arXiv:2605.01699v3 Announce Type: replace-cross Abstract: Recent attacks show that behavioural unlearning of large language models leaves internal traces recoverable by adversarial probes. We characterise where this retention lives and show it can be surgically removed without measurable capability cost. Our central protocol is a leave-one-out cross-sequence probe that tests whether a memorisation signature generalises across […]
AI-Generated Images: What Humans and Machines See When They Look at the Same Image
arXiv:2605.06143v1 Announce Type: cross Abstract: The misuse of generative AI in online disinformation campaigns highlights the urgent need for transparent and explainable detection systems. In this work, we investigate how detectors for AI-generated images can be more effective in providing human-understandable explanations for their predictions. To this end, we develop a suite of detectors with […]
EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields
arXiv:2605.06192v1 Announce Type: cross Abstract: Pretrained video diffusion models provide powerful spatiotemporal generative priors, making them a natural foundation for robotic world models. While recent world-action models jointly optimize future videos and actions, they predominantly treat video generation as an auxiliary representation for policy learning. Consequently, they insufficiently explore the inverse problem: leveraging action signals […]
Soft Deterministic Policy Gradient with Gaussian Smoothing
arXiv:2605.06228v1 Announce Type: cross Abstract: Deterministic policy gradient (DPG) is widely utilized for continuous control; however, it inherently relies on the differentiability of the critic with respect to the action during policy updates. This assumption is violated in practical control problems involving sparse or discrete rewards, leading to ill-defined policy gradients and unstable learning. To […]
Correct Code, Vulnerable Dependencies: A Large Scale Measurement Study of LLM-Specified Library Versions
arXiv:2605.06279v1 Announce Type: cross Abstract: Large language models (LLMs) are now largely involved in software development workflows, and the code they generate routinely includes third-party library (TPL) imports annotated with specific version identifiers. These version choices can carry security and compatibility risks, yet they have not been systematically studied. We present the first large-scale measurement […]
Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs
arXiv:2605.06320v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in teams, yet existing coordination approaches often occupy two extremes. Highly structured methods rely on fixed roles, pipelines, or task decompositions assigned a priori. In contrast, fully unstructured teams enable adaptability and exploration but suffer from inefficiencies such as error propagation, inter-agent conflicts, […]
Memory Efficient Full-gradient Attacks (MEFA) Framework for Adversarial Defense Evaluations
arXiv:2605.06357v1 Announce Type: cross Abstract: This work studies the robust evaluation of iterative stochastic purification defenses under white-box adversarial attacks. Our key technical insight is that gradient checkpointing makes exact end-to-end gradient computation through long purification trajectories practical by trading additional recomputation for substantially lower memory usage. This enables full-gradient adaptive attacks against diffusion- and […]
Operator-Guided Invariance Learning for Continuous Reinforcement Learning
arXiv:2605.06500v1 Announce Type: cross Abstract: Reinforcement learning (RL) with continuous time and state/action spaces is often data-intensive and brittle under nuisance variability and shift, motivating methods that exploit value-preserving structures to stabilize and improve learning. Most existing approaches focus on special cases, such as prescribed symmetries and exact equivariance, without addressing how to discover more […]
Coordination Matters: Evaluation of Cooperative Multi-Agent Reinforcement Learning
arXiv:2605.06557v1 Announce Type: cross Abstract: Cooperative multi-agent reinforcement learning (MARL) benchmarks commonly emphasize aggregate outcomes such as return, success rate, or completion time. While essential, these metrics often fail to reveal how agents coordinate, particularly in settings where agents, tasks, and joint assignment choices scale combinatorially. We propose a coordination-aware evaluation perspective that supplements return […]
When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels
arXiv:2605.06652v1 Announce Type: cross Abstract: Many deployments must compare candidate language models for safety before a labeled benchmark exists for the relevant language, sector, or regulatory regime. We formalize this setting as benchmarkless comparative safety scoring and specify the contract under which a scenario-based audit can be interpreted as deployment evidence. Scores are valid only […]
Goal-Driven Query Answering over First- and Second-Order Dependencies with Equality
arXiv:2412.09125v2 Announce Type: replace Abstract: In this paper we present the first goal-driven query answering technique for first- and second-order dependencies with equality. Our technique transforms the input dependencies so that applying the chase to the output avoids many inferences that are irrelevant to the query. The transformation proceeds in several steps, which comprise the […]
CompassLLM: A Multi-Agent Approach toward Geo-Spatial Reasoning for Popular Path Query
arXiv:2510.07516v2 Announce Type: replace Abstract: The popular path query – identifying the most frequented routes between locations from historical trajectory data – has important applications in urban planning, navigation optimization, and travel recommendations. While traditional algorithms and machine learning approaches have achieved success in this domain, they typically require model training, parameter tuning, and retraining […]