Search: “safety”

arXiv:2606.31307v1 Announce Type: new Abstract: Large language models used in task-oriented dialogue often produce fluent but unsafe responses when backend database calls fail, return empty results, o

Great creative happens when your tools move at the speed of your ideas. To help you create rich, reliable experiences while reducing regeneration time and costs, we’re adding two new models to Gemini

arXiv:2511.05852v4 Announce Type: replace-cross Abstract: Knowledge editing (KE) offers a lightweight alternative to retraining for updating large language models (LLMs). Meanwhile, fine-tuning remain

arXiv:2603.03335v2 Announce Type: replace Abstract: Large language models (LLMs) exhibit a wide range of capabilities, including mathematical reasoning, code generation, and linguistic behaviors. We s

arXiv:2606.28863v1 Announce Type: cross Abstract: AI systems increasingly exhibit behavior that differs systematically between evaluation and deployment contexts. Alignment faking, sandbagging, benchm

arXiv:2510.14207v3 Announce Type: replace Abstract: Large Language Model (LLM) agents are powering a growing share of interactive web applications, yet remain vulnerable to misuse and harm. Prior jail

arXiv:2606.30220v1 Announce Type: new Abstract: High benchmark accuracy does not guarantee genuine use of visual evidence. We study this problem in traffic accident Video Question Answering (VideoQA),

arXiv:2606.30059v1 Announce Type: new Abstract: Industry-scale video and live-streaming moderation imposes requirements that are difficult to satisfy with generic pretrained public models or external

arXiv:2606.27944v1 Announce Type: cross Abstract: Phone-use Agents can execute complex tasks end to end across real mobile applications. By operating a real device on the user's behalf, they reach far

arXiv:2606.29399v1 Announce Type: new Abstract: Reviewing nuclear regulatory documents requires multi-hop reasoning across tens of thousands of pages, where judgments depend on evidence assembled acro

arXiv:2606.29171v1 Announce Type: cross Abstract: While existing data attribution methods can identify which training examples build specific mechanistic circuits, they cannot explain how training dat

arXiv:2606.29700v1 Announce Type: new Abstract: Planning often requires symbolic specifications that are both executable and verifiable. For large language models deployed in autonomous or decision-su

arXiv:2606.30383v1 Announce Type: new Abstract: A rapidly growing class of LLM agents is multi-party: the agent acts for a principal (who briefs it, sends follow-ups, and receives results) while also

arXiv:2606.27500v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) specialized in healthcare are emerging as a promising research direction due to their potential impact in clinica

The Hugging Face CEO argues that being characterized as 'too dangerous' can serve as effective marketing for frontier AI companies, suggesting that such controversy may enhance their public profile an

arXiv:2606.27622v1 Announce Type: new Abstract: Byzantine-robust federated learning seeks to protect distributed model training from malicious or corrupted clients without requiring access to their pr

arXiv:2606.28011v1 Announce Type: cross Abstract: We propose an agentic Large Language Model (LLM) framework for active Fault-Tolerant Control (FTC) that transforms fault detection outputs into constr

arXiv:2409.13007v3 Announce Type: replace-cross Abstract: Class imbalance poses a significant challenge in classification tasks, often causing standard learning algorithms to become biased toward the

Clem Delangue argues that open-source AI development offers significant benefits for technological progress, market competition, and system transparency while presenting substantially lower risks comp

Ethan Mollick raises questions about whether Google's Gemini 3.5 Pro model should be subject to export controls, suggesting concerns about its capabilities and potential regulatory implications. The p

