Search: “safety”

arXiv:2604.09622v1 Announce Type: cross Abstract: The rapid adoption of generative artificial intelligence (AI) in educational assessment has created new opportunities for scalable item creation, pers

arXiv:2604.09578v1 Announce Type: new Abstract: The recent advancement in artificial intelligence (AI) technologies facilitates a paradigm shift toward automation. Autonomous systems are fully or part

arXiv:2604.10693v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting has improved LLM reasoning, but models often generate explanations that appear coherent while containing unfaithful int

arXiv:2602.10042v3 Announce Type: replace-cross Abstract: Recent studies have demonstrated that incorporating Chain-of-Thought (CoT) reasoning into the detection process can enhance a model's ability

arXiv:2604.11137v1 Announce Type: new Abstract: The integration of Large Language Models (LLMs) into clinical decision support is critically obstructed by their opaque and often unreliable reasoning.

arXiv:2601.03416v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have become widely deployed, yet their safety alignment remains fragile under adversarial inputs. Previous

arXiv:2604.09601v1 Announce Type: new Abstract: Discovering predictive alpha factors in quantitative finance remains a formidable challenge due to the vast combinatorial search space and inherently lo

arXiv:2604.10403v1 Announce Type: new Abstract: We address jailbreaks, backdoors, and unlearning for large language models (LLMs). Unlike prior work, which trains LLMs based on their actions when give

arXiv:2602.15481v2 Announce Type: replace Abstract: LLM-as-a-judge has emerged as a cornerstone technique for evaluating large language models by leveraging LLM reasoning to score prompt-response pair

arXiv:2604.11373v1 Announce Type: cross Abstract: Robots are increasingly entering human-interactive scenarios that require understanding of quantity. How intelligent systems acquire abstract numerica

arXiv:2308.12067v3 Announce Type: replace-cross Abstract: Multimodal large language models are typically trained in two stages: first pre-training on image-text pairs, and then fine-tuning using super

arXiv:2604.10165v1 Announce Type: new Abstract: Reinforcement Learning (RL) and Imitation Learning (IL) are the standard frameworks for policy acquisition in manipulation. While IL offers efficient po

arXiv:2604.10673v1 Announce Type: new Abstract: AI alignment is often framed as the task of ensuring that an AI system follows a set of stated principles or human preferences, but general principles r

arXiv:2604.11399v1 Announce Type: cross Abstract: Multimodal adaptation equips large language models (LLMs) with perceptual capabilities, but often weakens the reasoning ability inherited from languag

arXiv:2604.10842v1 Announce Type: cross Abstract: LLM-powered coding agents increasingly rely on tool-use protocols such as the Model Context Protocol~(MCP) to read and write files on a developer's wo

arXiv:2604.03753v2 Announce Type: replace-cross Abstract: Modern advanced driver assistance systems (ADAS) rely on deep neural networks (DNNs) for perception and planning. Since DNNs' parameters resid

arXiv:2604.10833v1 Announce Type: cross Abstract: Recent reports indicate that sustained interaction with conversational artificial intelligence (AI) systems can, in a small subset of users, contribut

arXiv:2604.11671v1 Announce Type: cross Abstract: Accurate material recognition is a fundamental capability for intelligent perception systems to interact safely and effectively with the physical worl

arXiv:2510.26202v2 Announce Type: replace-cross Abstract: Human feedback can alter language models in unpredictable and undesirable ways, as practitioners lack a clear understanding of what feedback d

arXiv:2604.09405v1 Announce Type: new Abstract: As text-to-image diffusion models grow increasingly prevalent, the ability to remove specific concepts-mostly explicit content and many copyrighted char

arXiv:2604.09265v1 Announce Type: new Abstract: Intelligent dialogue systems are increasingly deployed in emotionally and ethically sensitive settings, where failures in either emotional attunement or

arXiv:2604.09075v1 Announce Type: new Abstract: Large language models increasingly operate under multiple instructions from heterogeneous sources with different authority levels, including system poli

arXiv:2604.09059v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have recently achieved notable progress in end-to-end autonomous driving by integrating perception, reasoning, and

