A deep learning framework using multi-head attention and online learning accurately predicts repair durations by integrating categorical and numerical historical data. The model achieves 78% accuracy on real-world repair data from 2013 to 2020, outperforming feed-forward neural networks and random forests, with attention weights revealing key feature interactions.
Graph-of-Differences (GoD) introduces anatomy-structured difference alignment for medical image re-identification. It represents images as anatomy graphs, computes differences over matched anatomical regions, and anchors retrieval signals to homologous structures. GoD improves Rank-1 accuracy by 7.1 pp on fundus and 3.1 pp on CXR, with better generalization in zero-shot settings.
The paper proves that locally orthogonal directions in generative models guarantee latent factor identifiability without needing statistical independence or causal assumptions. Experiments with orthogonality-regularized normalizing flows confirm reliable recovery of true latent factors, challenging prior claims about unsupervised disentanglement impossibility.
ADualVUOT introduces a dual-encoder VAE with Continuous Normalizing Flows to improve latent representation flexibility in medical image segmentation. It uses Gaussian-Gromov-Wasserstein distance for domain alignment and adversarial augmentation to boost robustness, outperforming prior optimal transport-based methods on medical imaging benchmarks.
DCGC introduces a dual-attention convolution network and group-level contrastive learning to improve sparse tensor completion. The method captures complex cross-mode interactions and reduces vulnerability to data sparsity through self-supervised signals, outperforming state-of-the-art approaches on traffic and recommendation datasets.
The paper proposes a modular relational deep learning approach that decouples row encoding from graph message-passing. It introduces a transformer-based Universal Row Encoder that uses schema metadata to generate invariant row embeddings, enabling better generalization across databases and improving convergence on RelBench benchmarks.
Native space-based UNet pipelines outperform template space ones in subcortical segmentation, showing higher Dice scores and lower HD95 values for the Subthalamic Nucleus, Red Nucleus, and Substantia Nigra. Performance drops significantly when applied to 3T images, with synthetic 3T training data providing only modest gains, highlighting a persistent domain gap between 7T and 3T MRI.
A study validates a Cross-Correlation Function method to identify optimal temporal and depth lags between meteorological variables and soil moisture. Using satellite and meteorological data across seven agricultural plots in southeastern Spain, deep learning models achieved significant improvements: a per-pixel CNN reached R² = 0.877, while a CNN-LSTM hybrid achieved the highest overall performance with R² = 0.930. Subsurface depth information and meteorological features substantially enhanced estimation accuracy.
A formal proof shows no equivalence exists between adversarial risk and regularized risk in two-layer networks. Empirical results on Wide-ResNets confirm this impossibility persists in deeper, more expressive architectures.
A machine learning model developed using pre-colonoscopy clinical features predicts high-risk colorectal polyps in African Americans. The model, validated in a diverse urban cohort, uses demographic, lifestyle, and comorbidity data to identify patients at higher risk, with external validation conducted in 2023-2024.
A study introduces JS divergence in GRPO-style autoregressive text-to-image alignment, showing it effectively balances policy optimization and generation diversity. Experiments on LlamaGen and Janus-7B demonstrate JS divergence achieves top or competitive performance across metrics while preserving diverse outputs.
Hierarchical Block-Local Learning (HBLL) enables deep neural network training in O(log N) parallel time complexity, eliminating the need for full backpropagation. HBLL decomposes networks into hierarchically linked blocks and achieves competitive performance on vision and language tasks, with extensions to recurrent architectures.
The paper introduces Federated TGCN-A2C, a privacy-preserving framework that achieves 99.48% and 99.61% test accuracy on CICDDoS 2019 and TON-IoT benchmarks, outperforming Fed-Inforce-Fusion by 0.21 percentage points. It includes anomaly detection, digital twin-based scoring, adaptive action selection, and an enhanced honeypot layer, with all major attack classes achieving F1 scores above 0.92 and 0.94, respectively, and provides post-hoc explainability via SHAP, LIME, Grad-CAM, and counterfactual analysis.
A new framework using cross-lingual question answering reveals users' mental models of speech translation systems. Users develop stronger mental models with practice, especially with source language knowledge, relying on surface-level error cues. Providing speech transcriptions improves model development, showing cross-lingual question answering's potential in human-AI collaboration research.
AI-PAVE-Br uses large language models to enhance product attribute value extraction in Brazilian e-commerce. The system outperforms traditional NER methods, with a new Golden Set dataset providing a manually annotated benchmark for Portuguese product data.
DREAM uses autoregressive next-token prediction to supervise dense retrieval embedding training. It injects query-document similarity scores into a frozen LLM's attention heads, enabling gradient backpropagation for retriever optimization. DREAM outperforms baselines on BEIR and RTEB benchmarks across model scales.
CANDLE is a lightweight system that uses Connectionist Temporal Classification to deduplicate repeated characters in Arabic text, without relying on handcrafted rules or morphological analyzers. It achieves a Sentence Error Rate of 5.37% and reduces tokenizer fertility by up to 12.8%, lowering inference costs and improving context window usage.
Autonomous agents in e-commerce face a scarcity of trustworthy product information, not product matching. A proposed micro-transaction model allows agents to pay fractions of a cent to access verified data like service histories and test reports, with pricing and trust scored via reputation. This system prioritizes genuine product quality and real-time information acquisition over chatbot fluency.
L3Cube-MahaPOS introduces a gold-standard part-of-speech tagging dataset for Marathi, manually annotated with 32,354 sentences from news text. It includes a 16-tag Universal Dependencies scheme and benchmarks six model families, achieving 88.67% token-level accuracy and 81.67% macro-F1 on 15 tag classes using MahaBERT-v2.
We construct and release a large biomedical dataset with 1.88 million PMC articles. Analysis shows author-written abstracts vary in quality and alignment with source articles, enabling effective training-data selection. Training on high-quality subsets outperforms random sampling and matches larger random subsets on factuality metrics.