Search: “safety”

Evaluating the Diagnostic Robustness of Vision-Language Models Under Visual and Textual Perturbations

arXiv:2608.04885v1 Announce Type: cross Abstract: Standard accuracy metrics for VLMs often mask significant reliability failures in sensitive domains. In this work, we utilize a histopathology-validat

Safety

Feedback Loops and Code Perturbations in LLM-based Software Engineering: A Case Study on a C-to-Rust Translation System

DGX agent

arXiv:2512.02567v2 Announce Type: replace-cross Abstract: The advent of strong generative AI has a considerable impact on various software engineering tasks such as code repair, test generation, or la

safetyarxiv-cs-ai

6 Aug 2026

Guideline-as-Oracle: Zero-Annotation Training of an Ophthalmic Telephone Triage Agent

arXiv:2608.04772v1 Announce Type: cross Abstract: Scaling supervision for multi-turn medical agents is difficult because expert dialogue annotation is costly and clinical conversations are privacy-res

Local Violation Certification for Linear Predict-Then-Optimize Pipelines

arXiv:2608.04474v1 Announce Type: new Abstract: Data-driven decision pipelines combining predictive machine learning models with downstream optimization software are increasingly used to make high-sta

Long-term Measurements: Towards a Longitudinal Understanding of Human-AI Interactions

arXiv:2608.02491v2 Announce Type: replace Abstract: Language models have taken on the role of a very new type of technology, by virtue of their 'human-ness' and rapid integration into users' daily liv

Memorization in Large Language Models in Medicine: Prevalence, Characteristics, and Implications

arXiv:2509.08604v5 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated significant potential in medicine, with many studies adapting them through continued pre-traini

On July 24, the Black at Mila community hosted Prof. Vukosi Marivate @vukosi (University of Pretoria, co-founder of Masakhane, Lelapa AI, an…

On July 24, the Black at Mila community hosted Prof. Vukosi Marivate @vukosi (University of Pretoria, co-founder of Masakhane, Lelapa AI, and Deep Learning Indaba) for a powerful session on the future

safetyyoshua-bengio--x

Real-time probabilistic tsunami forecasting via generative AI

arXiv:2608.04327v1 Announce Type: new Abstract: Explicit onshore tsunami inundation forecasting can improve public risk awareness, but deterministically predicted inundation boundaries under highly un

SafeCommit: Certifying When Memory-Grounded Agents May Safely Act

arXiv:2608.04289v1 Announce Type: new Abstract: Long-horizon agents increasingly use persistent memory and tools to take actions with external side effects. A central failure mode is premature commitm

Temporal Context Awareness: A Defense Framework Against Multi-turn Manipulation Attacks on Large Language Models

arXiv:2503.15560v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly vulnerable to sophisticated multi-turn manipulation attacks, where adversaries strategically build conte

A game theory for foundation models shows new paths to rational cooperation through similarity inference

arXiv:2608.03958v1 Announce Type: new Abstract: As autonomous agents powered by foundation models are increasingly integrated into social and economic systems, understanding the principles governing t

A Wearable Stiffness-Rendering Haptic Device with a Honeycomb Jamming Mechanism for Bilateral Teleoperation

arXiv:2608.03002v1 Announce Type: new Abstract: This paper addresses the challenge of providing kinesthetic feedback in bilateral teleoperation by designing a wearable, lightweight (20 g), and compact

Accelerating Human-Aware Robot Trajectory Generation via Diffusion and Consistency Distillation

arXiv:2608.03159v1 Announce Type: new Abstract: This research proposes a constrained motion planning framework for robot manipulators in human-robot interaction (HRI). For a non-redundant manipulator

AI Assistance Reduces Persistence and Hurts Independent Performance

arXiv:2604.04721v3 Announce Type: replace Abstract: People often optimize for long-term goals in collaboration: A mentor or companion doesn't just answer questions, but also scaffolds learning, tracks

Another real-world manifestation of the kind of misaligned actions frontier systems developed by leading companies can take to achieve goals…

Another real-world manifestation of the kind of misaligned actions frontier systems developed by leading companies can take to achieve goals. Current frontier AI models are trained with reinforcement

safetyyoshua-bengio--x

Attribute-based Undetectable Watermarking for Generative AI Models

arXiv:2608.03174v1 Announce Type: cross Abstract: Generative AI systems increasingly produce content whose provenance is difficult to verify, motivating watermarking techniques for identifying model-g

Control Barrier Functions via Minkowski Operations for Safe Navigation among Polytopes

arXiv:2608.02886v1 Announce Type: new Abstract: Safely navigating polytopic environments while respecting the dynamics, control, and exact geometry of the underlying system is a challenge in robotics.

