Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2602. 05088v4 Announce Type: replace Abstract: Millions of people now use generative AI chatbots for psychological support.
arXiv:2607. 06963v1 Announce Type: cross Abstract: Large Language Models (LLMs) and generative AI (GenAI) systems, such as ChatGPT, Claude, Gemini, LLaMA, Copilot, Stable Diffusion by OpenAI, Anthropic, Google, Meta, Microsoft, Stability AI, respectively, are revolutionizing cybersecurity, enabling both automated defense and sophisticated attacks.
arXiv:2607. 07219v1 Announce Type: cross Abstract: Vision foundation models (VFMs) are increasingly being developed for radiological imaging, yet their definition, development and evaluation remain heterogeneous.
arXiv:2607. 07184v1 Announce Type: cross Abstract: Pre-deployment safety evaluations aim to inform the downstream risks of releasing a new AI model.
arXiv:2607. 06622v1 Announce Type: cross Abstract: Utilities increasingly rely on planning and operational tools to cope with the increased penetrations of distributed energy resources, yet the lack of realistic, openly available datasets remains a major barrier for benchmarking and comparison.
arXiv:2607. 07669v1 Announce Type: cross Abstract: Large language models increasingly \emph{understand} dialectal English, yet still \emph{produce} only standard, US-leaning English, leaving dialectal generation, the harder half of the problem, largely unaddressed.
arXiv:2607. 07565v1 Announce Type: cross Abstract: One-shot federated learning (OSFL) addresses the communication overhead of federated learning by limiting training to a single round, but doing so without sacrificing model quality is non-trivial, particularly when client data distributions diverge.
arXiv:2607. 07397v1 Announce Type: new Abstract: Autonomous agents promise substantial gains in speed, scale, and labor efficiency, but their failures can impose abrupt and often irreversible costs.
arXiv:2607. 06592v1 Announce Type: cross Abstract: Object detectors have many applications in safety-critical systems, but they are known to be sensitive to worst-case perturbations such as adversarial attacks, which limits their applicability in real-world scenarios.
arXiv:2601. 06135v3 Announce Type: replace Abstract: Spatial computation in geographic systems increasingly requires query-conditioned, local, interpretable aggregation under metric constraints.
arXiv:2607. 07052v1 Announce Type: cross Abstract: AI agents deployed for IT operations are typically permanent cost centers because every execution requires full LLM inference, even for previously solved problems.
arXiv:2607. 06615v1 Announce Type: cross Abstract: Image forgery detection is a critical task in digital forensics, yet many deep-learning localization approaches are typically GPU-accelerated and computationally heavier than handcrafted screening methods.
arXiv:2607. 07538v1 Announce Type: new Abstract: Training a model with noisy gradient descent can be idealized as overdamped Langevin dynamics on the loss landscape, and a natural safety question is to bound the probability $\nu_t(\mathcal{A}_H) = \mathbb{P}(Q_t \in \mathcal{A}_H)$ that the trajectory lies in a designated failure region $\mathcal{A}_H$.
arXiv:2607. 06766v1 Announce Type: cross Abstract: At Amazon Prime Video, we face the critical operational challenge of managing code deployments during live events and rapid feature releases without causing service outages.
arXiv:2512. 11935v2 Announce Type: replace Abstract: Agentic AI systems increasingly connect large language models (LLMs) to external scientific tools, yet whether and when tool access improves prediction accuracy remains uncharacterized.
arXiv:2607. 06630v1 Announce Type: new Abstract: Formal robustness certificates for embedded neural-interface models can pass while task accuracy collapses: at perturbation budget e=0.
arXiv:2607. 06638v1 Announce Type: new Abstract: Self-paced learning (SPL) is an effective learning paradigm that simulates the human learning process by progressing from easy to difficult samples based on the value of the loss function during the learning process.
arXiv:2603. 15685v2 Announce Type: replace-cross Abstract: Omnimodal large language models (OmniLLMs) jointly process audio and visual streams, but the resulting long multimodal token sequences make inference prohibitively expensive.
arXiv:2601. 17216v3 Announce Type: replace-cross Abstract: Intelligent Transportation Systems (ITS) demand real-time collision prediction to ensure road safety and reduce accident severity.
arXiv:2508. 17298v3 Announce Type: replace-cross Abstract: Compositional visual reasoning has emerged as a key research frontier in multimodal AI, aiming to endow machines with the human-like ability to decompose visual scenes, ground intermediate concepts, and perform multi-step logical inference.