Search: “safety”

arXiv:2604.18627v1 Announce Type: new Abstract: Ensuring human safety is of paramount importance in warehouse environments that feature mixed traffic of human workers and autonomous mobile robots (AMR

arXiv:2604.19001v1 Announce Type: new Abstract: Large reasoning models (LRMs) produce complex, multi-step reasoning traces, yet safety evaluation remains focused on final outputs, overlooking how harm

arXiv:2604.16424v1 Announce Type: cross Abstract: State-Space Models (SSMs) -- structured SSMs (S4, S4D, DSS, S5), selective SSMs (Mamba, Mamba-2), and hybrid architectures (Jamba) -- are deployed in

arXiv:2601.04043v2 Announce Type: replace Abstract: As Multimodal Large Language Models (MLLMs) become an indispensable assistant in human life, the unsafe content generated by MLLMs poses a danger to

arXiv:2509.18127v3 Announce Type: replace-cross Abstract: Sparse autoencoders (SAEs) enable interpretability research by decomposing entangled model activations into monosemantic features. However, un

arXiv:2604.09189v1 Announce Type: cross Abstract: LLMs internalize safety policies through RLHF, yet these policies are never formally specified and remain difficult to inspect. Existing benchmarks ev

arXiv:2604.08601v1 Announce Type: new Abstract: The rise of autonomous AI agents exposes a fundamental flaw in API-centric architectures: probabilistic systems directly execute state mutations without

arXiv:2610.14038v1 Announce Type: new Abstract: Embodied Artificial Intelligence (AI) introduces cyber-physical risks because digital failures and attacks can cause physical harm. This survey organize

Gary Marcus will be speaking at the @Bloomberg New Economy Forum in New Delhi tomorrow, October 15, on AI reliability, control and safety. @GaryMarcus Hope you’ll connect all the dots between… LLM bul

Generative AI: a yet-to-be-profitable industry facing price wars, increased competition, increased liability and safety concerns, and declining customer confidence, while often failing to deliver demo

arXiv:2610.14066v1 Announce Type: cross Abstract: Bird's-Eye-View (BEV) representations are increasingly used as compact inputs for autonomous driving perception and planning. However, lightweight and

The Information: A look at OpenAI's safety concerns over loop transformers before shipping its next major model; Microsoft accidentally confirmed GPT-6.1 Sol uses the technique — OpenAI is grappling w

Tony Diver / Telegraph: Sources: the US restores the UK AISI's access to the latest US models for safety testing, after ordering OpenAI and Anthropic to stop sharing models last month — US had blocked

arXiv:2510.13154v3 Announce Type: replace Abstract: What happens inside a language model when alignment training conflicts with a cultural value it encodes? Across 16 MENA countries, 26 models, and 1.

OpenAI is standing firm on its decision to fire three safety researchers after an investigation found they committed 'a significant breach of trust.' In a post on X on Friday, the company said Jasmine

arXiv:2502.06359v3 Announce Type: replace Abstract: Ensuring safe driving while maintaining travel efficiency for autonomous vehicles in dynamic and occluded environments is a critical challenge. This

Ben Berkowitz / Axios: Sam Altman says he's “very uncomfortable” with attributing religious force to AI, calling it “a real safety issue”, as Anthropic engages with religious leaders — OpenAI CEO Sam

How quickly things change in the artificial intelligence era. Just a few months after everyone was scrambling to infuse AI into every enterprise operation — and frankly they still are, as agents have

arXiv:2609.38421v1 Announce Type: new Abstract: Dynamical Systems (DS) are reactive motion policies representing vector fields trained with theoretical guarantees of stability and convergence. To ensu

