127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “safety”

22,398 results

Safety

Safe Exploration via Policy Priors

DGX agent

arXiv:2601.19612v4 Announce Type: replace-cross Abstract: Safe exploration is a key requirement for reinforcement learning (RL) agents to learn and adapt online, beyond controlled (e.g. simulated) env

safetyarxiv-cs-ai

14 Aug 2026

Safety

Semantic Steering for Controllable Generation: Tuning-Free Concept Erasure in Multimodal Diffusion Transformers

DGX agent

Search: “safety”

Safe Exploration via Policy Priors

Semantic Steering for Controllable Generation: Tuning-Free Concept Erasure in Multimodal Diffusion Transformers

Static analysis-guided agentic AI translation enables Rust as a full stack bioinformatics language

vToken: Token-Level Virtualization for Reclaimable KV Caches

AI Guardrail Survival under Single-Cycle Agentic Self-Summarization

Clustered Randomized Smoothing for Stochastic Prediction Functions

Confidence Calibration of Deep Learning Systems

Constructing Dynamic Master Logic Models as Knowledge Graphs for Complex System Diagnostics Using Retrieval-Augmented Large Language Models

Contextual Quality-Diversity Evolutionary Reinforcement Learning for HVAC Control in Tropical Commercial Buildings

Do Not Forget the Obvious - RISC: A Risk-Informed Slice-Coverage Protocol for Safe Autonomous Driving

Faithful, Sufficient and Understandable: Rethinking Graph Counterfactual Explanations via Discrete Diffusion Inversion

Forecasting Side Effects of Activation Steering

GRPO for Financial Advice Generation: Outperforming Commercial LLMs under CATE Evaluation

Is Per-Agent Policy Composition Safe? Rethinking Successor-Feature Transfer in Cooperative Multi-Agent Reinforcement Learning

Multi-Agent Embodied Autonomous Driving: From V2X Information Exchange to Shared World Models

On the Definition of Intelligence

TailBooster: A Dual-Layer Generative Framework for Extreme Value Augmentation with Operational Validity Enforcement

Topology-Aware Query Selection for Surgical Instrument Instance Segmentation

Unmasking Toxic Mimicry in Medical Offline Reinforcement Learning for ICU Sepsis Management via Counterfactual Clinical Audits

A Convolutional Layer Activation Dimensionality Reduction for Out-of-Distribution and Adversarial Attack Detection Methods

A Neural Network Based Teleoperation for Remote Controlled Vehicles

ConfTriage: A Calibration-Aware LLM Triage Framework for Pulmonary Nodule Malignancy with Selective Specialist Deferral

Data Attribution of Emergent Misalignment with Persona Features

Dreamer-SAC: Off-Policy Learning in Latent World Models for Sample-Efficient Autonomous Driving

Easy3D-Labels: Supervising Semantic Occupancy Estimation with 3D Pseudo-Labels for Automotive Perception

Expert-Guided g-computation with Large Language Models for Estimating Causal Effects on Timings: Applications to Hospital Quality Improvement

From Interpretability to Control: Insights from Six Years of the TrustNLP Workshop

LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations

REDAgentBench: Executable Red Teaming and Faithful Measurement of LLM Agent Systems

Similarity Gates Approve Reversals: A Validity Audit of Embedding-Cosine Thresholds in Agent Systems

Smart Enough to Go Extinct? An Evolutionary Challenge to the Value of General Intelligence and Its Ethical Implications for AGI

Toward a Theory of Value in AI Alignment

UPAIR: Diagnosing Reasoning States via Uncertainty-Progress Alignment for Selective Intervention

VIDS-Seg: Towards Reliable Uncertainty Quantification in Pediatric Cardiac Ultrasound Segmentation

A Unified Framework for Dynamic Reward Shaping in Reinforcement Learning

Adaptive Sequential Test Planning for Multi-Mechanism Reliability Qualification via Bayesian Monte Carlo Tree Search

Agentic Harnesses: LLM-Driven Verification Layers for Robot Autonomy

An Explainable GNN Framework for Component-Level Anomaly Diagnosis

Causal Falsification of Digital Twins

Context Is Not Authority: Structured Runtime Governance for Financial Market Agents

CyberAGENTS: Structured Autonomy for Agentic Gamified Learning in Cybersecurity

DH-VLM: Dual-Horizon Cooperative Latent Reasoning for Autonomous Driving

Dynamic Distribution-Aware Uncertainty Tracking in Vision-Language Representation Learning

KumbhDoot: A Scale-Ready, LLM-Bounded Architecture for Mass-Gathering Public-Service Assistants

LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing

Machine Learning and Data Analysis Using Posets: A Survey

Model-Based Systems Engineering Framework for SysML-Driven Design of Autonomous UAVs

Persuasive and Compliant Tendencies Predict Group Decision-Making in Humans and Language Models