Search: “safety”

arXiv:2608.10405v1 Announce Type: cross Abstract: Many studies have shown that specially crafted inputs can induce large language models (LLMs) to generate excessively long outputs, resulting in signi

arXiv:2608.10590v1 Announce Type: new Abstract: Vision Transformers (ViTs) are widely believed to require more labeled data than CNNs for industrial dense prediction. Through controlled experiments on

arXiv:2608.09967v1 Announce Type: new Abstract: Deep reinforcement learning (DRL) agents achieve strong performance in complex environments, yet their decision-making processes remain difficult to int

arXiv:2608.10153v1 Announce Type: new Abstract: Enterprises are deploying autonomous AI agents faster than they can govern them, and prevailing approaches stretch a single discipline, typically DevSec

arXiv:2603.20907v5 Announce Type: replace Abstract: As users increasingly turn to LLMs for practical and personal advice, they become vulnerable to subtle steering toward hidden incentives misaligned

arXiv:2608.10976v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models can connect scene understanding, semantic reasoning, and trajectory generation for autonomous driving. However, verb

arXiv:2608.09142v1 Announce Type: new Abstract: Treatment planning in precision oncology requires synthesizing heterogeneous patient information with rapidly evolving clinical guidelines to ensure gui

arXiv:2608.01043v2 Announce Type: replace-cross Abstract: We report a counter-intuitive interaction between image inputs and existing black-box defenses on Vision--Language Models (VLMs): pairing an e

arXiv:2608.08941v1 Announce Type: cross Abstract: Operational Design Domain (ODD) specifications describe where an automated driving system (ADS) is permitted to operate, but they do not prescribe wha

arXiv:2608.08623v1 Announce Type: new Abstract: In Reinforcement Learning with Verifiable Rewards (RLVR) frameworks for mathematical reasoning tasks, floating-point results are typically evaluated usi

arXiv:2608.09928v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) exhibit strong visual understanding, yet the internal features that cause these behaviors remain difficult to

arXiv:2608.08453v1 Announce Type: new Abstract: Under the current standard, Agent Skills are SKILL.md files that combine instructions with supporting resources, enabling Large Language Model (LLM) age

arXiv:2608.06727v1 Announce Type: new Abstract: Transformer models for high-dimensional omics analysis process thousands of genes or pathways, although only a subset requires deep computation. Mixture

arXiv:2608.06732v1 Announce Type: new Abstract: Recent text-to-video (T2V) generation models enable fake news videos to be synthesized from scratch, shifting the threat beyond cheap fakes assembled fr

arXiv:2608.06650v1 Announce Type: cross Abstract: Reduced-order models based on Cosserat-rod theory are now well established, and modeling theory is no longer the primary bottleneck in soft-robot cont

arXiv:2608.05221v1 Announce Type: new Abstract: The ongoing digitalization of rail systems and the increasing use of artificial intelligence (AI) are fundamentally transforming the design, operation,

arXiv:2608.05695v1 Announce Type: new Abstract: As large language model (LLM) agents increasingly invoke external tools and interact with real-world systems, unsafe actions may cause irreversible cons

arXiv:2608.04347v1 Announce Type: new Abstract: Fine-tuning enables a source model to acquire desired capabilities and behaviors in a target domain while retaining much of its general-purpose competen

arXiv:2608.02684v1 Announce Type: cross Abstract: Large Language Models (LLMs) are accelerating biological research, yet this same capability poses a critical biosecurity threat: models that assist in

arXiv:2608.03838v1 Announce Type: new Abstract: Reasoning-based guard models improve LLM safeguards, but decoding explicit rationales for every interaction makes them costly to deploy. Although latent

arXiv:2509.20851v2 Announce Type: replace Abstract: Video Large Language Models (VideoLLMs) are increasingly deployed as automated moderators on user-generated video platforms, where a few unwatched s

arXiv:2608.02630v1 Announce Type: new Abstract: Knowledge graph engineering often distributes accepted state, observations, constraints, processes, and hypothetical scenarios across artifacts whose co

arXiv:2603.15257v2 Announce Type: replace Abstract: Tactile sensing is a crucial capability for Vision-Language-Action (VLA) architectures, as it enables dexterous and safe manipulation in contact-ric