VCs are now sharing screenshots in group chats of Claude discouraging investment in open-source AI infra startups and models. Obviously there is an absolute EXPLOSION of pitches in inference companies

arXiv:2606.26541v1 Announce Type: new Abstract: Data from affected populations are crucial for informing humanitarian response, but their value depends on timely and consistent interpretation of nuanc

arXiv:2606.26753v1 Announce Type: new Abstract: Conversational memory retrieval optimizes relevance, yet a retrieved memory can be relevant and simultaneously outdated: a later turn updates, corrects,

arXiv:2606.12716v2 Announce Type: replace Abstract: The integration of Large Language Models (LLMs) and Multimodal LLMs (MLLMs) into scientific peer-review workflows introduces novel and significant r

arXiv:2508.17916v2 Announce Type: replace Abstract: Depth estimation is a foundational component for 3D reconstruction in minimally invasive endoscopic surgeries. However, existing monocular depth est

arXiv:2606.27128v1 Announce Type: new Abstract: Wildfire monitoring from UAVs requires reliable reasoning over complex aerial scenes, where smoke, scale variation, and occlusions often limit RGB-only

arXiv:2606.26936v1 Announce Type: cross Abstract: With a profusion of jailbreaks for LLMs now widely known, a growing concern is that non-expert malicious actors ('the average Jane') could elicit acti

arXiv:2606.26783v1 Announce Type: cross Abstract: Fang et al. (2025) introduced a null-space constrained projection, named AlphaEdit, for locate-then-edit knowledge editing methods, theoretically guar

arXiv:2602.08995v2 Announce Type: replace Abstract: Computer-use agents (CUAs) have made tremendous progress in the past year, yet they still frequently produce misaligned actions that deviate from th

arXiv:2606.25487v1 Announce Type: new Abstract: Almost every paper on LLM jailbreaks and prompt injection reports an attack-success rate (ASR), and that number is assigned not by people but by an auto

arXiv:2606.25990v1 Announce Type: new Abstract: As multimodal conversational systems increasingly engage in spoken interaction, their ability to navigate paralinguistic social cues has become a critic

arXiv:2512.02080v3 Announce Type: replace-cross Abstract: The integration of Formal Verification tools with Large Language Models (LLMs) offers a path to scale software verification beyond manual work

arXiv:2606.25160v1 Announce Type: cross Abstract: The rapid rise of Vision-Language Models (VLMs) in egocentric visual understanding has made low-latency inference in human-robot collaborative (HRC) t

arXiv:2606.25760v1 Announce Type: cross Abstract: Computer-use agents turn vision-language model (VLM) predictions into executable GUI clicks, so reliable uncertainty estimates are essential for rejec

arXiv:2606.25182v1 Announce Type: new Abstract: Jailbreak attacks reveal a persistent weakness in aligned Large Language Models: carefully crafted prompts can elicit policy-violating responses despite

arXiv:2606.25591v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have recently demonstrated strong generalization in robotic manipulation, yet their applicability to whole-body, con

A Tesla Model 3 crashed into a residential home in Katy, Texas, killing a 76-year-old grandmother, with the driver claiming Autopilot was active at the time. Elon Musk disputed the claim, and Tesla's

arXiv:2606.23870v1 Announce Type: cross Abstract: PLCverif is the most mature open-source platform for PLC formal verification, developed at CERN and in production use since 2019. Yet it has two funda

arXiv:2606.16821v2 Announce Type: replace Abstract: Large language model (LLM)-based search agents synthesize open-web content into actionable recommendations on behalf of users, creating a risk that

arXiv:2606.23938v1 Announce Type: new Abstract: Driving VLA models incorporating Chain-of-Thought (CoT) reasoning are attractive because they leverage pretrained VLM representations and expose interme

arXiv:2606.24523v1 Announce Type: cross Abstract: Scam phone calls exploit vulnerable communities worldwide, yet research on detection has focused almost exclusively on English and other high-resource

arXiv:2606.23992v1 Announce Type: cross Abstract: Clinical value sets define the standardized terminology codes used in quality measurement, phenotyping, cohort construction, and clinical decision sup

arXiv:2606.24145v1 Announce Type: new Abstract: Large language models (LLMs) can produce clinically fluent recommendations for type 2 diabetes while failing to satisfy guideline constraints or explici

Edge cases and failure modes reveal the fundamental boundaries and constraints of complex systems more effectively than typical operations, making them valuable for understanding system behavior and l

arXiv:2606.24759v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) have shown strong potential for autonomous driving scene understanding, yet existing methods still fac

arXiv:2606.22966v1 Announce Type: new Abstract: Many recent vision-language-action (VLA) policies adopt an imagine-then-act design. A world-action model (WAM) first imagines a short future as a latent