arXiv AI
Jul 28
Not All LLM Reasoning is Visible in the Chain-of-Thought
arXiv:2607. 22925v1 Announce Type: cross Abstract: A key question for AI safety is whether a language model expresses all of its reasoning in its output tokens.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Jul 28
Adversarial Test-Hardening for AI-Written Code: An Instrument Autopsy and a Pre-Registered Causal Estimate of the Critic Loop
arXiv:2607. 23002v1 Announce Type: cross Abstract: Large language models increasingly write both code and the tests meant to check it; coverage records what ran, not what was verified.
arXiv AI
Jul 28
Traceable LLM Reasoning for Fake-Order Fraud Detection
arXiv:2607. 23075v1 Announce Type: cross Abstract: Detecting fake-order fraud at scale remains a critical challenge for large online-to-offline (O2O) service platforms, as existing approaches often rely on expert-designed features, produce black-box decisions, and provide limited interpretability.
arXiv AI
Jul 28
Through the Bottleneck: How Multi-head Latent Attention Separates Content from Position in Language Models
arXiv:2607. 23054v1 Announce Type: cross Abstract: Multi-head Latent Attention (MLA), introduced in DeepSeek-V2, compresses key-value pairs through a shared low-rank bottleneck (cKV), achieving 81% KV-cache reduction during inference.
arXiv AI
Jul 28
Where Is the Cost of Third-Party API Routers in Agentic Software Development?
arXiv:2607. 23624v1 Announce Type: cross Abstract: Third-party API routers have become a common layer that unifies access across increasingly diverse LLM providers.
arXiv AI
Jul 28
LEX-EC: A Lexical Evidence-Channel Audit Framework for Zero-Shot LLM Personality Classification in Black-Box Settings
arXiv:2607. 24435v1 Announce Type: cross Abstract: Large language models may easily assign personality labels from text, but model interpretability remains an open problem.
arXiv AI
Jul 28
Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code Repair
arXiv:2607. 24604v1 Announce Type: cross Abstract: Generate--test--revise loops are common in coding agents, but repetition alone provides no reliability guarantee.
arXiv AI
Jul 28
Hybrid AI-Physical Modeling for Penetration Bias Correction in X-band InSAR DEMs: A Greenland Case Study
arXiv:2504. 08909v2 Announce Type: replace Abstract: Digital elevation models derived from Interferometric Synthetic Aperture Radar (InSAR) data over glacial and snow-covered regions often exhibit systematic elevation errors, commonly termed "penetration bias.
arXiv AI
Jul 28
OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows
arXiv:2510. 24411v3 Announce Type: replace Abstract: Computer-using agents powered by Vision-Language Models (VLMs) have demonstrated human-like capabilities in operating digital environments like mobile platforms.
arXiv AI
Jul 28
From Camera-Based Sensing to Reasoning: A Comprehensive Review Toward Proactive Vulnerable Road User Safety
arXiv:2510. 03314v2 Announce Type: replace-cross Abstract: Ensuring the safety of vulnerable road users (VRUs), such as pedestrians and cyclists, remains a critical challenge, as conventional infrastructure-based measures are often insufficient in dynamic urban environments.
arXiv AI
Jul 28
AutoFed: Personalized Federated Traffic Prediction via Adaptive Prompt
arXiv:2512. 24625v3 Announce Type: replace-cross Abstract: Accurate traffic prediction is essential for Intelligent Transportation Systems, including ride-hailing, urban road planning, and vehicle fleet management.
arXiv AI
Jul 28
Designing Service Systems from Textual Evidence
arXiv:2603. 10400v2 Announce Type: replace-cross Abstract: Designing service systems requires selecting among alternative configurations -- choosing the best chatbot variant, the optimal routing policy, or the most effective quality control procedure.
arXiv AI
Jul 28
Stability of AI Governance Systems: A Coupled Dynamics Model of Public Trust and Social Disruptions
arXiv:2603. 20248v2 Announce Type: replace-cross Abstract: AI systems are increasingly entrenched in public governance, yet scholarship lacks formal tools to determine when deviations of public trust in algorithmic institutions dissipate and when they grow into collapse.
arXiv AI
Jul 28
SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills
arXiv:2604. 06550v3 Announce Type: replace-cross Abstract: Agent skills combine natural-language instructions with executable code while inheriting an agent's filesystem, credential, and network access.
arXiv AI
Jul 28
Opaque Epistemic Mediation: How LLM Deployment Configurations Shape the Validation of Pseudo-Science
arXiv:2607. 22513v2 Announce Type: replace-cross Abstract: Commercial large language models are increasingly used as knowledge references, yet their stance on contested scientific claims is neither stable nor transparent.
arXiv Machine Learning
Jul 28
Dementia Etiology Diagnosis via Collaborative Meta Knowledge Enhancement
arXiv:2607. 22770v1 Announce Type: new Abstract: Although artificial intelligence (AI) has shown promising performance in several medical tasks, accurate dementia etiology diagnosis with AI remains challenging due to complex overlapping symptoms among diseases.
arXiv Machine Learning
Jul 28
Predicting the Outcome of rTMS Depression Therapy using EEG Signals and CNN
arXiv:2607. 22776v1 Announce Type: new Abstract: Repetitive transcranial magnetic stimulation (rTMS) is a non invasive therapy for Major Depressive Disorder (MDD).
arXiv Machine Learning
Jul 28
Same Predictions, Different Reasons: The Effect of Quantization on Model Explanations
arXiv:2607. 22872v1 Announce Type: new Abstract: Post-training quantization (PTQ) has become a practical solution for deploying deep learning models on resource-constrained edge devices by compressing high-precision floating-point weights into low-precision representations without requiring retraining.
arXiv Machine Learning
Jul 28
Distribution-Specific Curvature Control with Finite-Sample Guarantees for Open-Weight Safety
arXiv:2607. 22929v1 Announce Type: new Abstract: A short fine-tuning run can undo the safety guards of an open-weight model---retraining a refusal-trained assistant to aid weapons development or produce hate speech.
arXiv Machine Learning
Jul 28
On the Impossibility of Unbiased and Length-Invariant Policy Optimization with Outcome Rewards
arXiv:2607. 23364v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is the dominant reinforcement learning algorithm for training reasoning capabilities in large language models, notably adopted by DeepSeek-R1.