AI News

Sleep EEG Signal Criticality as a Non-Invasive Predictor of Cognitive Decline in Dementia (arxiv.org)

RAT: Reference-Augmented Training for ASV Anti-Spoofing (arxiv.org)

Non-linear mechanical field reconstruction coupling recurrent neural networks with physics-informed graph neural networks (arxiv.org)

Ethical and Technical Limits of Deepfake Speech Datasets (arxiv.org)

What Do Deepfake Speech Detectors Actually Hear? (arxiv.org)

Task Robustness via Re-Labelling Vision-Action Robot Data (arxiv.org)

A Constrained Natural-Language Interface for Variational Multi-Physics Finite Element Simulations in FEniCS (arxiv.org)

Density Field State Space Models: 1-Bit Distillation, Efficient Inference, and Knowledge Organization in Mamba-2 (arxiv.org)

Democratising Camera Trap AI: An Open-Source Model for Detecting UK Mammals (arxiv.org)

Generative Explainability for Next-Generation Networks: LLM-Augmented XAI with Mutual Feature Interactions (arxiv.org)

Generative Archetype-Grounded Item Representations for Sequential Recommendation (arxiv.org)

Hidden Consensus:Preference-Validity Compression in Human Feedback (arxiv.org)

Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias Correction (arxiv.org)

From Data Heterogeneity to Convergence: A Data-Centric Review of Federated Learning (arxiv.org)

Recoverable but Not Stationary:Local Linear Structures in Weights and Activations (arxiv.org)

A Reliable Fault Diagnosis Method Based on Belief Rule Base Consider Robustness Analysis (arxiv.org)

CLP: Collocation-Length Prediction for Zero-Loss Adaptive Multi-Token Inference (arxiv.org)

Provenance Tracking in AI Compilers through the Lens of Coalgebra (arxiv.org)

Optimizing 2D Input Representations and Sub-phase Fusion Strategies for Differential Diagnosis of Asthma and COPD Using CNN- and GRU-Based Networks (arxiv.org)

Understanding and mitigating the risks of OpenClaw for non-technical users: A practical guide with Skill (arxiv.org)

Structured Adaptive Tensor Prediction for Streaming Data (arxiv.org)

Decision-Making under Combinatorial Risk (arxiv.org)

Discovering Interpretable Multi-Parameter Control Policies for Evolutionary Algorithms Using Deep Reinforcement Learning (arxiv.org)

Ambiguous Strategic Classification (arxiv.org)

Compositional Generative Modeling from Decentralized Data (arxiv.org)

Quality Is Not a Safety Proxy Under Quantization (arxiv.org)

Unsupervised Style Representation Learning for AI-Text Detection via Paraphrase Inversion (arxiv.org)

What makes a harness a harness: necessary and sufficient conditions for an agent harness (arxiv.org)

Emotion Profiling in LLM-Based Literary Translation: Systematic Shifts Across MT and Post-Editing (arxiv.org)

MetaPlate: Counterfactual-Guided RAG-LLM Tool for Personalized Food Recommendation and Hyperglycemia Prevention (arxiv.org)

FedSteer: Taming Extreme Gradient Staleness in Federated Learning with Corrective Projections and Caching (arxiv.org)

BiWM: Advancing Open-Source Interactive Video World Models with Bidirectional Autoregression (arxiv.org)

Fisher-Guided Progressive Parameter Selection for Adaptive Fine-Tuning (arxiv.org)

Integral Field Unit Spectroscopy with One Fiber (arxiv.org)

Density Ridge Selective Prediction for LLM and VLM Hallucination Detection under Calibration Label Scarcity (arxiv.org)

An Improved Generative Adversarial Network for Micro-Resistivity Imaging Logging Restoration (arxiv.org)

Improving Text-Instance Alignment Of Foreground Conditioned Out-Painting Via Customized Concept Embedding (arxiv.org)

Exploration of Foundation Model-Based Robots in Patient and Elderly Care (arxiv.org)

YUBI: Yielding Universal Bidigital Interface for Bimanual Dexterous Manipulation at Scale (arxiv.org)

Detecting Knowledge Gaps from Conversational AI Interactions Using Curriculum Prerequisite Graphs (arxiv.org)

Spatial-Omni: Spatial Audio Understanding Integration in Multimodal LLMs via FOA Encoding (arxiv.org)

Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models (arxiv.org)

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation (arxiv.org)

Dep-LLM: Training-Free Depression Diagnosis via Evidence-Guided Structured Multi-factor with Reliable LLM Reasoning (arxiv.org)

Beyond APIs: Probing the Limits of MLLMs in Physical Tool Use (arxiv.org)

Earth-OneVision: Extending Remote Sensing Multimodal Large Language Models to More Sensor Modalities and Tasks (arxiv.org)

A Unified Siamese Learning Framework for Zero-Day Anomaly Detection and Classification in Optical Networks (arxiv.org)

Pose-ICL: 3D-Aware In-Context Learning for Pose-Controllable Subject Customization (arxiv.org)

Learning Entropy and Spatial Adaptation Dynamics of Multilayer Perceptrons for Structural Point Extraction (arxiv.org)

A Continuous-Time Markov Chain Framework for Insertion Language Models (arxiv.org)