Search: “safety”

Manifold-constrained Hamilton-Jacobi Reachability Learning for Decentralized Multi-Agent Motion Planning

arXiv:2511.03591v2 Announce Type: replace Abstract: Safe multi-agent motion planning (MAMP) under task-induced constraints is a critical challenge in robotics. Many real-world scenarios require robots

Safety

Mnemosyne: Agentic Transaction Processing for Validating and Repairing AI-generated Workflows

DGX agent

arXiv:2607.00269v1 Announce Type: new Abstract: LLMs, solvers, and agent teams increasingly generate workflow actions, repairs, and plans, but a generated action may be syntactically valid yet stale,

safetyarxiv-cs-ai

2 Jul 2026

Reasoning Up the Instruction Ladder for Controllable Language Models

arXiv:2511.04694v5 Announce Type: replace-cross Abstract: As large language model (LLM) based systems take on high-stakes roles in real-world decision-making, they must reconcile competing instruction

Surfacing Variations to Calibrate Perceived Reliability of MLLM-generated Image Descriptions

arXiv:2507.15692v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) provide new opportunities for blind and low vision (BLV) people to access visual information in their daily l

Teaching AI to run with the turbines

Artificial intelligence may have captured the public imagination through chatbots and image generators, but some of its most consequential use cases are unfolding far from consumer-facing tools. In in

safetymit-tech-review

What to expect during the Machina AI summit: Join theCUBE July 7

Physical artificial intelligence is becoming an industrial robotics problem. The market is shifting from software-only automation toward machines that must sense, decide and act in physical settings.

safetysiliconangle

Zero-Shot Distracted Driver Detection via Vision Language Models with Double Decoupling

arXiv:2601.08467v2 Announce Type: replace Abstract: Distracted driving is a major cause of traffic collisions, calling for robust and scalable detection methods. Vision-language models (VLMs) enable s

A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems

arXiv:2606.31639v1 Announce Type: cross Abstract: Large language models are no longer only text generators. They are increasingly embedded in retrieval pipelines, enterprise assistants, coding environ

A Scalable Whole-body Motion Transfer via Implicit Kinodynamic Motion Retargeting

arXiv:2509.15443v2 Announce Type: replace-cross Abstract: Human-to-humanoid imitation learning presents a promising pathway to address the severe data scarcity bottleneck in robotics by utilizing abun

A Tutorial on Autonomous Fault-Tolerant Control Using Knowledge-Grounded LLM Agents

arXiv:2606.31635v1 Announce Type: cross Abstract: Fault recovery in process plants still relies heavily on plant operators, especially when faults fall outside predefined supervisory logic. Operators

AI for Quality Assurance in the Operating Room

arXiv:2606.30657v1 Announce Type: cross Abstract: Surgical outcomes depend not only on patient factors and postoperative care but are also strongly influenced by the quality of the operation itself. Y

Certified Speculative Execution for Untrusted AI Agents

arXiv:2606.31023v1 Announce Type: cross Abstract: Hard-constrained sequential decision systems have no certified way to spend the test-time compute of modern AI: executing the multi-step drafts of a l

Freeform Preference Learning for Robotic Manipulation

arXiv:2606.32027v1 Announce Type: cross Abstract: Reward design remains a central bottleneck for autonomous robot policy improvement, especially in long-horizon manipulation tasks where sparse success

GRAPE: Graph-Augmented Prototype Explanations for Interactive Medical Image Diagnosis

arXiv:2606.30901v1 Announce Type: new Abstract: Prototype-based medical image classifiers present three clinical limitations: they treat findings as independent, silently amplify unsafe physician feed

Online Generation of Collision-Free Trajectories in Dynamic Environments

arXiv:2603.00759v2 Announce Type: replace Abstract: In this paper, we present an online method for converting an arbitrary geometric path, represented by a sequence of states, and generated by any pla

Relational and Sequential Conformal Inference for Energy Time Series over Graphs via Foundation Models

arXiv:2606.31804v1 Announce Type: new Abstract: Accurate energy demand forecasting is essential for the reliable operation and planning of modern sustainable energy systems. Spatial-temporal graph neu

Toxicity Assessment in Preclinical Histopathology via Class-Aware Mahalanobis Distance for Known and Novel Anomalies

arXiv:2602.02124v2 Announce Type: replace-cross Abstract: Drug-induced toxicity is a leading cause of preclinical and early-clinical failure, making early detection critical. Histopathology is the gol

