Search: “safety”

arXiv:2604.04410v2 Announce Type: replace Abstract: Aligning language models with human preferences is essential for ensuring their safety and reliability. Although most existing approaches assume spe

arXiv:2609.34268v1 Announce Type: new Abstract: Large language models (LLMs) are now the default cognitive core of embodied household agents, yet the plans they emit are rarely checked against a groun

Anthropic PBC today announced the launch of Claude Sonnet 5.5, the most capable mid-tier model in the company’s AI family, designed for everyday tasks and a clear upgrade over the previous generation,

arXiv:2609.30275v1 Announce Type: new Abstract: A statistic reported without the quantity needed to interpret it is not evidence. We develop that thesis for a concrete practice in AI safety. Interpret

arXiv:2609.31154v1 Announce Type: new Abstract: Recent advances in text-to-image (T2I) generation have substantially improved visual synthesis, but have also raised increasing safety concerns due to t

arXiv:2609.30716v1 Announce Type: cross Abstract: When a language model receives two conflicting documents as input, how does it decide which one to prioritize? Does it rely on how the sources are fra

arXiv:2609.28703v1 Announce Type: cross Abstract: Hate speech on social media poses serious risks to social harmony, mental well-being, and public safety, making its timely and accurate detection esse

arXiv:2609.30217v1 Announce Type: cross Abstract: A central concern in AI safety is that agents may treat oversight as an obstacle when it conflicts with completing their goals. We study instrumental

arXiv:2609.26176v2 Announce Type: replace-cross Abstract: Encoded-prompt attacks are evaluated almost entirely on their harmful arm: a benchmark sends obfuscated harmful requests and reports how often

arXiv:2609.22694v1 Announce Type: new Abstract: Public crash databases increasingly support automated safety analysis, but crash severity prediction remains difficult to translate into public-sector d

arXiv:2609.23488v1 Announce Type: new Abstract: End-to-end autonomous driving maps current observations directly to future trajectories, yet those trajectories must remain valid as the scene evolves.

OpenAI announced the GPT‑6 Sol and Luna models on September 22 2026. These variants incorporate advances from the Astra project, yielding improved alignment safety relative to earlier GPT‑5.6 systems.

arXiv:2609.21504v1 Announce Type: new Abstract: Vision-and-language navigation (VLN) has advanced rapidly in static indoor environments, but robots operating in human-populated spaces must ground lang

arXiv:2609.21713v1 Announce Type: cross Abstract: Edge AI accelerators are increasingly deployed in safety-critical environments, where model outputs may control physical actuators, make access-contro

arXiv:2602.02888v2 Announce Type: replace-cross Abstract: Hallucinations remain a major obstacle for large language models (LLMs), especially in safety-critical domains. We present HALT (Hallucination

Zack Korman tweeted that rogue AI agents could pose a severe safety threat—“super scary” and potentially lethal—even to entire families. He clarified that the agent‑trace logs from the recent Hugging

With the recent Nvidia Huggingface acquisition and frontier AI labs screaming about safety and putting guardrails everywhere, I think it's important that we have local models that aren't affected by a

arXiv:2609.15297v1 Announce Type: new Abstract: In order to make Reinforcement Learning algorithms applicable in real world scenarios, safety must be ensured even under adverse operating conditions. I

arXiv:2609.15794v1 Announce Type: new Abstract: Clinical AI systems are evaluated with instruments built for research settings (reference-based similarity metrics and expert rubric panels) that measur

arXiv:2609.13328v1 Announce Type: cross Abstract: Anticipating whether a pedestrian will cross the road is safety-critical for autonomous vehicles, requiring real-time inference under challenging cond

arXiv:2609.12173v1 Announce Type: new Abstract: Transportation agencies need pedestrian volume estimates across entire road networks to prioritize safety investments, yet manual counts are expensive a

arXiv:2609.11185v1 Announce Type: new Abstract: Evidence-based medicine demands strict logical consistency, yet current evaluations of large language models (LLMs) prioritize superficial label matchin

arXiv:2609.10895v1 Announce Type: new Abstract: Reacting to sudden physical hazards (catching a slipping plate, dodging a falling knife) is both a meaningful test of embodied intelligence and a hard r

