AI News

Bio-inspired Learning and Decision-Making with Probabilistic In-Memory Computing Hardware: Part 1 (arxiv.org)

When Synthetic Data Hurts: On Catastrophic Forgetting in Skill Retrieval for LLM Agents (arxiv.org)

Compute-Bounded Security Assurance - Coverage, Verification, and Response under Resource Constraints (arxiv.org)

Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents (arxiv.org)

Geometry Conditioning in an Embodied SLM: Training Controls and Robustness Diagnostics in a 0.8B Hybrid Model (arxiv.org)

AgentHijack: Visual Patch Attacks on Multimodal Computer-Use Agents (arxiv.org)

M3-Former: Multimodal Transformer with Mixture-of-Experts for Long-Term Vessel Trajectory Prediction (arxiv.org)

Empirical Evaluation of Data Poisoning Attacks in Supervised Learning (arxiv.org)

Weighted Empirical Risk Minimization for Machine Learning under Long-Range Dependence: Exact Pathwise Rates and Learning-Error Geometry (arxiv.org)

Positional task conditioning for scalable defect detection across product families in large product catalogs (arxiv.org)

Certifying Lower Bounds for Risk-Sensitive Reinforcement Learning under Adversarial State Perturbations (arxiv.org)

A Hilbert-Valued Functional Decomposition Framework for Explaining Time-Dependent Outputs (arxiv.org)

UBCL: A Reinforcement Learning Framework for Controllable and Diverse Player Behaviors (arxiv.org)

Story Imprinting: AI Assistants Absorb Traits from Human Characters They Resemble (arxiv.org)

Risk-Averse Decision Making with Multi-Level Reliability Guarantees (arxiv.org)

The Truth Was Never Gone: Perfect Aliasing in Compliant-Context Truth Probes (arxiv.org)

Measuring the Value of World-Model Updates: A Counterfactual Utility Protocol for Continual Adaptation (arxiv.org)

A distribution-free certification framework for trustworthy crash-severity prediction (arxiv.org)

Identifiability of Nonnegative Tensor Decompositions via Positive Scattering (arxiv.org)

CARTS: Contextual Autoregressive Rank Transcoding Steganography for Full-Capacity Keyed Text Encoding (arxiv.org)

ObstaDiff: Generalizable Diffusion Policy Learning via Obstacle-aware Representations (arxiv.org)

Temporal and Multimodal Deep Learning for Cyberattack Detection in LEO Satellite Systems (arxiv.org)

Semidefinite Programming for Quantum Channel Learning (arxiv.org)

Partial GFlowNet: Accelerating Convergence in Large State Spaces via Strategic Partitioning (arxiv.org)

Generalization Analysis of Distributed Kernel-based Robust Gradient Descent Algorithms (arxiv.org)

When More Is Not Better: Component Anti-Synergy in a P300 Speller (arxiv.org)

Near-Optimal Reinforcement Learning with Multi-Step Transition Lookahead (arxiv.org)

Published Unlearning Numbers Move Per Checkpoint, and Not Because the Removed Data Survives: An Audit of 263 Released Batch-Normalized Checkpoints (arxiv.org)

GEOSTEER: Geodesic Optimization for Activation Steering in Large Language Models (arxiv.org)

Artificial Intelligence Algorithms for the Detection of Pathologies Related to Lung Cancer through Image Analysis using Convolutional Neural Networks and Data Augmentation: a systematic mapping of the literature (arxiv.org)

Byzantine-Robust Federated Fire Detection with a Rotating Coordinator (arxiv.org)

Testing Between the Test Cases: Proving End-to-End Steering in Conditions You Never Drove (arxiv.org)

DiSCo: A Distribution-First Steering and Cultural Prior Evaluation Framework for Measuring Cultural Preference Bias in LLMs (arxiv.org)

SynCo: Synthetic Community-Aware Attributed Graph Generator for Graph Neural Network Benchmarking (arxiv.org)

Hierarchical and Permutation-Invariant Feature Transformation Learning via Policy-Guided Embedding Search (arxiv.org)

Sequence-Informed Geometric Evaluation of RNA 3D Structures (arxiv.org)

Numbat: Building and Verifying a Self-Contained Machine-Learning Stack (arxiv.org)

From Cycle Space to Cycle Manifold: Limits and Achievability of Blind False Data Injection Attacks (arxiv.org)

A Multi-Stage Rule-Chaining Framework for Compositional and Interpretable Cognitive Reasoning (arxiv.org)

A Station-Based Evaluation of Machine Learning-based Weather Forecasting Models in Northern Norway (arxiv.org)

An Empirical Measurement of Jailbreaking Evaluators (arxiv.org)

SoK: Privacy Attacks on Machine Learning via Explainable AI (arxiv.org)

TRACE: Training Reasoning Agents for Causal Exploration with Synthesized Rewards (arxiv.org)

Quantifying the Memorization-to-Generalization Transition: Scaling Laws and Phase Structure in Grokking (arxiv.org)

Adaptive Diffusion Freezing: Privacy-preserving Diffusion Models Against Membership Inference Attacks (arxiv.org)

On the Relation between Code Quality and Machine Learning Performance: A Large-scale Empirical Study (arxiv.org)

Understanding In-Context Multimodal Jailbreaks via Posterior Reweighting (arxiv.org)

PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving (arxiv.org)

MOONWALK: Mediating Operations with Intent-Evidence-Action Alignment Across Junior-Supervisor Review Workflows in Animation/VFX Pre-Production (arxiv.org)

Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization (arxiv.org)