127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

safety

19,755 results

Safety

ARdena: Scenario-driven control of real-time LLM agents

DGX agent

arXiv:2607.22651v1 Announce Type: new Abstract: Large language models (LLMs) have enabled increasingly capable conversational agents, but reliably controlling their behavior in real-time interactive e

safetyarxiv-cs-ai

28 Jul 2026

Safety

Are Flat Minima an Illusion?

DGX agent

arXiv:2605.05209v2 Announce Type: replace-cross Abstract: Flat minima are an account of why deep networks generalise. However flatness is a matter of form (parameters), while generalisation is of func

safety

ARdena: Scenario-driven control of real-time LLM agents

Are Flat Minima an Illusion?

Asymmetric Hierarchical Anchoring for Robust Audio-Visual Cross-Modal Generalization

Attribution and Uncertainty Behavior of Learned Residual Gyro Correction for Gyro-Stellar Estimation

Beyond a Global Norm: Personalizing Toxicity Sensitivity in Language Models Without Retraining

Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks

Breaking the Synthetic-Real Domain Shortcut for Training-Free Generative Replay-based Class Incremental Learning

Concept-based Visual Counterfactual Explanations with Diffusion Models

Concurrent Prehensile and Nonprehensile Manipulation: A Practical Approach to Multi-Stage Dexterous Tasks

ConFusion: Continuous Fusion Space Learning for Fine-Grained Controllable Infrared and Visible Image Fusion

Constrained Reinforcement Learning Using Successor Representations

Continual-RL for Generalization in Autonomous Racing on the RoboRacer Platform

CoopReflect: Towards Natural Language Communication for Cooperative Autonomous Driving via Multi-Agent Learning

Covariance-Boosted Gaussian Processes for Spatiotemporal Irregularities

CRAFT: Learn the Schema, Execute the Plan

D3O: Dynamic Distribution Distillation for Ordinal Regression

Data Pyramid for Embodied Manipulation

Dementia Etiology Diagnosis via Collaborative Meta Knowledge Enhancement

Dependency-Guided Code Generation: Structured Matrix Decomposition and Consistency-Guided Refinement

Designing Service Systems from Textual Evidence

DeVA: Decoupled Video-Action Model with physical guidance for robot policy learning

DICA: Dual-Indicator Guided Contrastive Alignment in Multimodal Large Language Models

Directional Influence Function: Estimating Training Data Influence in Constrained Learning

Disentangling Acoustic Cues in Alzheimer's Pathology and Perception: The Roles of Language and Gender

Disentangling Semantic Attention from Structural Bias in the Attention Manifold

Do LLM Debates Repeat Arguments Differently Across Languages?

Does Faithfulness-Guided Alignment Hurt Accuracy? Unlocking Accurate and Faithful Post-Retrieval Reasoning

EchoBridge: Long-Tail-Aware ECG-Echocardiography Text Alignment for Echocardiography-Derived Cardiac Findings

Efficiency Matters in Autonomous Research

Epistemic Norms for AI Safety and Alignment Research

Eviction as Estimation: A Fixed-Lag Smoothing View of Test-Time Memory, and When Measuring Beats Accumulating

Execution-Grounded Security Testing for Coding Agents in Software Engineering Pipelines

Face Age Verification Vulnerabilities Under Simple Appearance Manipulations

Finite-Time Analysis of the Natural Policy Gradient in Finite-Horizon Markov Decision Processes

FlowCTS: On-policy Continuous Trajectory Supervision of Flow Models

Forecasting the Emergence and Evolution of Crash Hotspots: A Unified Deep Learning Framework for Proactive Traffic Safety

From Camera-Based Sensing to Reasoning: A Comprehensive Review Toward Proactive Vulnerable Road User Safety

From 'Help' to Helpful: A Hierarchical Assessment of LLMs in Mental e-Health Applications

From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search

Frustratingly Simple Black-Box Adaptation of Language Models via Logit Bias

FutureRTC: Real-Time Robot Execution with Anticipatory-Conditioned Action Chunking

Generalization bounds and sample complexity for remaining useful life prediction from complete degradation trajectories

HALLELUAI: A Hallucination-Aware AI System for Ultra-Realistic Image-to-Video Generation at Scale

HeraSys: Collaborative Serving of Multiple LLM Workflows via Fine-Grained End-to-End Optimization

Hierarchical Soft Actor-Critic for Sparse-Reward Long-Horizon Reinforcement Learning

How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift

Hybrid AI-Physical Modeling for Penetration Bias Correction in X-band InSAR DEMs: A Greenland Case Study

IJCB-AFMFR 2026: Competition on Adapting Foundation Models for Face Recognition Using Synthetic Training Data