Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 08859v1 Announce Type: cross Abstract: Wireless Body Area Networks (WBANs) generate multivariate physiological time series that are highly nonstationary and must often be processed under strict computational and memory constraints.
arXiv:2608. 08743v1 Announce Type: cross Abstract: Reinforcement learning (RL) seeks to optimize sequential decisions to maximize population-level benefits over time.
arXiv:2605. 27689v2 Announce Type: replace Abstract: When machine learning systems under-perform for particular subgroups, affected users typically have no way to correct these disparities without relying on platform-level fixes.
arXiv:2606. 07998v3 Announce Type: replace-cross Abstract: Recent advances in generative AI, especially powerful Large Language Models (LLMs), raise concerns over the interpretability, safety and sustainability of these large and opaque AI models.
arXiv:2608. 07953v1 Announce Type: new Abstract: Distribution shift poses a significant challenge to the robustness of machine learning models, but the current solutions only aim to detect out-of-distribution (OOD) samples and predict uncertainty levels.
arXiv:2608. 09594v1 Announce Type: cross Abstract: Recently, AI-driven video generation has attracted considerable attention.
arXiv:2608. 00818v2 Announce Type: replace Abstract: The discovery of scaling laws has highlighted the extraordinary potential of AI systems with a striking empirical pattern: as AI systems scale, their capabilities tend to improve predictably.
arXiv:2605. 20721v2 Announce Type: replace Abstract: Label noise is a central challenge in learning from implicit feedback for recommendation.
arXiv:2509. 09078v3 Announce Type: replace-cross Abstract: Given-data methods for variance-based sensitivity analysis have significantly advanced the feasibility of Sobol' index computation for computationally expensive models and models with many inputs.
arXiv:2607. 26574v2 Announce Type: replace-cross Abstract: Safety classifiers ("guards") are the dominant black-box defense for vision-language models, yet a guard judges an input's surface form, not its meaning: a harmful request re-encoded as set theory, formal logic, a classical language, code, or text rendered inside an image slips past a guard that would block it in plain language - the decode gap.
arXiv:2605. 00527v3 Announce Type: replace-cross Abstract: Lissajous confocal laser endomicroscopy (CLE) is a promising solution for high-speed in vivo optical biopsy for handheld scenarios.
arXiv:2604. 03919v2 Announce Type: replace-cross Abstract: We present the first systematic study of Sparse Autoencoders (SAEs) on video representations.
arXiv:2605. 12530v2 Announce Type: replace-cross Abstract: LLM fairness should be evaluated through in-situ behavioral pattern rather than standardized-test Q&A benchmarks.
arXiv:2608. 08440v1 Announce Type: new Abstract: Cross-subject electroencephalogram (EEG)-based emotion recognition remains challenging due to substantial inter-individual variability and discrete formulation that overlooks affective continuity.
arXiv:2608. 08468v1 Announce Type: cross Abstract: Agent Skills---structured packages of instructions and scripts that augment LLM-based agents---are rapidly proliferating, yet their security properties remain under-explored.
arXiv:2608. 08829v1 Announce Type: cross Abstract: Activation steering edits the behaviour of a frozen language model by adding a learned vector to its residual stream, and current practice fixes the injection layers globally per task.
arXiv:2608. 08575v1 Announce Type: cross Abstract: Accurate 3D medical image segmentation requires the integration of long-range anatomical context with fine boundary detail.
arXiv:2608. 09052v1 Announce Type: cross Abstract: Semi-supervised adaptation of vision foundation models (VFMs) commonly freezes the pretrained backbone and updates lightweight modules such as LoRA.
arXiv:2608. 09636v1 Announce Type: cross Abstract: Accurate 3D neuron segmentation in fluorescence microscopy is critical for neuroscience.
arXiv:2504. 18587v2 Announce Type: replace-cross Abstract: Reinforcement learning has emerged as a powerful approach for improving the reasoning capabilities of large language models, as demonstrated by systems such as OpenAI's O1~\cite{o1} and DeepSeek-R1~\cite{r1}.