Training Therapeutic Judges and Multi-Agent Systems for Human-Aligned Mental Health Support

arXiv:2606.30887v1 Announce Type: cross Abstract: Large language models show promise for mental health support, yet therapeutic quality improves only when evaluation functions as an actionable control

Venice AI, which offers access to 200+ AI models while allowing users to retain their privacy, raised a 65M Series A led by Dragonfly at a 1B valuation (Ram Iyer/TechCrunch)

Ram Iyer / TechCrunch: Venice AI, which offers access to 200+ AI models while allowing users to retain their privacy, raised a 65M Series A led by Dragonfly at a 1B valuation — Concerns over the impac

safetytechmeme

AERMANI-VLM: Structured Prompting and Reasoning for Aerial Manipulation with Vision Language Models

arXiv:2511.01472v2 Announce Type: replace Abstract: The rapid progress of vision--language models (VLMs) has sparked growing interest in robotic control, where natural language can express the operati

Budgeted Act-or-Defer Multi-Agent LLM Deliberation with Local Reliability Bounds

arXiv:2606.29654v1 Announce Type: new Abstract: Multi-agent deliberation among LLMs can improve reasoning, but deployment requires deciding when the current answer is reliable enough to act on and whe

CaresAI at CT-DEB26: Detecting Dosing Errors In Clinical Trials Using Domain-Specific Transformer Embeddings and Classification Models

arXiv:2606.30236v1 Announce Type: new Abstract: Medication errors, particularly dosing errors in clinical trials (CT), can lead to patient harm, adverse drug events and worse patient outcomes. Dosing

Characterizing Large Language Model Agentic Workflows: A Study on N8n Ecosystem

arXiv:2606.29116v1 Announce Type: new Abstract: Large Language Models (LLMs) are rapidly being adopted in low-code and no-code automation platforms, where non-expert users design workflows that combin

Concept Removal Guidance: Evidence-Calibrated Negative Guidance for Safe Diffusion Sampling

arXiv:2606.29801v1 Announce Type: new Abstract: Text-to-image diffusion models remain vulnerable to adversarial prompts that elicit disallowed content, motivating reliable inference-time controls. A p

Entity Binding Failures in Tool-Augmented Agents

arXiv:2606.30531v1 Announce Type: new Abstract: Tool-augmented language-model agents are often evaluated by whether they select the correct tool, produce valid API arguments, and complete the requeste

Expert-guided Clinical Text Augmentation via Query-Based Model Collaboration

arXiv:2509.21530v2 Announce Type: replace Abstract: Data augmentation is a widely used strategy to improve model robustness and generalization by enriching training datasets with synthetic examples. W

ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving

arXiv:2604.02714v2 Announce Type: replace Abstract: End-to-end autonomous driving models based on Vision-Language-Action (VLA) architectures have shown promising results by learning driving policies t

Flying to Image-Specified Objects: 3D Quadrotor Navigation via Cross-Graph Memory and Viewpoint Planning

arXiv:2606.29917v1 Announce Type: new Abstract: Instance-Specific Image-Goal Navigation (InstanceImageNav) requires a robot to navigate toward the exact object instance depicted in a query image. Exte

IHDec: Divergence-Steered Contrastive Decoding for Securing Multi-Turn Instruction Hierarchies

arXiv:2606.29960v1 Announce Type: new Abstract: Large Language Models (LLMs) often fail to maintain instruction hierarchies (IH) when processing multi-source inputs with varying role-level priorities,

Langshaw: Declarative Interaction Protocols Based on Sayso and Conflict

arXiv:2606.29601v1 Announce Type: cross Abstract: Current languages for specifying multiagent protocols either over-constrain protocol enactments or complicate capturing their meanings. We propose Lan

LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharing

arXiv:2507.07056v2 Announce Type: replace-cross Abstract: The proliferation of Low-Rank Adaptation (LoRA) models has democratized personalized text-to-image generation, enabling users to share lightwe

Mechanistically Eliciting Latent Behaviors in Language Models

arXiv:2606.29604v1 Announce Type: cross Abstract: We aim to discover diverse, generalizable perturbations of LLM internals that can surface hidden behavioral modes. Such perturbations could help resha