Wall Street Journal: OpenAI says it “parted ways” with three researchers for violating its “handling sensitive” info policies; sources: they shared it with an AI safety organization — OpenAI has parte

arXiv:2609.39788v1 Announce Type: new Abstract: Latent communication enables multi-agent systems to exchange information directly in internal representation space, reducing the token, computation, and

arXiv:2609.39549v1 Announce Type: cross Abstract: As Large Language Model (LLM) agents are increasingly deployed in complex environments, multi-turn interaction attacks have become a significant secur

arXiv:2603.04410v3 Announce Type: replace-cross Abstract: While different stakeholders are trying to leverage Arabic Language Models (ALMs), safety alignment in ALMs remains largely underexplored, hin

arXiv:2609.29960v1 Announce Type: cross Abstract: Fine-tuning large language models on new objectives can improve helpfulness, instruction following, or domain-specific performance, but it can also in

arXiv:2609.25994v1 Announce Type: new Abstract: Providing safe and effective mobility assistance plays a crucial role in restoring independence and enhancing the quality of life for individuals with m

arXiv:2602.20628v2 Announce Type: replace Abstract: AIs are increasingly being deployed with greater autonomy and capabilities, which increases the risk that a misaligned AI may be able to cause catas

arXiv:2512.24493v3 Announce Type: replace-cross Abstract: Control barrier functions for port-Hamiltonian systems inherit model uncertainty when the Hamiltonian is learned from data. We show how to pro

arXiv:2609.21470v1 Announce Type: new Abstract: Sparse representation formulates the environment perception for the end-to-end driving system as a set of discrete elements like objects and lane lines.

arXiv:2609.21223v1 Announce Type: new Abstract: Vision-language-conditioned robot policies integrate perception, language understanding, and control for general-purpose manipulation. However, existing

arXiv:2609.19325v1 Announce Type: cross Abstract: Safety tuning pipelines judge only the final answer, which makes it difficult to distinguish robust refusal from two undesirable shortcuts: blanket re

In 2023, Lina Khan at the FTC launched an investigation into OpenAI over safety concerns. There was an entire AI regulatory program over there, including law enforcement, policy, and litigation. Trump

Jeezus. OpenAI cannot be trusted with the safety of the world. They can’t even keep their own servers secure. On July 25, we hacked OpenAI. Two bugs let us take over ChatGPT/Codex accounts of OpenAI e

arXiv:2609.20578v1 Announce Type: cross Abstract: Connected-vehicle safety evaluations rely on coupled traffic and network simulations, but standard channel models ignore radio resource competition in

New York Times: A former US State Department envoy says the US-China AI safety talks will not yield a breakthrough treaty as Beijing is prioritizing its strategic advantage — The United States is prep

Learn how to build a synthetic data augmentation pipeline on Amazon SageMaker AI and Amazon Rekognition that generates photo-realistic, auto-labeled training images for industrial safety AI. This appr

arXiv:2609.07288v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly employed to orchestrate robot behavior through natural-language interfaces, yet no benchmark exists to eva

I dropped out of a PhD in AI safety partially for the opposite reason. I didn’t believe AI existential risk was as important as the doomers think. My biggest pet peeve is that no one can really provid

Tim Fernholz / TechCrunch: Paul Christiano, an AI researcher and advisor at CAISI, is joining the OpenAI Foundation board of directors and its Safety and Security Committee — Paul Christiano, an influ

Despite everything that has happened, OpenAI has seemingly decided to stay competitive by burning down the only meaningful bit of safety assurance we actually have today - CoT monitoring. Completely d

arXiv:2606.16583v2 Announce Type: replace Abstract: Safe deployment of clinical vision-language models (VLMs) requires reliable uncertainty estimation (UE): a signal indicating when predictions should

Exciting day for NVIDIA and @huggingface. Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty. They allow every developer, startup, university,

arXiv:2609.02293v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) is a scaling architecture for large language models that activates only a small subset of expert modules per token, enabling

arXiv:2609.00760v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly trained to decline queries that fall outside their knowledge (knowledge-based refusal, KR) or violate safe

arXiv:2609.00370v1 Announce Type: cross Abstract: Surrogate safety measures allow road-safety assessment from trajectory data in which crashes are absent, yet the dominant proximity measures - time-to

arXiv:2607.10014v2 Announce Type: replace-cross Abstract: Learning-based separation assurance for small Unmanned Aircraft Systems (sUAS) achieves near-zero collision rates in simulation, but assumes a

arXiv:2512.15052v4 Announce Type: replace-cross Abstract: Disclaimer: Samples in this paper may be harmful and cause discomfort. Multimodal large language models (MLLMs) enable multimodal understandin