arXiv:2604.09024v1 Announce Type: cross Abstract: Multi-modal large language models (MLLMs) have emerged as powerful tools for analyzing Internet-scale image data, offering significant benefits but al

arXiv:2604.08719v1 Announce Type: cross Abstract: Recent years have seen remarkable progress in autonomous driving, yet generalization to long-tail and open-world scenarios remains a major bottleneck

arXiv:2604.04144v2 Announce Type: replace-cross Abstract: The holy grail of LLM personalization is a single LLM for each user, perfectly aligned with that user's preferences. However, maintaining a se

arXiv:2604.09253v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are powerful but remain vulnerable to multimodal jailbreak attacks. Existing attacks mainly rely on either explicit visu

arXiv:2604.09104v1 Announce Type: cross Abstract: Scheming, the covert pursuit of misaligned goals by AI systems, represents a potentially catastrophic risk, yet scheming research suffers from signifi

arXiv:2604.03058v2 Announce Type: replace-cross Abstract: LLMs can be socially sycophantic, affirming users when they ask questions like 'am I in the wrong?' rather than providing genuine assessment.

arXiv:2604.08341v1 Announce Type: new Abstract: Current Human-Robot Interaction (HRI) systems for skill teaching are fragmented, and existing approaches in the literature do not offer a cohesive frame

arXiv:2510.18196v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are commonly used as evaluators in various applications, but the reliability of the outcomes remains a challenge.

arXiv:2604.07132v1 Announce Type: cross Abstract: Child Sexual Abuse Imagery (CSAI) classification is an important yet challenging problem for computer vision research due to the strict legal and ethi

arXiv:2604.06899v1 Announce Type: cross Abstract: Data leakage is the inadvertent transfer of information between training and evaluation datasets that poses a subtle, yet critical, risk to the reliab

arXiv:2510.20549v2 Announce Type: replace Abstract: Despite advancements in SLAM technologies, robust operation under challenging conditions such as low-texture, motion-blur, or challenging lighting r

arXiv:2604.06833v1 Announce Type: cross Abstract: As high quality public data becomes scarce, Federated Learning (FL) provides a vital pathway to leverage valuable private user data while preserving p

arXiv:2604.06219v1 Announce Type: cross Abstract: Across the Global North, calls for participatory artificial intelligence (AI) to improve the responsible, safe, and ethical use of AI have increased,

arXiv:2604.06203v1 Announce Type: cross Abstract: The integration of continuous data from built-in sensors and Large Language Models (LLMs) has fueled a surge of 'Sensor-Fused LLM agents' for personal

arXiv:2604.06215v1 Announce Type: cross Abstract: The governance of frontier general-purpose artificial intelligence has become a public-sector problem of institutional design, not merely a technical

arXiv:2604.07833v1 Announce Type: new Abstract: Embodied agents are evolving from passive reasoning systems into active executors that interact with tools, robots, and physical environments. Once gran

arXiv:2604.06285v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have become essential for tasks such as image synthesis, captioning, and retrieval by aligning textual and visual inform

arXiv:2510.25597v2 Announce Type: replace-cross Abstract: This paper presents a decentralized control framework that incorporates social awareness into multi-agent systems with unknown dynamics to ach

arXiv:2510.07809v4 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) empower autonomous mobile agents, yet their security under realistic mobile deployment constraints remain

arXiv:2604.08425v1 Announce Type: cross Abstract: When humans label subjective content, they disagree, and that disagreement is not noise. It reflects genuine differences in perspective shaped by anno

arXiv:2604.08039v1 Announce Type: new Abstract: Interpreting the concepts encoded by individual neurons in deep neural networks is a crucial step towards understanding their complex decision-making pr

arXiv:2603.04300v2 Announce Type: replace Abstract: Foundation models in general promise to accelerate scientific computation by learning reusable representations across problem instances, yet constra

arXiv:2604.08203v1 Announce Type: new Abstract: Medical Vision-Language Models (VLMs) hold immense promise for complex clinical tasks, but their reasoning capabilities are often constrained by text-on