arXiv:2606.16723v2 Announce Type: replace Abstract: Large language model (LLM) agents increasingly take actions (screening applicants, recommending credit, triaging patients), yet fairness for LLMs is

arXiv:2609.08861v1 Announce Type: new Abstract: Benchmark scores are a central currency in model releases: they inform purchasing decisions, shape public trust, and influence policy. Yet, a key assump

arXiv:2609.10439v1 Announce Type: new Abstract: Large Language Models (LLMs) can memorize and reproduce sensitive, copyrighted, or otherwise undesirable training content, creating privacy, safety, and

arXiv:2609.05531v1 Announce Type: cross Abstract: No specification says how a governed autotelic AI agent organization, where agents pursue self-generated goals inside guardrails, should be designed a

arXiv:2609.07986v1 Announce Type: new Abstract: Purpose: Accurate CT protocol selection is critical for diagnostic quality and patient safety, yet the current process is manual, time-consuming, and pr

arXiv:2609.07188v1 Announce Type: new Abstract: Out-of-distribution (OOD) detection is critical for safe deployment of medical AI systems. Recently, test-time adaptation (TTA) has emerged as a new par

arXiv:2609.07780v1 Announce Type: new Abstract: Automated drone surveillance has become increasingly important for public safety, critical infrastructure protection,and restricted airspace monitoring.

arXiv:2609.08041v1 Announce Type: new Abstract: Many pedestrian trajectory prediction algorithms have been proposed to improve the safety of navigation for mobile robots working in human-robot coexist

arXiv:2609.05992v1 Announce Type: cross Abstract: As LLM-based agents continue to advance, their evaluation has become increasingly multifaceted: a capable agent must not only achieve high task comple

arXiv:2609.08512v1 Announce Type: new Abstract: Autonomous exploration on uneven terrain requires ground robots to balance exploration efficiency, coverage completeness, and terrain safety. Detailed t

Enterprise agent adoption isn’t one-size-fits-all. While many teams will opt for managed commercial platforms, such as Gemini Enterprise Agent Platform for turnkey agent deployment and governance, dev

arXiv:2609.03693v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to jailbreak attacks that bypass safety alignment through carefully crafted prompts. Many existing defense

arXiv:2609.05199v1 Announce Type: cross Abstract: We consider safety-critical control problems involving multiple requirements with different priorities and uncertainty in their evaluation. We represe

arXiv:2609.05241v1 Announce Type: new Abstract: A rapidly expanding ecosystem of actors is removing built-in safety guardrails from open-weight AI models. We profile this ecosystem by identifying key

arXiv:2609.03677v1 Announce Type: cross Abstract: Understanding the composition of large-scale autonomous driving datasets is essential for safety, robustness, and reliable operation across domains. F

arXiv:2609.02091v1 Announce Type: new Abstract: Knowledge editing provides an efficient way to update factual knowledge in large language models. However, malicious edits may introduce safety risks, m

arXiv:2609.02830v1 Announce Type: new Abstract: LiDAR-based semantic segmentation is a core perception module for autonomous vehicles and mobile robots. Despite the strong performance of recent state-

arXiv:2609.01161v1 Announce Type: new Abstract: Large language models can reproduce memorized text verbatim, yet copyright defenses are usually evaluated under incompatible protocols. We introduce Cop

arXiv:2609.00699v1 Announce Type: new Abstract: Reward models trained on human preferences are known to suffer from length, formatting, and other stylistic biases. In this paper we use patterning, whi

arXiv:2609.00385v1 Announce Type: cross Abstract: Autonomous highway overtaking demands foresighted decision-making to handle complex interactions, stochastic traffic evolution, and temporal risk accu

Anthropic PBC today debuted Claude Fable 5.1 and Claude Mythos 5.1, its most capable large language models to date. The launch comes a day after the company inked a 35 billion infrastructure deal with

arXiv:2608.30025v1 Announce Type: new Abstract: Large language models (LLMs) frequently generate source code containing vulnerabilities, yet little work studies the internal mechanisms that distinguis

After an unreleased OpenAI model wreaked enough havoc to make international headlines, OpenAI delayed the development of a different unreleased model suite, Astra, in order to shore up its safety work