This study enhances maritime security using AI and computer vision, comparing six deep learning architectures on 6,468 images. The Vision Transformer achieved 100% accuracy with the lowest error rates and fastest processing, demonstrating AI's potential for surveillance, border protection, and autonomous navigation.

RAMS is a lightweight runtime controller for object detection on embedded edge devices, dynamically selecting among YOLOv8 tiers (NANO/SMALL/MEDIUM) based on resource pressure and detection results. On Jetson Orin, the safety2 policy achieves 3.41 ms mean latency (5.6x faster than fixed MEDIUM) while retaining 74% proxy accuracy. Detection-conditioned switching improves SWAS by up to 47.3% under heavy load.

ReportQA is a clinical and flexible radiology report evaluation framework using QA pairs and LLM-as-judge to compute QAScore, addressing limitations of existing NLG and CE metrics. Experiments show QAScore aligns better with radiologist judgments, and question-driven inference outperforms report-based paradigms.

This study evaluates LSTM, TCN, and Transformer models on the WESAD dataset for multimodal emotion recognition using wrist and chest sensors. Transformer achieved highest accuracy in multimodal settings, TCN best on wrist-only. Ensemble late-fusion achieved 98.91% accuracy and 98.56% macro-F1.

This study re-evaluates online augmentation modules for web agents under a fixed inference budget, finding that AWM, ASI, and ReasoningBank do not provide significant advantages over a token-matched vanilla baseline that uses the same budget for additional actor steps. The baseline matches or surpasses all augmentation methods in success rate while often using fewer total tokens. The effect extends to enterprise knowledge-work tasks, and run-to-run variance is highlighted as a crucial evaluation metric.

Nemotron 3 Ultra is a 550B total/55B active parameter hybrid Mamba-Transformer MoE model by NVIDIA. Pre-trained on 20T tokens with 1M context, it achieves 6x higher throughput than open LLMs with on-par accuracy. Open-sourced on HuggingFace.

Introduces CoRA, a GRPO-based reinforcement learning framework that aligns model confidence with generated rationales, reducing misleading high-confidence answers. On datasets like MedQA, it reduces alignment error by up to 26.51% while maintaining accuracy and improving calibration.

Causal Transformers, while efficient for left-to-right decoding, struggle with arbitrary conditionals (e.g., text conditioned on both past and future tokens). The proposed AC-GPT introduces a simple modification to standard causal Transformers, enabling evaluation and sampling from arbitrary conditionals—including past, future, and mixed contexts—in a single forward pass. It preserves left-to-right ordering and next-token prediction, allowing fine-tuning of existing LLMs. Empirical results show it outperforms baselines on arbitrary conditional modeling without degrading standard performance.

Researchers propose 'Telegraph English,' a readable symbolic format for compressing context in multi-hop question answering. It outperforms matched-budget baselines, including coherent summaries, by 13-20 F1 points. The advantage does not increase with reasoning depth.

This paper presents the first study on the robustness of proof autoformalization models in Lean 4. It introduces global and local perturbations to test model faithfulness, finding that all seven evaluated models are sensitive to changes and mostly fail to reflect local perturbations faithfully.

PhoneHarness is a mixed-action benchmark and execution harness for studying phone-use agents on verifiable mobile workflows. It integrates GUI, CLI, and host-side tool actions, achieving a 75.0% pass rate, outperforming non-PhoneHarness settings by 12.9 percentage points, highlighting the importance of action-surface routing and verifiable execution.

Introduces CILN, a framework to generate instance-dependent label noise via controlled input corruptions, enabling explicit control over ambiguity sources. Demonstrates on CIFAR-10, MNIST, Adult that noise structure impacts algorithm behavior beyond noise rate.

This study applies machine learning to physiological data collected during exams to predict performance. Various models were compared, finding that while deep learning excels at complex patterns, simpler models like random forests can be more efficient and interpretable.

A comparative study of 19 graph neural network layers for trajectory prediction reveals that ARMA, Chebyshev, and topology-aware layers perform best. Key design principles include sum-based aggregation, multi-head attention, and differentiated hop weights.

This paper introduces a stateful ReAct agent built with LangGraph that avoids re-reading entire history at each iteration, cutting token costs by 90% in hyperparameter tuning and 52% in code optimization while maintaining performance. It provides a blueprint for practitioners to implement token-efficient autonomous experimentation. (Source: arXiv, June 2026)

This paper formalizes embedding model routing as an adversarial contextual linear bandit with low-rank experts, introduces a log-quadratic policy class for efficient online learning, and proposes the Hypentropy Policy Gradient (HPG) algorithm that achieves sublinear regret without curse of dimensionality.

