Search: “safety”

Spatiotemporal Semantic V2X Framework for Cooperative Collision Prediction

arXiv:2601.17216v3 Announce Type: replace-cross Abstract: Intelligent Transportation Systems (ITS) demand real-time collision prediction to ensure road safety and reduce accident severity. Conventiona

9 Jul 2026

Validate the Dream Before You Trust Its Verdict: Admissibility for World-Model Simulators

DGX agent

arXiv:2607.07196v1 Announce Type: cross Abstract: Across robotics, World Models (WMs) are increasingly used to evaluate action policies by simulating the consequences of actions in an imagined world,

safetyarxiv-cs-ai

9 Jul 2026

Model Releases

PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails

model-releasesarxiv-cs-ai

arXiv:2607.05910v1 Announce Type: cross Abstract: Image guardrails are typically trained and evaluated under a fixed safety policy, implicitly treating safety as an intrinsic property of an image. Rea

8 Jul 2026

Safe Bayesian Optimization with Counterfactual Policies

arXiv:2607.05620v1 Announce Type: cross Abstract: In many decision-making settings, new interventions are acceptable only if they do not reduce outcomes below some established threshold. For example,

8 Jul 2026

Synthetic-to-Real Translation for Class-Agnostic Motion Prediction

arXiv:2607.06319v1 Announce Type: new Abstract: Motion understanding is critical for ensuring safety and robustness in autonomous driving systems, driving increasing interest in motion prediction. A k

8 Jul 2026

Beyond Heuristics: A Standardized Real2Sim Pipeline for Physical Human Robot Interaction in Human-in-the-Loop Simulation

arXiv:2607.03017v1 Announce Type: new Abstract: The aging global population drives demand for assistive robots, yet the safety risks and costs of physical testing make Human-in-the-Loop (HITL) simulat

CDCP: Conditional Diffusion Model with Contextual Prompts for Multi-task Offline Safe Reinforcement Learning

arXiv:2607.03903v1 Announce Type: new Abstract: Multi-task offline safe reinforcement learning (RL) promises to learn a shared optimal safe policy from offline data across multiple tasks. This paradig

Model Releases

Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models

model-releasesarxiv-cs-cl

arXiv:2506.07468v4 Announce Type: replace-cross Abstract: Conventional large language model (LLM) safety alignment relies on a reactive, disjoint loop: attackers exploit a static model, then defenders

Human-Centric Reflective Architecture for Human-AI Collaborative Decision-Making

arXiv:2607.03025v1 Announce Type: new Abstract: The use of Large Language Models (LLMs) across diverse areas of human activity-ranging from everyday tasks to safety-critical applications-aims to enhan

Knowing When Not to Answer: Lightweight KB-Aligned OOD Detection for Safe RAG

arXiv:2508.02296v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) systems are increasingly deployed in high-stakes domains, where safety depends not only on how a system answers

safetyarxiv-cs-cl

Open Problems in AI Incident Governance

arXiv:2607.05163v1 Announce Type: cross Abstract: AI systems may produce failures after deployment that pre-deployment safety assessments do not anticipate. Managing these failures requires what we re

Overloading Large Vision-Language Models for Jailbreaking

arXiv:2607.02961v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) exhibit remarkable vision-language capabilities and are increasingly deployed in real-world applications such as pe

Probabilistic Robustness in Medical Image Classification

arXiv:2607.03797v1 Announce Type: new Abstract: Deep learning (DL) has shown strong performance in medical image classification, but its trustworthy deployment remains challenging in safety-critical c

RL-Ballast: Ship Ballast Water Path Planning and Clog Prediction via Reinforcement Learning

arXiv:2607.04906v1 Announce Type: new Abstract: Under the Shipping 4.0 paradigm, autonomous and reduced-crew vessels require intelligent internal systems to maintain operational safety and structural

Safe RLHF Beyond Expectation: Stochastic Dominance for Universal Spectral Risk Control

arXiv:2603.10938v2 Announce Type: replace-cross Abstract: Safe Reinforcement Learning from Human Feedback (RLHF) typically enforces safety through expected cost constraints, but the expectation captur

Uncertainty Quantification for Regression: A Unified Framework based on kernel scores

arXiv:2510.25599v2 Announce Type: replace Abstract: Regression tasks, notably in safety-critical domains, require reliable uncertainty quantification, yet the literature remains largely classification