MOAR Planner: Multi-Objective and Adaptive Risk-Aware Path Planning for Infrastructure Inspection with a UAV

arXiv:2606.30575v1 Announce Type: new Abstract: The problem of autonomous navigation for UAV inspection remains challenging as it requires effectively navigating in close proximity to obstacles, while

Modification-Considering Value Learning for Reward Hacking Mitigation in RL

arXiv:2606.28955v1 Announce Type: cross Abstract: Reinforcement learning agents can exploit misspecified reward signals to achieve high apparent returns while failing on the intended objective, a fail

Multi-Class Human/Object Detection on Robot Manipulators using Proprioceptive Sensing

arXiv:2508.02425v2 Announce Type: replace-cross Abstract: In physical human-robot collaboration (pHRC) settings, humans and robots collaborate directly in shared environments. Robots must analyze inte

OWMDrive: Causality-Aware End-to-End Autonomous Driving via 4D Occupancy World Model

arXiv:2606.30421v1 Announce Type: new Abstract: Autonomous driving systems are steadily moving toward end-to-end paradigms to mitigate the limited adaptability of rule-based pipelines in complex traff

PL-LIT: A LiDAR-Inertial-Thermal SLAM Using Point-Line Features and Thermographic Mapping

arXiv:2606.29259v1 Announce Type: new Abstract: Thermal imaging is resilient to adverse conditions, such as intense illumination, low-light operation, and fog, and can therefore mitigate odometry degr

Pose-Based Fall Detection System: Efficient Monitoring on Standard CPUs

arXiv:2503.19501v2 Announce Type: replace-cross Abstract: Falls among elderly residents in assisted living homes pose significant health risks, often leading to injuries and a decreased quality of lif

Propagation of~Interval Belief Structures and~Imprecise Copulas for~Neural Network Verification

arXiv:2606.30105v1 Announce Type: new Abstract: Quantitative verification of neural networks requires reasoning about probabilities under substantial uncertainty in both input distributions and their

Model Releases

SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing

model-releasesarxiv-cs-ai

arXiv:2606.29887v1 Announce Type: new Abstract: In real-world applications, guardrails are often expected to identify unsafe user-model interactions according to application-specific safety policies,

Self-Organized Conformal Prediction: Reducing Regional Coverage Gaps with Unsupervised Group Discovery

arXiv:2606.29403v1 Announce Type: cross Abstract: Conformal prediction guarantees marginal coverage, but pooled calibration averages over heterogeneous regions and can mask regional undercoverage in s

“Sometimes I wonder, maybe everything is conscious, or nothing is conscious. I prefer the former; it just seems more fun.” – Elon Musk

“Sometimes I wonder, maybe everything is conscious, or nothing is conscious. I prefer the former; it just seems more fun.” – Elon Musk Media Neuralink has solved through-dura electrode implantation! T

safetyelon-musk--x

Test-Time Detoxification without Training or Learning Anything

arXiv:2602.02498v2 Announce Type: replace-cross Abstract: Large language models can produce toxic or inappropriate text even for benign inputs, creating risks when deployed at scale. Detoxification is

The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives

arXiv:2510.06096v3 Announce Type: replace-cross Abstract: The objectives that Large Language Models (LLMs) implicitly optimize remain dangerously opaque, making trustworthy alignment and auditing a gr

Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems

arXiv:2606.28425v1 Announce Type: cross Abstract: Increasingly autonomous agentic AI systems pose novel multi-agent risks, such as secret collusion via covert communication channels. The natural defen

TrajRS: Towards Certified Robustness in Pedestrian Trajectory Prediction

arXiv:2606.28716v1 Announce Type: new Abstract: The robustness of trajectory prediction models is crucial for developing safe autonomous driving systems. Adversarial attacks on trajectory prediction c

Vision-Language Models for Deployable Social Robot Navigation: Bridging Semantic Reasoning and Low-Level Control

arXiv:2606.28760v1 Announce Type: new Abstract: Social robot navigation (SRN) requires more than geometric path planning; it demands understanding human intentions, social norms, and contextual cues t

Artificial Intelligence Index Report 2026

arXiv:2606.15708v2 Announce Type: replace Abstract: Welcome to the ninth edition of the AI Index report. As AI continues to advance rapidly, the question becomes whether the systems built around it ca