GRASP is a novel multi-source transfer learning method that achieves superior knowledge integration with constant O(1) memory through sequential processing, parameter-wise gradient alignment, and iterative fine-tuning, outperforming ensemble methods on continual learning benchmarks.

The study proposes an α-FISP framework that balances actuarial and solidarity fairness through constrained optimization, with parameter α enabling a continuum from purely actuarial to purely solidarity pricing while ensuring solvency. Numerical experiments demonstrate computational tractability and alignment with heterogeneous U.S. state-level regulations.

This paper proposes GRAPE, a training framework that progressively exposes parameters and uses an adversarial spectral utilization score to guide capacity, improving PGD-20 robust accuracy from 51.70% to 56.94% on CIFAR-10 with 21.4% fewer parameters under matched compute.

QPILOTS is a method that steers the denoising process at inference time using Q-values without modifying the original policy. It projects intermediate noisy states to an estimate of the final clean action to compute critic gradients, avoiding instability from direct backpropagation. It achieves 90% average success rate across 50 offline-to-online RL tasks and outperforms prior inference-time approaches on simulated manipulation tasks using a VLA model.

This study introduces a foundation model-driven framework for cross-modal representation alignment between CT imaging and longitudinal EHR data, systematically evaluating four fusion strategies on pulmonary embolism mortality and cardiovascular disease outcome prediction tasks. Results show that contrastive multimodal fusion provides the most consistent improvements, while task-specific fusion strategies are crucial for robust generalization.

OSGuard is a dual-granularity benchmark for evaluating safety in computer-use agents under benign instructions. It includes an action-level benchmark for local guardrail decisions and a risk-augmented execution suite for end-to-end evaluation. Experiments show that current multimodal guardrails perform well on isolated action judgments but reveal gaps in reliable end-to-end safety.

Metric Match is a method for estimating correlation-based reliability metrics of LLM judges from limited human annotations. It selects a representative subset of samples for annotation, achieving a win-rate of 0.838 against random selection across four metrics and 15 datasets, reducing average estimation error by 18.7% and annotation needs by 32.5%. A medical case study showed savings of $1,041.67. The method also extends to reliability classification. Code is publicly available.

A new geometric framework identifies 'AI engrams'—identifiable memory traces in deep neural networks—by formalizing neuroscientific criteria into a constrained inverse problem. The closed-form estimator isolates individual memories from entangled parameters, enabling surgical composition or erasure via linear arithmetic without iterative optimization. Experiments from MLPs to LLMs demonstrate causal validity and scalability, bridging biological memory and representation learning.

Existing retrieval-augmented time series forecasting methods rely solely on numerical similarity, often failing under non-stationarity. This paper proposes SERAF, which performs dual retrieval over time series and their self-generated textual descriptions, effectively combining numerical and semantic information. Experiments on seven real-world datasets show superiority over baselines.

This research proposes a behavioral measure based on costly verification to quantify trust between AI agents. In a cooperative survival game, agents demonstrate trust by reducing verification of reliable teammates. Experiments with six frontier model snapshots show that larger models (e.g., Claude Opus 4.6, GPT-5.1) reduce verification by 60-85%, while smaller models show little adjustment. Trust recovery is slower than formation, and clustered failures prolong suspicion. Results suggest trust dispositions can be measured pre-deployment and governance should focus on calibration rather than maximal suspicion.

The paper extends structural causal models to relational settings where objects and relations vary, enabling reasoning about interventions and counterfactuals across unseen object combinations. It defines relational causal graphs, derives symbolic identification criteria, and proposes relational neural causal models.

DR-DCI is a retriever-steered Direct Corpus Interaction (DCI) framework that treats retrieval as an agent-callable action to dynamically expand a local workspace, achieving scalable and precise evidence resolution. Experiments show up to 73.3% accuracy on Browsecomp-Plus, outperforming raw DCI and BM25, and scaling stably to 20M documents.

This paper proposes a definition of good explanations inspired by counterfactual explanations, incorporating the interlocutor's prior beliefs, and explores its implications for AI explainability, particularly why LLM outputs are difficult to explain well.

Fog is a notes app for Apple devices that uses on-device AI to automatically organize notes into smart collections called Clouds. It ensures privacy with no third-party servers and syncs via iCloud.