UNDREAM: Bridging Differentiable Rendering and Photorealistic Simulation for End-to-end Adversarial Attacks

arXiv:2510.16923v3 Announce Type: replace-cross Abstract: Deep learning models deployed in safety critical applications like autonomous driving use simulations to test their robustness against adversa

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models

arXiv:2509.25533v2 Announce Type: replace-cross Abstract: As Vision Language Models (VLMs) are deployed across safety-critical applications, understanding and controlling their behavioral patterns has

When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games

arXiv:2607.05132v1 Announce Type: cross Abstract: As large language models are deployed as autonomous agents that communicate intentions before acting, a critical safety question is whether agents tha

safetyarxiv-cs-cl

Rethinking Post-Hoc Calibration in Semantic Segmentation

arXiv:2607.01902v1 Announce Type: cross Abstract: Reliable confidence estimates are essential in semantic segmentation, especially in safety-critical settings where overconfident errors can mislead do

3 Jul 2026

Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces

arXiv:2607.00481v1 Announce Type: cross Abstract: Jailbreak attacks remain a critical threat to the safe deployment of large language models (LLMs). While prior work has primarily studied attacks and

Decentralized Geometric Control for Cable-Suspended Payload Transport with Adaptive Mass Estimation

arXiv:2607.00024v1 Announce Type: new Abstract: Cooperative aerial transport requires controllers that respect nonlinear manifold geometry, operate without centralized coordination, and respect operat

Evaluating Implicit Biases in LLM Reasoning through Logic Grid Puzzles

arXiv:2511.06160v2 Announce Type: replace Abstract: While recent safety guardrails effectively suppress overtly biased outputs, subtler forms of social bias emerge during complex logical reasoning tas

From Prediction Uncertainty to Conformalized Distance Fields for Safe Motion Planning

arXiv:2607.00776v1 Announce Type: new Abstract: Safe motion planning in dynamic environments requires reasoning about the uncertainty in predicted obstacle motion without sacrificing real-time perform

From Silos to Systems: Process-Oriented Hazard Analysis for AI Systems

arXiv:2410.22526v2 Announce Type: replace Abstract: To effectively address potential harms from Artificial Intelligence (AI) systems, it is essential to identify and mitigate system-level hazards. Cur

Learning Expert Strategy for Autonomous Robotic Endovascular Intervention via Decoupled Procedural Execution

arXiv:2607.00066v1 Announce Type: new Abstract: Endovascular interventions are high-stakes procedures requiring precise device operation within complex and tortuous vascular anatomies. Autonomous endo

Sam Altman calls for US-led international forum to set global AI standards

Sam Altman is calling for a US-led international forum to set global safety standards for artificial intelligence, arguing that no single country should be left to dominate the technology. In an op-ed

safetysiliconangle

DDIAgents: Mechanism-Conditioned Context Flow for Drug-Drug Interaction Prediction

arXiv:2606.31085v1 Announce Type: new Abstract: Drug-drug interaction (DDI) prediction is essential for medication safety, yet it requires reasoning over heterogeneous biomedical evidence whose releva

FLARE-AI: Flaw Reporting for AI

arXiv:2606.31567v1 Announce Type: cross Abstract: Flaw reporting for deployed AI systems is fundamental to identifying system failures and improving AI safety. Yet the AI reporting ecosystem is fragme

Great new episode with @So8res on @PeterMcCormack's podcast, give it a watch! https://www.youtube.com/watch?v=1laTnwAdaLA

Connor Leahy promoted a podcast episode featuring So8res (a researcher/AI safety figure) on Peter McCormack's podcast, sharing a YouTube link to the full video on X/Twitter. The post encourages viewer

safetyconnor-leahy--x

LabGuard: Grounding Natural-Language Laboratory Rules into Runtime Guards for Embodied Laboratory Agents

arXiv:2606.31045v1 Announce Type: new Abstract: Scientific embodied agents are increasingly capable of carrying out laboratory procedures, but executing these procedures safely in dynamic laboratory e

Stealthy Multi-Task Adversarial Attacks

arXiv:2411.17936v2 Announce Type: replace-cross Abstract: Deep neural networks are highly vulnerable to adversarial perturbations, raising serious safety concerns in the real-world systems. While prio

ActiveVital: Geometry-Aware Embodied Vital Signs Monitoring for Home Healthcare Robots

arXiv:2606.30275v1 Announce Type: new Abstract: Home robots require reliable vital signs monitoring to support long-term companionship and safety in daily environments, yet obtaining respiration and h

