Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 11950v2 Announce Type: replace-cross Abstract: Brain field potentials are scale-free: their power spectra follow a $1/f^{\beta}$ law whose aperiodic exponent $\beta$ tracks cortical state, and sleep depth in particular is a shift in $\beta$.
arXiv:2607. 14658v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) excel in general tasks, rigorous scientific reasoning remains challenging due to the limitations of monolithic, linear planning.
arXiv:2607. 14886v1 Announce Type: new Abstract: Temporal Knowledge Graph (TKG) reasoning under the extrapolation setting focuses on forecasting future time-stamped events (facts) from historical data in a temporal knowledge graph.
arXiv:2607. 14228v1 Announce Type: cross Abstract: In this paper, we ask whether vision foundation models construct representations that reflect the intrinsic properties of 3D Euclidean space.
arXiv:2607. 14510v1 Announce Type: new Abstract: Industrial time series serve as the foundation for Prognostics and Health Management (PHM) to ensure the reliability and safety of industrial equipment such as aero-engines.
arXiv:2607. 14353v1 Announce Type: cross Abstract: As automated decision-making and data-driven technologies pervade society and are used to manage consequential outcomes, understanding the technology's capabilities, limitations, and attendant risks in context requires analysis of full sociotechnical systems.
arXiv:2607. 15267v1 Announce Type: new Abstract: Poisoning pretraining data can introduce harmful behaviors to LMs that are difficult to detect and mitigate.
arXiv:2601. 05050v3 Announce Type: replace Abstract: Large language models (LLMs) have been shown to be persuasive across a variety of contexts.
arXiv:2607. 14375v1 Announce Type: cross Abstract: We study exact verification of ReLU networks in an adversarial smoothed model.
arXiv:2607. 14271v1 Announce Type: cross Abstract: Feature-attribution methods are central to explainable artificial intelligence.
arXiv:2607. 14816v1 Announce Type: cross Abstract: Large Language Models (LLMs) perform differently on identical programming tasks when prompted in different natural languages, a phenomenon known as language bias.
arXiv:2607. 14705v1 Announce Type: new Abstract: Graph neural networks (GNNs) frequently encounter group fairness issues, often yielding biased predictions against specific demographic groups defined by sensitive attributes such as gender or race.
arXiv:2510. 09416v4 Announce Type: replace Abstract: Learning on temporal graphs has become a central topic in graph representation learning, with numerous benchmarks indicating the strong performance of state-of-the-art models.
arXiv:2607. 15218v1 Announce Type: new Abstract: Large language models (LLMs) increasingly serve as high-level planners for embodied agents, where linguistically benign instructions can become unsafe once grounded in the physical world.
arXiv:2607. 14419v1 Announce Type: new Abstract: Machine-learning datasets labelled "4D" universally denote three spatial dimensions plus time.
arXiv:2607. 14466v1 Announce Type: new Abstract: Noise injection is a well-known technique in stochastic optimization.
arXiv:2406. 01514v4 Announce Type: replace-cross Abstract: We introduce a training-free safety enhancement method for aligning large language models (LLMs) without the need for supervised fine-tuning or reinforcement learning from human feedback.
arXiv:2607. 14275v1 Announce Type: new Abstract: Context engineering has become central to building reliable AI agents, yet it remains largely unmeasured.
arXiv:2607. 14607v1 Announce Type: cross Abstract: Machine learning (ML) models deployed in sensitive domains such as healthcare, law enforcement, and finance must satisfy not only utility requirements but also fairness and privacy guarantees.
arXiv:2607. 14194v1 Announce Type: cross Abstract: Text-to-video (T2V) generators can synthesize realistic and temporally coherent videos, but controllably removing a target concept from a generator remains difficult.