arXiv:2608.02520v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for health-related advice. Existing research measures their safety with static questions rather than

arXiv:2506.07121v2 Announce Type: replace Abstract: Ensuring the safety and robustness of large language models (LLMs) is a fundamental challenge and a critical prerequisite for the responsible deploy

arXiv:2608.02139v1 Announce Type: new Abstract: Large language models (LLMs) capable of self-improvement require not only effective policy optimization, but also a principled mechanism for transformin

arXiv:2608.01378v1 Announce Type: new Abstract: Design campaigns in chemistry, materials science, and machine learning share a bottleneck: determining how good a candidate truly is requires an expensi

arXiv:2607.29190v1 Announce Type: new Abstract: Tool-using LLM agents act on typed tool returns, records pairing provenance and categorical fields with numerical values. Runtime permission gates gener

arXiv:2506.07225v2 Announce Type: replace-cross Abstract: Transluminal minimally invasive surgery uses natural orifices and small incisions to access internal anatomical structures, promoting quicker

arXiv:2602.23971v4 Announce Type: replace-cross Abstract: Sycophancy, the tendency of large language models to favour user-affirming responses over critical engagement, has been identified as an align

arXiv:2607.27508v1 Announce Type: new Abstract: Assistance games formalize human-robot collaboration under asymmetric information: the human knows the goal, while the robot must infer it from observat

arXiv:2511.19982v3 Announce Type: replace Abstract: Continuous emotional image content generation (C-EICG) is emerging rapidly due to its ability to produce images aligned with both user descriptions

arXiv:2607.26423v1 Announce Type: cross Abstract: As autonomous drone deployments scale from individual units to coordinated swarms, the human operator's role shifts from direct piloting to high-level

arXiv:2607.26541v1 Announce Type: cross Abstract: Audio-capable foundation models enable end-to-end spoken interaction, but they also introduce safety risks beyond transcript content. It remains uncle

arXiv:2607.25489v1 Announce Type: new Abstract: Large language models and multimodal foundation models are enabling medical artificial intelligence (AI) systems to move beyond isolated prediction and

arXiv:2607.25375v1 Announce Type: new Abstract: India is a vast nation of over 1.4 billion people, varied by hundreds of diverse and locally specific traditions and cultures and 22 officially recogniz

arXiv:2607.25857v1 Announce Type: new Abstract: We introduce Shieldstral, a 3B-parameter policy-adaptive multimodal safety classifier that matches or outperforms models nearly 7imes its size on text s

arXiv:2607.25219v1 Announce Type: new Abstract: Social navigation has progressed from simplified 2D environments toward a more general vision-based setting, in which a robot needs to achieve socially

arXiv:2607.24275v1 Announce Type: cross Abstract: Ethical governance of AI-driven systems is often expressed through high-level principles and static documentation, creating a gap between regulatory r

arXiv:2601.18350v5 Announce Type: replace-cross Abstract: Large language models fine-tuned via a two-stage pipeline (domain adaptation followed by instruction alignment) can exhibit non-trivial interf

arXiv:2607.22651v1 Announce Type: new Abstract: Large language models (LLMs) have enabled increasingly capable conversational agents, but reliably controlling their behavior in real-time interactive e

arXiv:2607.22837v1 Announce Type: cross Abstract: Many organizations aim to adapt language models for internal use, both to improve performance on domain-specific tasks and to address privacy concerns

arXiv:2607.22676v1 Announce Type: new Abstract: Post-training is a key mechanism for adapting large language models to downstream tasks. While prior work suggests that task adaptation can alter a mode

arXiv:2607.24422v1 Announce Type: new Abstract: This paper presents a summary of the Competition on Adapting Foundation Models for Face Recognition Using Synthetic Training Data (AFMFR), held at the 2

arXiv:2607.18263v2 Announce Type: replace Abstract: AI-generated non-consensual intimate imagery (AIG-NCII) is not adequately addressed in AI/ML literature regarding AI-generated media, commonly refer

arXiv:2601.14032v2 Announce Type: replace Abstract: Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human preferences. Due to the difficulty of obtaining high-qua