Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2606. 11687v1 Announce Type: cross Abstract: Unmanned Aerial Vehicle (UAV) threats have emerged as a defining security challenge of the 21st century.
arXiv:2606. 11262v1 Announce Type: cross Abstract: Access control in large language models (LLMs) requires modular mechanisms to enable domain-specific behavior without retraining or cross-domain interference.
arXiv:2506. 01396v2 Announce Type: replace Abstract: Differential privacy (DP) has become an essential framework for privacy-preserving machine learning.
arXiv:2606. 12032v1 Announce Type: new Abstract: Contemporary AI alignment research treats self-preservation as an instrumental nuisance to be suppressed by external mechanisms.
arXiv:2606. 12251v1 Announce Type: cross Abstract: Gradient-based adversarial attacks remain a dominant threat to deep neural networks (DNNs), as they exploit gradient information to efficiently optimize adversarial perturbations.
arXiv:2506. 03933v2 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have shown remarkable capabilities in multimodal understanding, yet their susceptibility to adversarial perturbations poses a significant threat to their reliability in real-world applications.
arXiv:2510. 02660v2 Announce Type: replace-cross Abstract: When researchers claim AI systems possess ToM or mental models, they are fundamentally discussing behavioral predictions and bias corrections rather than genuine mental states.
arXiv:2604. 25018v2 Announce Type: replace-cross Abstract: The Internet of Everything (IoE) represents an evolution of the Internet of Things (IoT) by integrating people, data, processes, and things into a unified intelligent ecosystem.
arXiv:2605. 16651v2 Announce Type: replace-cross Abstract: Explanation mechanisms are increasingly used to support transparency and trust in vision-language models (VLMs), particularly in settings where model decisions require human oversight.
arXiv:2605. 10907v3 Announce Type: replace-cross Abstract: The dominant paradigm for AI agents is an "on-the-fly" loop in which agents synthesize plans and execute actions within seconds or minutes in response to user prompts.
arXiv:2606. 12392v1 Announce Type: cross Abstract: Recently, large language models (LLMs) have achieved promising progress in the fields of classical Chinese translation and the generation of classical poetry.
arXiv:2509. 26294v2 Announce Type: replace-cross Abstract: We consider imitation learning in the low-data regime, where only a limited number of expert demonstrations are available.
arXiv:2509. 23248v3 Announce Type: replace Abstract: The rapid advancement of large language models (LLMs) has enabled an emergence of agentic artificial intelligence (AI) with powerful reasoning and autonomous decision-making capabilities.
arXiv:2606. 11518v1 Announce Type: cross Abstract: Fourier neural operators (FNOs) are effective and efficient surrogates for approximating solutions of PDEs and generalize across discretizations.
arXiv:2509. 23982v2 Announce Type: replace-cross Abstract: Preference alignment is a critical step in making Large Language Models (LLMs) useful and aligned with (human) preferences.
arXiv:2602. 20958v2 Announce Type: replace-cross Abstract: Vision-based Unmanned Aerial Vehicles (UAVs) frameworks aid human search tasks by detecting and recognizing specific individuals, then tracking and following them while maintaining a safe distance.
arXiv:2606. 12397v1 Announce Type: cross Abstract: Router is the cornerstone component to the Mixture-of-Experts models.
arXiv:2606. 11555v1 Announce Type: cross Abstract: The escalating demand for mental healthcare, driven by rising societal stress, highlights the limitations of traditional psychiatric diagnostics.
arXiv:2605. 12288v3 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) is a widely used RL-free method for aligning language models from pairwise preferences, but it models preferences over full sequences even though generation is driven by per-token decisions.
arXiv:2606. 12065v1 Announce Type: new Abstract: Automating compliance check for geometry-intensive regulations remains a significant technical bottleneck in Building Information Modeling (BIM), primarily due to the semantic disparity between high-level regulatory logic and structured IFC data.