Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 07564v1 Announce Type: cross Abstract: In digital dentistry and oral surgery, the registration of jawbone CT and intraoral scanner (IOS) data is essential for integrating internal bone structure with high-resolution dental surface geometry.
arXiv:2608. 09393v1 Announce Type: cross Abstract: We identify and quantify temporal misgrounding: the systematic retrieval and citation of the currently in-force version of a legal article when the applicable version is an earlier or future one.
arXiv:2608. 09510v1 Announce Type: cross Abstract: Detecting machine-generated disinformation on social media is increasingly difficult as large language models (LLMs) make it easier to generate and rewrite misleading content at scale.
arXiv:2608. 09548v1 Announce Type: cross Abstract: Large language models are increasingly deployed in education as tutors, teaching assistants, and content generators.
arXiv:2608. 07902v1 Announce Type: cross Abstract: Youth increasingly turn to AI chatbots for social and emotional support, raising concerns about how these systems respond, especially in high-stakes situations.
arXiv:2608. 08634v1 Announce Type: new Abstract: Open-weight language models from Chinese AI labs caught up on benchmarks relative to proprietary frontier models in recent months.
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}.
arXiv:2603. 07313v4 Announce Type: replace-cross Abstract: Robustness under latent distribution shift remains challenging in partially observable reinforcement learning.
arXiv:2608. 07851v1 Announce Type: new Abstract: Residual connections rely on a static residual pathway, and are essential for training deep neural networks.
arXiv:2608. 08489v1 Announce Type: new Abstract: Neural network classifiers trained by cross-entropy minimization are highly sensitive to label noise and adversarial contamination.
arXiv:2511. 18721v4 Announce Type: replace-cross Abstract: The SmoothLLM defense provides a certification guarantee against jailbreaking attacks, but it relies on a strict "k-unstable" assumption that rarely holds in practice.
arXiv:2608. 09328v1 Announce Type: new Abstract: Model learning by an eavesdropper is treated as an estimation problem in a federated environment.
arXiv:2608. 09121v1 Announce Type: new Abstract: Web navigation agents are capable of addressing various types of tasks on different websites.
arXiv:2608. 08138v1 Announce Type: cross Abstract: Recent data protection laws have accelerated the adoption of Federated Learning (FL) for privacy-preserving decentralized training.
arXiv:2608. 07621v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have recently achieved impressive performance for end-to-end autonomous driving, yet existing approaches are primarily designed for an individual single autonomous driving agent with limited support for cooperative perception, reasoning, and planning.
arXiv:2608. 09332v1 Announce Type: new Abstract: Hallucinations are a major concern for the integration of artificial intelligence into medicine, although less explored in the realm of medical image processing.
arXiv:2602. 01267v3 Announce Type: replace Abstract: Kronecker adapters have emerged as a promising approach for fine-tuning large-scale models, enabling high-rank updates through tunable component structures.
arXiv:2608. 07822v1 Announce Type: cross Abstract: Quaternion-valued neural networks and variational quantum circuits (VQCs) both derive local transformations from $\mathrm{SU}(2)$ geometry, yet their performance on classical supervised learning remains poorly understood.
arXiv:2508. 16481v3 Announce Type: replace Abstract: Ensuring the safe use of agentic systems requires a thorough understanding of the range of malicious behaviors these systems may exhibit.
arXiv:2509. 25003v3 Announce Type: replace Abstract: Membership inference attacks (MIAs) against Diffusion Models (DMs) raise pressing privacy concerns by revealing whether a sample was part of the training set.