Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2511. 01352v2 Announce Type: replace Abstract: In this paper, we present a new algorithm, MiniFool, that implements physics-inspired adversarial attacks for testing neural network-based classification tasks in particle and astroparticle physics.
arXiv:2606. 17646v1 Announce Type: cross Abstract: Saliency map visualizations explain image-based AI predictions by pointing to regions, but these are often unintuitive and semantically unclear, leaving an interpretability gap.
arXiv:2606. 18098v1 Announce Type: new Abstract: Advances in Artificial Intelligence (AI) have led AI for Theorem Proving to become a promising means of formally verifying computer systems.
arXiv:2507. 15104v2 Announce Type: replace-cross Abstract: Recent advances in generative AI (GenAI) have shown transformative potential for modern hardware design.
arXiv:2606. 17474v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly considered for use in clinical consultation tasks, yet most medical evaluations remain static, single-turn, or narrowly outcome-based, limiting their ability to reflect the sequential, uncertain, and interactive nature of real-world care.
arXiv:2512. 01241v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are routinely used by physicians and patients for medical advice, yet their clinical safety profiles remain poorly characterized.
arXiv:2602. 05790v2 Announce Type: replace-cross Abstract: Fast computation of a matrix product $W^\top X$ is a workhorse of modern LLMs.
arXiv:2606. 17405v1 Announce Type: new Abstract: Clinical decision support AI systems (CDSASs) must adapt to evolving patient conditions in real-time while adhering to strict safety constraints.
arXiv:2606. 18060v1 Announce Type: new Abstract: As Large Language Model based agents enter autonomous scientific research, their ability to resist pseudoscience becomes increasingly important.
arXiv:2602. 08939v2 Announce Type: replace Abstract: Large language models increasingly produce fluent causal explanations, yet they often fail in ways aggregate accuracy cannot diagnose: confusing association with intervention, abandoning correct judgments under pressure, over-refusing valid claims, or answering when evidence is underdetermined.
arXiv:2606. 18111v1 Announce Type: cross Abstract: Fairness is an important aspect of decision-making in multi-objective reinforcement learning (MORL), where policies must ensure both optimality and equity across multiple, potentially conflicting objectives.
arXiv:2606. 17476v1 Announce Type: new Abstract: Laser-induced breakdown spectroscopy (LIBS) quantitative analysis faces critical challenges in wavelength selection due to high-dimensional spectral data and the fundamental trade-off between prediction accuracy and feature efficiency.
arXiv:2510. 11709v2 Announce Type: replace-cross Abstract: Why do adversarial examples exist, and why do they transfer between models?
arXiv:2606. 17889v1 Announce Type: cross Abstract: Compositional learning systems must balance plasticity, the ability to acquire new knowledge, with stability, the preservation of previously learned components, especially when tasks share structure and risk interference.
arXiv:2512. 25065v2 Announce Type: replace-cross Abstract: Systems resource management tasks rely primarily on hand-designed heuristics.
arXiv:2606. 12867v2 Announce Type: replace Abstract: Multimodal-attributed graphs (MAGs) couple graph topology with node semantics from text, images, and other modalities.
arXiv:2606. 17464v1 Announce Type: new Abstract: Membership inference attacks (MIAs) are a canonical way to assess a machine learning model's privacy properties.
arXiv:2606. 17684v1 Announce Type: cross Abstract: Graph-based learning methods have become increasingly prominent due to their strong performance across diverse applications.
arXiv:2606. 10774v2 Announce Type: replace Abstract: Decentralized Federated Learning(DFL) enables collaborative model training across wireless edge nodes, including IoT deployments, autonomous vehicles, UAV swarms, and satellite constellations.
arXiv:2510. 01359v2 Announce Type: replace-cross Abstract: Code-capable large language model (LLM) agents are embedded in software engineering workflows where they can read, write, and execute code, raising "jailbreak" stakes beyond text-only settings.