LaGen: Towards Autoregressive LiDAR Scene Generation

arXiv:2511.21256v2 Announce Type: replace Abstract: Generative world models for autonomous driving (AD) are of great value in applications such as data augmentation, closed-loop simulation, and safety

VISTA-DZ: Visual Semantic Trajectory Adaptation for Personalized Dilemma Zone Prediction

arXiv:2606.29548v1 Announce Type: cross Abstract: Driver decision making in the dilemma zone at signalized intersections is safety critical, as vehicles approaching a yellow signal must decide whether

Zero-Label Driving Scenario Complexity Detection via Joint Embedding Predictive Architecture

arXiv:2606.28383v1 Announce Type: new Abstract: Identifying complex and safety-critical driving scenarios in large unlabelled datasets is an important but expensive problem. Existing approaches rely o

OperatorSHAP: Fast and Accurate Shapley Value Estimation for Neural Operators

arXiv:2606.28065v1 Announce Type: cross Abstract: Understanding model predictions is essential for physical applications, where outputs often inform safety-critical decisions, such as structural load

29 Jun 2026

PPO-EAL: Exact Augmented Lagrangian Proximal Policy Optimization for Safe Robotic Control

arXiv:2606.27861v1 Announce Type: new Abstract: Reinforcement learning (RL) has emerged as a promising solution to accomplish complex robotic control tasks; however, most of the current work ignores t

29 Jun 2026

Reasoning-Enhanced Rare-Event Prediction with Balanced Outcome Correction

arXiv:2601.16406v2 Announce Type: replace-cross Abstract: Rare-event prediction is critical in domains such as healthcare, finance, reliability engineering, customer support, aviation safety, where po

29 Jun 2026

Chai: Agentic Discovery of Cryptographic Misuse Vulnerabilities

arXiv:2606.26933v1 Announce Type: cross Abstract: AI-assisted vulnerability discovery has proven effective for bug classes like memory safety, where instrumentation confirms memory violations and effi

26 Jun 2026

HauntAttack: When Attack Follows Reasoning as a Shadow

arXiv:2506.07031v5 Announce Type: replace-cross Abstract: Emerging Large Reasoning Models (LRMs) consistently excel in mathematical and reasoning tasks, showcasing remarkable capabilities. However, th

26 Jun 2026

RecallRisk-BERT: A Multi-Task Framework for Post-Report Medical Device Recall Triage

arXiv:2606.27174v1 Announce Type: new Abstract: Medical device recalls are a critical regulatory mechanism for protecting patient safety. The growing volume of FDA recall records presents challenges i

26 Jun 2026

Model Releases

Falcon: Functional Assembly and Language for Compositional Reasoning in X-ray

model-releasesarxiv-cs-cv

arXiv:2606.25701v1 Announce Type: new Abstract: Conventional vision-language models are largely object-centric, focusing on detecting and describing individual entities. In safety-critical X-ray bagga

25 Jun 2026

The Tatoxa System for Text Detoxification in Low-Resource Languages: The Case of Tatar

arXiv:2606.26015v1 Announce Type: new Abstract: Text detoxification, the automated detection and mitigation of abusive and harmful content, is essential for ensuring the safety of online communities a

safetyarxiv-cs-cl

25 Jun 2026

Towards Understanding The Calibration Benefits of Sharpness-Aware Minimization

arXiv:2505.23866v2 Announce Type: replace Abstract: Deep neural networks have been increasingly used in safety-critical applications such as medical diagnosis and autonomous driving. However, many stu

25 Jun 2026

DDStereo: Efficient Dual Decoder Transformers for Stereo 3D Road Anomaly Detection

arXiv:2606.24805v1 Announce Type: new Abstract: Stereo-based 3D object detection still faces two critical safety challenges: real-time performance and open-set generalization. Existing stereo 3D metho

24 Jun 2026

One Year Later...The Harms Persist, But So Do We!

arXiv:2606.23884v1 Announce Type: cross Abstract: General-purpose large language models (LLMs) are increasingly used for mental health-related conversations, yet safety safeguards remain inadequate an

24 Jun 2026

An LLM-Explainable DRL Framework for Passenger-Directed Autonomous Driving

arXiv:2606.20640v1 Announce Type: cross Abstract: Autonomous vehicles offer the potential for safer and more efficient mobility, yet public trust remains limited due to the lack of transparency in the