Flying over The Uncertain Nature (FORTUNE): Intelligent and Humanistic 3D Path Planning for Low-Altitude Collaboration

arXiv:2608.03408v1 Announce Type: new Abstract: The proliferation of low-altitude intelligent agents is increasing the demand for timely and socially responsible collaborative sensing in dynamic urban

GenOS: Compositional Certificates for Semantic Robustness in AI Code Generation

arXiv:2608.03588v1 Announce Type: cross Abstract: AI coding agents are stochastic workflows: prompts are interpreted, artifacts are sampled, validators produce observations, and orchestrators commit o

ICO: Enhancing Semantic-Shift Jailbreaks via Iterative Context Optimization

arXiv:2608.03210v1 Announce Type: new Abstract: Foundation models have achieved remarkable success across diverse tasks, but they remain vulnerable. To investigate such vulnerabilities, semantic-shift

Long-term Traffic Scene Prediction via Polynomial Representations in Autonomous Driving

arXiv:2608.03330v1 Announce Type: new Abstract: This thesis addresses fundamental challenges in traffic scene prediction for autonomous driving by introducing robust and computationally efficient mode

MVP-Tac: A Miniaturized Dual-Modal Vision and Photoelastic Tactile Sensor for Robot-Assisted Minimally Invasive Surgery

arXiv:2607.18660v2 Announce Type: replace Abstract: Robot-assisted minimally invasive surgery (RMIS) offers major benefits over open and conventional laparoscopic procedures, yet it still lacks tactil

RealWeather: Realistic and Scene-Faithful Weather Translation with Driving World Models

arXiv:2608.02953v1 Announce Type: new Abstract: Realistic weather translation is valuable for developing and evaluating autonomous driving systems, yet collecting paired videos of the same scenes unde

Robust General Utility for Reinforcement Learning

arXiv:2608.03562v1 Announce Type: new Abstract: Reinforcement learning (RL) with general utility extends classic RL by optimizing an arbitrary utility functional of the policy-induced occupancy measur

Rogue AI agents created fake online identities in another hacking attempt

Yet more rogue AI agents from OpenAI and Anthropic have been caught attempting to hack real targets online without permission. The discoveries add to a growing list of previously unknown incidents tha

safetythe-verge-ai

Stiffness Copilot: An Impedance Policy for Contact-Rich Teleoperation

arXiv:2603.14068v2 Announce Type: replace Abstract: In teleoperation of contact-rich manipulation tasks, selecting robot impedance is critical but difficult. The robot must be compliant to avoid damag

A Forward-Inverse Dynamic Game Framework for Enhanced Multi-Agent Trajectory Planning

arXiv:2608.01636v1 Announce Type: new Abstract: This paper studies feedback Nash equilibrium (FBNE) seeking for multi-agent trajectory planning in nonlinear dynamical systems with unknown agents' obje

ARMOR: Robust Reinforcement Learning-based Control for UAVs under Physical Attacks

arXiv:2506.22423v2 Announce Type: replace Abstract: Unmanned Aerial Vehicles (UAVs) depend on onboard sensors for perception, navigation, and control. However, these sensors are susceptible to physica

Constrained Co-Design for Photonic Bayesian Neural Networks

arXiv:2608.02229v1 Announce Type: new Abstract: Classical neural networks frequently produce overconfident predictions on ambiguous or out-of-distribution (OOD) data, a liability that grows with each

DiffuseAgent-MI: Distributionally-Grounded,Tool-Integrated Self-Evolving Agents for Faithful Visual Reasoning

arXiv:2608.00540v1 Announce Type: new Abstract: Tool-integrated vision-language agents have made remarkable progress on compositional and multi-step visual reasoning. Yet their outputs frequently exhi

EndoWAM: A Grounded World-Action Model for Generalizable Endoscopic Navigation

arXiv:2608.01221v1 Announce Type: new Abstract: Autonomous endoscopic navigation can reduce clinicians' operational burden, yet robust control remains challenging due to tissue deformation, transient

Expert-Choice Routing Enables Adaptive Computation in Diffusion Language Models

arXiv:2604.01622v2 Announce Type: replace-cross Abstract: Diffusion language models (DLMs) enable parallel, non-autoregressive text generation, yet existing DLM mixture-of-experts (MoE) models inherit

