arXiv AI
Jun 2
From Cues to Horizons: Dynamic Risk Horizon Profiling for Trajectory Prediction
arXiv:2606. 00857v1 Announce Type: cross Abstract: Accurate and reliable vehicle trajectory prediction is essential for safe autonomous driving.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Jun 2
SORA: Free Second-Order Attacks in Fast Adversarial Training
arXiv:2606. 00738v1 Announce Type: cross Abstract: Adversarial Training (AT) is a leading defense against adversarial examples but often suffers from Catastrophic Overfitting (CO) in efficient single-step variants, where robustness to multi-step attacks collapses despite high single-step performance.
arXiv AI
Jun 2
Brain-Atlas-Guided Generative Counterfactual Attention for Explainable Cognitive Decline Diagnosis Using Multimodal Connectomes
arXiv:2606. 01237v1 Announce Type: new Abstract: Mild cognitive impairment (MCI) and subjective cognitive decline (SCD) are closely associated with the early Alzheimer's disease continuum, where accurate and explainable diagnosis is important for early risk assessment and intervention.
arXiv Machine Learning
Jun 2
Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs
arXiv:2606. 01710v1 Announce Type: cross Abstract: Vision-Language models (VLMs), such as CLIP, achieve powerful zero-shot classification.
arXiv AI
Jun 2
The Paradox of Outcome Optimization: A Causal Information-Theoretic Bound on Reasoning Shortcuts in LLMs
arXiv:2606. 00674v1 Announce Type: cross Abstract: Large Language Models (LLMs) aligned via outcome-based Reinforcement Learning (RL) frequently exhibit a critical failure mode: they achieve high performance on in-distribution benchmarks while demonstrating brittle reasoning capabilities on out-of-distribution (OOD) tasks.
arXiv AI
Jun 2
COPF: An Online Framework for Deployment-Stable Counterfactual Fairness in Evolving Graphs
arXiv:2606. 00700v1 Announce Type: cross Abstract: Online link recommendation on evolving graphs is performative: by choosing which candidate links to show users, the system changes which links form and what feedback it later observes.
arXiv AI
Jun 2
Authenticity Debt and the Synthetic Content Threat Landscape: A Layered Framework for Trust, Provenance, and IP Governance in the Generative AI Era
arXiv:2606. 00621v1 Announce Type: cross Abstract: Generative artificial intelligence has fundamentally changed how content is now produced.
arXiv AI
Jun 2
MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation
arXiv:2606. 00610v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become an essential method for mitigating hallucinations in Large Language Models (LLMs) by leveraging external knowledge.
arXiv AI
Jun 2
TabChange: Precise Attribute Changes in Tabular Data
arXiv:2606. 00503v1 Announce Type: cross Abstract: Modifying an attribute in tabular data often introduces an unnatural instance by breaking its relationships with other attributes.
arXiv Machine Learning
Jun 2
Investigating and Alleviating Harm Amplification in LLM Interactions
arXiv:2606. 02423v1 Announce Type: cross Abstract: Large language models (LLMs) can serve as helpful assistants, yet they can equally function as harm amplifiers that enable malicious users to achieve harmful outcomes beyond their capabilities through extended interactions.
arXiv AI
Jun 2
CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards
arXiv:2606. 00020v1 Announce Type: cross Abstract: Large Language Model (LLM) based Chinese Grammatical Error Correction (CGEC) systems face two critical challenges: general-purpose models lack specialized linguistic priors for subtle grammatical distinctions, and Supervised Fine-Tuning (SFT) with Maximum Likelihood Estimation fails to optimize for precision-focused metrics, leading to systematic over-correction.
arXiv AI
Jun 2
Detect Before You Leap: Mirage Detection in Vision-Language Models
arXiv:2606. 00435v1 Announce Type: cross Abstract: Vision-language models (VLMs) can produce confident visual answers even when the required visual evidence is missing, blank, or unrelated to the question.
arXiv AI
Jun 2
eMoT: evolving Memory-of-Thought via Symbolic Anchoring and Memory Corrosion
arXiv:2606. 02054v1 Announce Type: new Abstract: While Large Language Models (LLMs) achieve impressive performance on multi-step reasoning tasks, their reliability is persistently hindered by critical limitations such as unconstrained hallucinations and poor numerical computation.
arXiv Machine Learning
Jun 2
Controllable Value Alignment in Large Language Models through Neuron-Level Editing
arXiv:2602. 07356v2 Announce Type: replace Abstract: Aligning large language models (LLMs) with human values has become increasingly important as their influence on human behavior and decision-making expands.
arXiv AI
Jun 2
SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning
arXiv:2606. 01991v1 Announce Type: new Abstract: As Large Language Model (LLM) agents increasingly leverage the Model Context Protocol (MCP) to operate in complex environments, the expansion of their action spaces offers agents unsafe capabilities and underscores the risk of power-seeking.
arXiv AI
Jun 2
Physically-Constrained Mamba-SDE for Remaining Useful Life Prediction under Irregular Observations
arXiv:2606. 01894v1 Announce Type: new Abstract: Accurate Remaining Useful Life prediction is critical for industrial predictive maintenance.
arXiv Machine Learning
Jun 2
Measuring Alignment-Induced Activation Shifts Correctly: A Template-Controlled Difference-in-Differences Protocol
arXiv:2605. 24583v3 Announce Type: replace Abstract: Comparing a model's internal activations before and after alignment is a natural way to ask what safety training changes: one forms the matrix of paired aligned-minus-base activations on safety-relevant inputs and reads off its effective rank or top direction.
arXiv AI
Jun 2
GovAI-Pipe: A Layered AI Governance Pipeline for Citizen-Facing AI in Turkey's e-Government Gateway
arXiv:2606. 01417v1 Announce Type: new Abstract: Turkey's e-Government Gateway (e-Devlet) serves over 68 million registered users with more than 9,200 government services, and is increasingly integrating artificial intelligence into citizen-facing applications such as chatbot assistants and eligibility assessments.
arXiv AI
Jun 2
AXIOM: A Trust-First Neuro-Symbolic Execution Architecture for Verifiable Mathematical Reasoning
arXiv:2606. 00671v1 Announce Type: new Abstract: We present AXIOM, a trust-first neuro-symbolic execution architecture for natural-language mathematical reasoning.
arXiv Machine Learning
Jun 2
Semimage: HSV-Based Semantic Image Encoding for Disentangled Text Representation
arXiv:2512. 00088v2 Announce Type: replace-cross Abstract: We propose SemImage, a novel method for representing a text document as a two-dimensional semantic image to be processed by convolutional neural networks (CNNs).