127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “deployment”

12,448 results

Safety

LLM Biases

DGX agent

arXiv:2604.26960v1 Announce Type: cross Abstract: Transformer-based agentic AI is rapidly being deployed on major platforms to help users shop, watch, and navigate content with less effort. While thes

safetyarxiv-cs-ai

1 May 2026

Safety

Atomic-Probe Governance for Skill Updates in Compositional Robot Policies

DGX agent

arXiv:2604.26689v1 Announce Type: cross Abstract: Skill libraries in deployed robotic systems are continually updated through fine-tuning, fresh demonstrations, or domain adaptation, yet existing type

Search: “deployment”

LLM Biases

Atomic-Probe Governance for Skill Updates in Compositional Robot Policies

FASTER: Rethinking Real-Time Flow VLAs

Progressive Semantic Communication for Efficient Edge-Cloud Vision-Language Models

From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models

AI Safety Training Can be Clinically Harmful

CoFi-PGMA: Counterfactual Policy Gradients under Filtered Feedback for Multi-Agent LLMs

Layerwise Convergence Fingerprints for Runtime Misbehavior Detection in Large Language Models

Learning Selective LLM Autonomy from Copilot Feedback in Enterprise Customer Support Workflows

Mind the Gap: Evaluating Model- and Agentic-Level Vulnerabilities in LLMs with Action Graphs

One Size Fits None: Heuristic Collapse in LLM Investment Advice

Resource-Constrained UAV-Based Weed Detection for Site-Specific Management on Edge Devices

SycoPhantasy: Quantifying Sycophancy and Hallucination in Small Open Weight VLMs for Vision-Language Scoring of Fantasy Characters

AgentMark: Utility-Preserving Behavioral Watermarking for Agents

Estimating Tail Risks in Language Model Output Distributions

Adaptive Defense Orchestration for RAG: A Sentinel-Strategist Architecture against Multi-Vector Attacks

ImageHD: Energy-Efficient On-Device Continual Learning of Visual Representations via Hyperdimensional Computing

The Last Harness You'll Ever Build

Why Do Language Model Agents Whistleblow?

AVISE: Framework for Evaluating the Security of AI Systems

Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science Workflows

Hidden Reliability Risks in Large Language Models: Systematic Identification of Precision-Induced Output Disagreements

Stateless Decision Memory for Enterprise AI Agents

A Heterogeneous Long-Micro Scale Cascading Architecture for General Aviation Health Management

A Mechanism and Optimization Study on the Impact of Information Density on User-Generated Content Named Entity Recognition

Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language

Ensembling Pruned Attention Heads For Uncertainty-Aware Efficient Transformers

FASE : A Fairness-Aware Spatiotemporal Event Graph Framework for Predictive Policing

LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation

Multi-Cycle Spatio-Temporal Adaptation in Human-Robot Teaming

AWPD: Frequency Shield Network for Agnostic Watermark Presence Detection

Bridging the Reasoning Gap in Vietnamese with Small Language Models via Test-Time Scaling

Calibrated? Not for Everyone: How Sexual Orientation and Religious Markers Distort LLM Accuracy and Confidence in Medical QA

Can we generate portable representations for clinical time series data using LLMs?

Clinical Note Bloat Reduction for Efficient LLM Use

Correction and Corruption: A Two-Rate View of Error Flow in LLM Protocols

DexWorldModel: Causal Latent World Modeling towards Automated Learning of Embodied Tasks

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling

PrinciplismQA: A Philosophy-Grounded Approach to Assessing LLM-Human Clinical Medical Ethics Alignment

RASP-Tuner: Retrieval-Augmented Soft Prompts for Context-Aware Black-Box Optimization in Non-Stationary Environments

SafeLM: Unified Privacy-Aware Optimization for Trustworthy Federated Large Language Models

SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning

AdaVFM: Adaptive Vision Foundation Models for Edge Intelligence via LLM-Guided Execution

Beyond Surface Statistics: Robust Conformal Prediction for LLMs via Internal Representations

Efficient Video Diffusion Models: Advancements and Challenges

In-Context Distillation with Self-Consistency Cascades: A Simple, Training-Free Way to Reduce LLM Agent Costs

Information-Consistent Language Model Recommendations through Group Relative Policy Optimization

Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs