A one-class anomaly detector trained on normal behavior of CVEs sharing a CWE class can generalise to unseen CVEs within the same class, but effectiveness varies by CWE family. The CWE-307 detector achieves F1 = 0.6976 at 5% false positive rate, while CWE-89 and CWE-434 perform poorly, with F1 ≤ 0.21. Cross-CVE transfer is direction-dependent and driven more by the breadth of the source normal profile than the CWE category.
This paper introduces Text2DSL, a distinct task of generating domain-specific language code from natural language. Using the PolkitBench dataset of 4,204 validated pairs, it shows that structured context—such as BNF grammar and API specs—boosts syntactic and structural validity and CodeBLEU scores by 60% to 95% across different LLM models, without fine-tuning.
Baidu has released Unlimited-OCR, a model that transcribes dozens of pages in a single forward pass using Reference Sliding Window Attention (R-SWA). It builds on DeepSeek-OCR, inheriting its encoder, image compression, and MoE architecture, with only 500M active parameters per token. The model achieves 93.92% accuracy on OmniDocBench v1.6, outperforming DeepSeek-OCR's 87.01% on v1.5, though vendor-reported results warrant independent validation.
PaperClaw is a multi-agent system that autonomously conducts research from field selection to paper publication. It uses a validated, iterative propose-test-reflect loop, grounded in real references and runnable results, and supports human-in-the-loop refinement at any stage. Evaluation shows it produces strong papers both autonomously and with human oversight.
This paper proposes an optimal subsampling scheme in reproducing kernel Hilbert spaces, based on asymptotic analysis of an empirical risk minimizer with Horvitz-Thompson reweighting. The scheme, derived via the trace of the covariance operator, is shown to be implementable via plug-in and performs well on synthetic and real-world datasets.
TeaNet, a task-enhanced augmentation network, reconstructs randomly masked spectra to generate augmented samples that preserve original spectral features while introducing domain-specific variations. This approach enables deep neural networks to identify discriminant wavenumbers more effectively, outperforming CNNs by 17% in challenging synthetic scenarios and offering improved interpretability in few-shot learning tasks.
Topological Neural Dynamics (TND) introduces a neuron-wise framework for sequence modeling, where each neuron evolves independently through a directed graph structure. In a single-player Pong behavior cloning task, TND achieves a mean of 17.47 consecutive catches per round, surpassing all baseline models by more than three times.
NASDAQ addresses low-dimensional observation challenges in reinforcement learning by normalizing observation spaces to balance reconstruction losses. It integrates value learning with short-term value and next observation prediction, achieving competitive or superior performance with less training time across domains.
We propose a diagnostic workflow to reveal behavioral variation in multi-objective reinforcement learning policies. The method highlights differences in policy trajectories beyond expected returns, offering quantitative and visual tools for policy inspection. Validated on grid worlds and scaled to continuous control tasks, it effectively captures behavioral diversity under increasing complexity.
MedTS-TTT introduces a test-time training framework for medical time series classification. Built on CLSA-TTT and a Gated Convolutional Backbone, it enables rapid, single-step adaptation without iterative optimization. On four public datasets, it achieves 11 top-1 rankings out of 12 evaluations across nine baselines and three metrics.
KaLM-Reranker-V1 is a fast but not late-interaction reranker that decouples query and passage computation while maintaining strong relevance modeling through cross-attention. It achieves state-of-the-art performance on BEIR, outperforms industrial models like Qwen3-Reranker, and shows excellent results on MIRACL and LMEB, with the 0.27B Nano model remaining competitive against 7-12B models.
A Kolmogorov--Smirnov test on reservoir computer output weights detects regime changes in nonlinear systems. The method distinguishes visually identical attractors, resolves parameter drifts seven times smaller than deep-learning baselines, and identifies ventricular flutter in ECG recordings.
Sea-Scan uses machine learning to detect and localize dark vessels from unlabeled data. It achieves a 97.8% detection rate with only a 1.98% false-trigger rate, using weak supervision from imperfect AIS labels.
Ramanujan Propagation uses Ramanujan graphs to reduce over-squashing in Graph Neural Networks by ensuring non-negative resistance curvature. The method preserves local connectivity while enabling efficient long-range information flow, outperforming nine state-of-the-art rewiring techniques.
This paper explores Reservoir Computing as a feature-free method for raw audio signal classification. It shows that parallel deep reservoir architectures outperform shallow and sequential ones in accuracy while maintaining low complexity, enabling efficient, low-power audio processing with minimal preprocessing.
A new framework uses public infrastructure and OpenStreetMap data to reconstruct urban power grid topology from transmission to building-level connections. It successfully maps the grid for 7,330 buildings in Oslo's Alna district, enabling detailed power system analysis such as flow optimization and resilience studies.
SOHET introduces a hierarchical transformer architecture with event-type-specific tabular encoders and self-supervised pre-training. It outperforms existing methods by 5.8% on Booking.com's fraud detection task and achieves state-of-the-art results on 6 out of 8 EBES benchmark tasks.
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.