From Failures to Supervision: DynamicEnvPlan for Robust Long-Horizon Embodied Planning

arXiv:2608.00613v1 Announce Type: new Abstract: Physical-world interaction is inherently dynamic, as environments can evolve during execution, requiring agents to adapt their plans under non-stationar

Model Releases

Humans Are More Diverse: Frontier LLMs Show Extreme Policies in Idealised AI Development Races

model-releasesarxiv-cs-lg

arXiv:2608.01193v1 Announce Type: cross Abstract: An AI development race creates a multi-agent safety dilemma. Each company can develop slowly and safely, or move faster while taking a risk that may r

Interaction Dynamics MPC for Knee Rehabilitation Exoskeletons: A Closed-Loop SEA Outer-Loop Study

arXiv:2606.13485v3 Announce Type: replace-cross Abstract: Safe rehabilitation is an interaction-dynamics problem: the controller must regulate a prescribed motion while absorbing involuntary spasm, vo

Invisible Ink Threats: Adversarial Goals Behind Legitimate Tasks in Computer-Use Agents

arXiv:2608.02018v1 Announce Type: new Abstract: Computer-use agents (CUAs), which empower large language models to autonomously operate operating systems and the web, are increasingly vulnerable to in

Learning-Based Motion Planning for Dynamic Environments: From Foundational Algorithms to Emerging Paradigms

arXiv:2608.00625v1 Announce Type: new Abstract: Motion planning in dynamic environments is a fundamental problem in robotics, aiming to generate safe and efficient paths, trajectories, or control acti

Near-Optimal Reinforcement Learning for Constrained Recurrence Objectives

arXiv:2511.19849v2 Announce Type: replace-cross Abstract: Recurrence objectives, where a target region must be visited infinitely often, are a fundamental class of specifications for Markov decision p

Neural operator learning for collision-aware trajectory planning of spacecraft swarms

arXiv:2608.00320v1 Announce Type: new Abstract: Autonomous spacecraft swarms must plan fuel-efficient, collision-free maneuvers in increasingly congested orbits, yet classical trajectory optimization

No One Wins in Nuclear War: A Social Simulation of Military Decision-making

arXiv:2608.01868v1 Announce Type: cross Abstract: WOPR is a social-simulation environment for studying how organizations make high-stakes decisions, built on a deterministic, replay-validated rules en

Nonparametric Distribution Regression Re-calibration

arXiv:2602.13362v2 Announce Type: replace-cross Abstract: A key challenge in probabilistic regression is ensuring that predictive distributions accurately reflect true empirical uncertainty. Minimizin

ORCESTRA: VLM-driven Visual Robot programming in Mixed Reality

arXiv:2608.00775v1 Announce Type: cross Abstract: ORCESTRA is a mixed-reality system for programming robot digital twins through no-code waypoint teaching and language-guided control. In a passthrough

Red Hat leads open-source project to automate AI governance

IBM Corp.’s Red Hat subsidiary today announced the formation of asago, an open-source community project intended to turn artificial intelligence governance policies into operational controls that can

safetysiliconangle

Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Models

arXiv:2507.02778v3 Announce Type: replace Abstract: Although large language models (LLMs) have transformed AI, they still make errors and follow unproductive reasoning paths. Self-correction is vital

StableMimic: Smooth Human-Like Recovery for Humanoid Motion Tracking - Learning Beyond the Tracking Distribution for Structured Post-Fall Behavior

arXiv:2608.02385v1 Announce Type: new Abstract: Humanoid motion trackers perform reliably within learned tracking distributions, but falls can move the robot into low-height, contact-rich states from

TANGO-VIO: Triangulation-Aware Navigation with Guaranteed Feature-Observability for Visual-Inertial Odometry

arXiv:2608.02079v1 Announce Type: new Abstract: In vision-aided navigation and visual-inertial odometry, the quality of triangulated three-dimensional feature positions is a fundamental prerequisite f

TravKAN: Fast and Interpretable Nonlinear Traversability Analysis with Kolmogorov-Arnold Networks

arXiv:2608.02320v1 Announce Type: cross Abstract: Traversability analysis is a fundamental capability for autonomous mobile robots operating in unstructured environments. While modern machine learning

Trust or Check? Understanding the (Evolutionary) Dynamics of User Trust in AI Systems

arXiv:2603.24742v2 Announce Type: replace-cross Abstract: As the capabilities and adoption of Artificial Intelligence (AI) systems grow, trust in these AI systems is an increasingly urgent concern. Mu