaining fine-grained"},{"citing_arxiv_id":"2602.23342","ref_index":43,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"AlayaLaser: Efficient Index Layout and Search Strategy for Large-scale High-dimensional Vector Similarity Search","primary_cat":"cs.DB","submitted_at":"2026-02-26T18:48:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"AlayaLaser uses a SIMD-optimized on-disk graph layout plus caching and search strategies to outperform prior on-disk ANNS systems and match or exceed in-memory performance on large high-dimensional datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.12433","ref_index":34,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Temporal Data and Short-Time Averages Improve Multiphase Mass Flow Metering","primary_cat":"eess.SP","submitted_at":"2026-01-18T14:39:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Short-time averages within experiments plus temporal-preserving models like CNNs cut multiphase mass flow metering errors to 4.3% MAPE on air-water-oil data, outperforming single-averaged baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.20657","ref_index":277,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Intelligent Agents with Emotional Intelligence: Current Trends, Challenges, and Future Prospects","primary_cat":"cs.HC","submitted_at":"2025-10-11T07:40:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":2.0,"formal_verification":"none","one_line_summary":"A holistic survey of affective computing for intelligent agents covering emotion understanding via multimodal data, affective cognition, emotional expression synthesis, key challenges, and future directions emphasizing generative technologies.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"expressions, addressing challenges posed by image noise, such as lighting variations, facial angles, and dis- tortions. To make the model more intelligent and adaptable, it applies data augmentation tricks including image rotations, brightness shifts, and strategic cropping, mimicking real-world variations. State-of-the-art deep networks, such as CNNs[276], ResNet[277], and VGG[278], enhanced with attention mechanisms[279], facilitate the model to focus on the most informative facial regions, even under poor conditions. By integrat- ing transfer learning with auto-encoder-based noise reduction, the model effectively learns from high-quality features while filtering out unwanted distortions. This boosts accuracy and enhances the reliability of emo-"},{"citing_arxiv_id":"2509.12266","ref_index":22,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Genome-Factory: A Library for Tuning, Deploying, and Interpreting Genomic Foundation Models","primary_cat":"q-bio.GN","submitted_at":"2025-09-13T03:31:55+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Genome-Factory is an open-source Python library that integrates data pipelines, model tuning, inference, benchmarks, and biological interpretation for genomic foundation models.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2508.08441","ref_index":64,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"SpectraLLM: Uncovering the Ability of LLMs for Molecular Structure Elucidation from Multi-Spectral Data","primary_cat":"q-bio.QM","submitted_at":"2025-08-04T13:33:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SpectraLLM is an LLM fine-tuned to predict small-molecule structures from single or multiple spectra, reporting state-of-the-art results on four public benchmarks with gains from multi-modal input.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2506.14980","ref_index":34,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Advances in Compliance Detection: Novel Models Using Vision-Based Tactile Sensors","primary_cat":"cs.CV","submitted_at":"2025-06-17T21:10:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"LRCN and Transformer models using GelSight tactile images improve compliance prediction accuracy over baselines and show that objects harder than the sensor are harder to estimate.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2411.11896","ref_index":28,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"HeartBERT: A Self-Supervised ECG Embedding Model for Efficient and Effective Medical Signal Analysis","primary_cat":"eess.SP","submitted_at":"2024-11-08T14:25:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"HeartBERT applies self-supervised pretraining on a RoBERTa architecture to ECG signals, producing embeddings that enable strong performance on sleep staging and heartbeat classification with smaller labeled datasets and fewer parameters than baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2411.02622","ref_index":11,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"AdaProb: Efficient Machine Unlearning via Adaptive Probability","primary_cat":"cs.LG","submitted_at":"2024-11-04T21:27:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"AdaProb performs machine unlearning by substituting final-layer output probabilities with optimized uniform pseudo-probabilities and updating model weights.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2402.07619","ref_index":26,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Developing a Multi-variate Prediction Model For COVID-19 From Crowd-sourced Respiratory Voice Data","primary_cat":"cs.SD","submitted_at":"2024-02-12T12:52:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"HuBERT reaches 86% accuracy and 0.93 AUC detecting COVID-19 from 893 voice samples in the Cambridge COVID-19 Sound database.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2309.12063","ref_index":10,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Suppression of Neutron Background using Deep Neural Network and Fourier Frequency Analysis at the KOTO Experiment","primary_cat":"hep-ex","submitted_at":"2023-09-21T13:33:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Using a deep CNN and Fourier frequency analysis on calorimeter data, the KOTO experiment suppressed neutron background by a factor of 5.6×10^5 while maintaining 70% efficiency for the signal decay.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}