AI Wiki — Knowledge Base

Secure On-Premise Deployment of Open-Weights Large Language Models in Radiology: An Isolation-First Architecture with Prospective Pilot Evaluation

arXiv:2604.22768v1 Announce Type: cross Abstract: Purpose: To design, implement, evaluate, and report on the regulatory requirements of a self-hosted LLM infrastructure for radiology adhering to the p

model-releasesarxiv-cs-cl

28 Apr 2026

Search: “self-host”

Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?

From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix

HiMe: Real-Time Self-Hosted Personal Agent Platform for Health Insights with Wearable Devices

Same Pieces, Different Servers: A Tetris Benchmark for AI Agents as Served

Lessons learned from deploying imaging AI with the open PACS-AI platform

LogRouter: Adaptive Two-Level LLM Routing for Log Question Answering in Big Data Systems

Secure On-Premise Deployment of Open-Weights Large Language Models in Radiology: An Isolation-First Architecture with Prospective Pilot Evaluation

SQL Query Engine: A Self-Healing LLM Pipeline for Natural Language to PostgreSQL Translation

The Commercial Tax: Rent-vs-Own Blind Spots in Multi-Hop Retrieval Benchmarks

Locate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QA

Constructing Challenging Browser-Use Tasks by Controlled Environment Interventions

Auditing and Repairing LLM-as-Judge Failures in a Production Text-to-SQL Pipeline

DeepEdu-v1: Efficient and Scalable Agentic LLMs for Vietnamese Education

Muslim: A Deployed Arabic Voice AI Platform for Grounded Islamic Knowledge

Combating Instruction Conflict via Energy-Driven Latent Conflict Detection

Djinnlang: Higher-Level Programming by Unambiguous Specification with an LLM in the Compiler

From Monolithic Blending to Agentic Orchestration: Dynamic Response for Conversational Assistants at Scale

A Measurement Study of LLM Inference Trade-offs Across Edge Continuum Hardware

Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box LLM Observers on Shared Endpoints

Closing Cost-Quality Gap in Document VLMs: Difficulty-Aware Data Curation and Quality-Adjusted Deployment Economics

Zero-Shot Self-Orchestration with Ledger-Based Control for Improved LLM Coding Performance

Retrieve, Match, Escalate: Accurate and Scalable Product Linking with VLM-Distilled Cross-Encoders and Agentic VLMs

Paritok-4B: Intent-Conditioned Context Compression for Coding Agents

OGX: An Open-Source, Vendor-Neutral Generative AI Application Server

Dialogue-Aware Video-to-Music Generation Using Public Domain Film Collections

A Cost-Efficient Routing Pipeline for Multilingual Short-Text Classification Using Small Language Models

Harnessing the Wisdom of LLM Crowds through Complementarity-Driven Iterative Collaboration

AIriskEval-edu Demo: Auditing of Pedagogical Risks in Educational Explanations

FMRP-LEAN: A HIPAA-Compliant AI-Augmented LIMS Architecture for End-to-End Clinical Assay Workflow Optimization

Differentiate the Evaluator, Not the Program: An Efficient Runtime Representation for Neuro-Symbolic Learning

Evaluating Intellectual Property Guardrails of Generative Image Models: A Technical Report

GRACE-RAG: Governed Retrieval Architecture for Canonical Evidence Synthesis, Enabling Lightweight Deployment in Closed-Domain Institutional Settings

ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents

Field Order Should Not Matter: Permutation-Invariant Embedding Model Fine-Tuning for Structured Metadata Retrieval

Adaptive Evaluation of Out-of-Band Defenses Against Prompt Injection in LLM Agents

Can Large Language Models Reliably Code Qualitative Humanitarian Data? A Benchmark Study Against Human Expert Adjudication

Specialize Roles, Mix Deployments: Pushing the Cost-Accuracy Frontier of LLM Agent Teams

Compile Once, Differentiate Everywhere: A Differentiable Meta-Circular Interpreter

Syll: Open-Source Personal Automation with Cross-Surface Execution

Cross-Generational Transfer of Adversarial Attacks Reveals Non-Monotonic Safety Alignment in LLMs

LLM-FACETS: A Privacy-Preserving Framework for Evaluating LLM Transparency and Accountability

ResearchLoop: An Evidence-Gated Control Plane for AI-Assisted Research

KadiAssistant: A conversational AI Agent for information retrieval in Kadi4Mat

ClawArena: Benchmarking AI Agents in Evolving Information Environments

Rethinking LLMOps for Fraud and AML: Building a Compliance-Grade LLM Serving Stack

AI to Learn 2.0: A Deliverable-Oriented Governance Framework and Maturity Rubric for Opaque AI in Learning-Intensive Domains