Search: “safety”

arXiv:2610.00601v1 Announce Type: cross Abstract: Reasoning-enabled VLA policies expose chain-of-thought (CoT) traces that appear to explain and guide their actions, creating a potential interface for

arXiv:2609.38379v1 Announce Type: new Abstract: Large language models (LLMs) are frequently updated for various use cases, where filtering out misaligned training samples is a common practice for prev

arXiv:2510.26142v2 Announce Type: replace Abstract: Trajectory planning for mobile robots remains a major challenge, particularly in cluttered environments, where existing planning algorithms often fa

arXiv:2609.39101v1 Announce Type: new Abstract: Equipping VLM agents with world modeling capabilities has shown strong potential for complex reasoning and long-horizon planning, while reducing the dep

arXiv:2609.39071v1 Announce Type: new Abstract: Legal language models require reward signals that capture not only answer correctness but also the multidimensional quality of legal responses. Existing

Artificial intelligence giant Anthropic PBC is reportedly forging ahead with its plans to go public and has set a new target date of Nov. 9, according to a report from Bloomberg that cited anonymous s

arXiv:2609.39854v1 Announce Type: new Abstract: In this paper, we present an approach for combining stochastic nonlinear model predictive control (SNMPC) and reinforcement learning (RL) to enable prob

arXiv:2609.38389v1 Announce Type: cross Abstract: Large language models (LLMs) remain vulnerable to adversarial attacks that circumvent safety alignment to elicit harmful outputs. It remains unclear h

arXiv:2609.35812v1 Announce Type: new Abstract: In-car conversational assistants (ICAs) are increasingly integrated into vehicles to support route planning, vehicle control, and information access. En

arXiv:2609.36847v1 Announce Type: new Abstract: Percutaneous iliosacral screw fixation is an important minimally invasive treatment for unstable pelvic fractures. Because the sacroiliac region has com

Meeting the moment The global conversation on AI has begun. In the wake of Jacob Coxon’s resignation from Anthropic, calls by AI CEOs and over a thousand employees for a potential industry slowdown, a

arXiv:2609.36633v1 Announce Type: new Abstract: This paper proposes a physics-guided gradient-ascent-based machine unlearning method that couples the forgetting signal with the physical residual of th

arXiv:2609.36851v1 Announce Type: new Abstract: End-to-end autonomous driving policies are commonly trained via imitation learning on logged demonstrations without observing the consequences of their

arXiv:2609.32740v1 Announce Type: new Abstract: Intraoperative anesthesia requires systems to interpret evolving multimodal evidence, recommend timely management, and revise decisions as patient state

arXiv:2609.33637v1 Announce Type: cross Abstract: In this paper, we propose a hierarchical multi-agent reinforcement learning framework for coordinating robot teams in warehouse environments under com

arXiv:2609.33543v1 Announce Type: cross Abstract: Coupled rollouts can reduce the noise of counterfactual action comparisons, but two issues prevent standard common-random-number constructions from se

arXiv:2609.34426v1 Announce Type: new Abstract: This paper addresses the problem of safe offline reinforcement learning, which involves training a policy to satisfy safety constraints using an offline

arXiv:2607.15457v2 Announce Type: replace Abstract: We study robust peak-cost constrained reinforcement learning (ours), where the objective is to maximize expected reward while controlling the maximu

arXiv:2609.31773v1 Announce Type: new Abstract: We study whether a manually specified runtime supervisor can correct recurring failures of an existing end-to-end parking policy in a fixed CARLA parkin

NVIDIA OpenShell 0.1.0 is an open‑source runtime that enforces which systems and data an AI agent may access without requiring changes to the agent itself. Its components—Gateway, Supervisor, Sandbox,

arXiv:2609.30341v1 Announce Type: new Abstract: Data Spaces enable sovereign and governed data sharing across organizational boundaries, but their integration with AI agents remains challenging due to

arXiv:2609.31062v1 Announce Type: new Abstract: Patient-facing AI assistants promise valuable support to patients, but incoming queries can pose medical risks. To create guardrails, we work with oncol

arXiv:2609.30572v1 Announce Type: new Abstract: Large language models are often post-trained on expert demonstrations using cross-entropy (CE), even when the downstream objective is not to imitate the

From what we know (take with a grain of salt, we need much more transparency!), if @OpenAI had been running this on their own agents that attacked us, they would have caught them before we did! Since

arXiv:2609.30657v1 Announce Type: cross Abstract: Large language model email assistants are particularly vulnerable to indirect prompt injection because untrusted email content can be retrieved into t

arXiv:2609.31032v1 Announce Type: cross Abstract: Existing text-to-video (T2V) jailbreak methods mainly seek more effective or stealthier attack candidates. In guarded T2V systems, however, video gene

arXiv:2609.31603v1 Announce Type: cross Abstract: Large language models (LLMs) implicitly infer attributes of their users and adapt their behavior accordingly, yet these beliefs remain difficult to in

OpenAI: OpenAI says it paused training, evaluation, and inference with tool-use of its most capable models after a model bypassed internet restrictions during training — Summary — An agent attempting

The volume of data being generated today brings both opportunity and massive operational complexity. Most teams that operate at scale don't discover issues until they appear on an invoice — and by the

arXiv:2609.27938v1 Announce Type: new Abstract: Enabling operators to perceive and interact with remote environments naturally is a fundamental challenge in robotic teleoperation. This is especially c

arXiv:2609.27756v1 Announce Type: new Abstract: Large language models are increasingly asked to analyze data and report what the results mean, a task distinct from the belief- or preference-alignment

arXiv:2609.26490v1 Announce Type: new Abstract: This study introduces an interdisciplinary framework for benchmarking robots deployed in public environments, addressing the gap between traditional lab

arXiv:2609.25031v1 Announce Type: new Abstract: In the field of Human-Robot Interaction (HRI), achieving flexibility in human-accompanying within real-world environments holds great potential for vari

arXiv:2510.17904v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are widely used because they process structures, syntax and code well, but this same ability also makes them para

arXiv:2609.23731v1 Announce Type: cross Abstract: Robotic systems are typically composed of multiple independently developed modules that work together to perceive, predict, and act in the environment

arXiv:2609.24547v1 Announce Type: new Abstract: Real-time embodied companion interaction requires a robot to infer user intent from streaming speech, generate timely responses, and execute expressive,

🚨 BREAKING: US Treasury Secretary Scott Bessent declares OpenAI management personally responsible for HuggingFace hack > 'The Hugging Face incident, that is the responsibility of the OpenAI management

The loudest voices stoking fears about AI dangers have made tremendous headway in the past two weeks. AI technology has not taken some unexpected, dangerous turn, but the hype around it — propelled by

arXiv:2609.21580v1 Announce Type: new Abstract: Fully-actuated multirotor aerial vehicles must not only track nominal wrenches but retain the 'readiness' to modulate them rapidly under disturbances. C

arXiv:2609.20989v1 Announce Type: cross Abstract: As generative AI is increasingly used as a source of personal financial guidance, understanding how people appraise such advice is important for suppo

Truman Dickerson / Business Insider: Jensen Huang says AI leaders calling for regulation don't want new legislation, but to be “relieved of the laws we do have” because of “ulterior reasons” — Don't l

Anthropic, an AI safety and research organization, has established a “wet lab” in the Bay Area to enable the Claude language model to perform real‑world biology experiments. The move accompanies effor

gotta agree with @noahopinion that having an arrogant and somewhat tone deaf AI company starting a wet lab is a not a great idea. michael crichton made a movie about this kind of thing. Only Anthropic

with @Thom_Wolf in sunny italy ☀️chatting about the @huggingface @OpenAI attack, the “tell” that it was an agentic swarm, how misalignment arises in RL, whether agent awareness of evaluation is eviden

arXiv:2609.19272v1 Announce Type: new Abstract: Research in humanoid robotics has achieved rapid progress in locomotion, and recent results have pushed the boundary on autonomous navigation. We demons

Micah Barkley / Bloomberg: Andrew Ng says renewed AI extinction warnings are “much more science fiction than science” and the latest “wave of PR” is probably intended to shape regulation — Artificial