InfoQ Homepage Machine Learning Content on InfoQ
-
/articles/local-first-ai-inference-cloud/en/smallimage/Local-First-AI-Inference-A-Cloud-Architecture-Pattern-for-Cost-Effective-Document-Processing-thumb-image-1778141518292.jpg)
Local-First AI Inference: A Cloud Architecture Pattern for Cost-Effective Document Processing
The Local-First AI Inference pattern routes 70–80% of documents to deterministic local extraction at zero API cost, reserving Azure OpenAI calls for edge cases and flagging low-confidence results for human review. Deployed on 4,700 engineering drawing PDFs, it cut API costs by 75% and processing time by 55%, while bounding errors through a human review tier.
-
/articles/optimization-in-automated-driving/en/smallimage/optimization-in-automated-driving-thumbnail-1774348229685.jpg)
Optimization in Automated Driving: from Complexity to Real-Time Engineering
In this article, author Avraam Tolmidis discusses technical architecture of autonomous vehicles, with focus on optimization techniques like context-aware sensor fusion and Model Predictive Control (MPC) solvers to help with processing raw sensor data into safe control commands.
-
/articles/architecting-agentic-mlops-a2a-mcp/en/smallimage/architecting-agentic-mlops-a2a-mcp-1770303550343.jpg)
Architecting Agentic MLOps: a Layered Protocol Strategy with A2A and MCP
In this article, the authors outline protocols for building extensible multi-agent MLOps systems. The core architecture deliberately decouples orchestration from execution, allowing teams to incrementally add capabilities via discovery and evolve operations from static pipelines toward intelligent, adaptive coordination.
-
/articles/why-ml-projects-fail-production/en/smallimage/why-ml-projects-fail-production-thumbnail-1769072877092.jpg)
Why Most Machine Learning Projects Fail to Reach Production
In this article, the author diagnoses common failures in ML initiatives, including weak problem framing and the persistent prototype-to-production gap. The piece provides practical, experience-based guidance on setting clear business goals, treating data as a product, and aligning cross-functional teams for reliable, production-ready ML delivery.
-
/articles/agent-reinforcement-learning-apache-spark/en/smallimage/thumbnail-1769431334097.jpg)
Autonomous Big Data Optimization: Multi-Agent Reinforcement Learning to Achieve Self-Tuning Apache Spark
This article introduces a reinforcement learning (RL) approach grounded in Apache Spark that enables distributed computing systems to learn optimal configurations autonomously, much like an apprentice engineer who learns by doing. The author also implements a lightweight agent as a driver-side component that uses RL to choose configuration settings before a job runs.
-
/articles/ai-assisted-development-series/en/smallimage/ai-assisted-development-thumb-image-1768388299998.jpg)
Article Series: AI-Assisted Development: Real World Patterns, Pitfalls, and Production Readiness
In this series, we examine what happens after the proof of concept and how AI becomes part of the software delivery pipeline. As AI transitions from proof of concept to production, teams are discovering that the challenge extends beyond model performance to include architecture, process, and accountability. This transition is redefining what constitutes good software engineering.
-
/articles/training-data-preprocessing-for-text-to-video-models/en/smallimage/training-data-preprocessing-for-text-to-video-models-thumbnail-1762244675850.jpg)
Training Data Preprocessing for Text-to-Video Models
In this article, author Aleksandr Rezanov discusses the data preparation for generative text-to-image models to accelerate work on video generation services to be used in TV series and films. He explains how data is prepared and can serve as a starting point for creating custom datasets to develop proprietary models.
-
/articles/ai-ml-data-engineering-trends-2025/en/smallimage/the-infoq-trends-report-500x500-logo-1758095546194.jpeg)
InfoQ AI, ML and Data Engineering Trends Report - 2025
This InfoQ Trends Report offers readers a comprehensive overview of emerging trends and technologies in the areas of AI, ML, and Data Engineering. This report summarizes the InfoQ editorial team’s and external guests' view on the current trends in AI and ML technologies and what to look out for in the next 12 months.
-
/articles/causal-reasoning-observability/en/smallimage/causal-reasoning-observability-thumbnail-1756372623637.jpg)
How Causal Reasoning Addresses the Limitations of LLMs in Observability
Large language models excel at converting observability telemetry into clear summaries but struggle with accurate root cause analysis in distributed systems. LLMs often hallucinate explanations and confuse symptoms with causes. This article suggests how causal reasoning models with Bayesian inference offer more reliable incident diagnosis.
-
/articles/mcp-connector-for-building-smarter-modular-ai-agents/en/smallimage/mcp-connector-for-building-smarter-modular-ai-agents-thumbnail-1756277862571.jpg)
MCP: the Universal Connector for Building Smarter, Modular AI Agents
In this article, the authors discuss Model Context Protocol (MCP), an open standard designed to connect AI agents with tools and data they need. They also talk about how MCP empowers agent development, and its adoption in leading open-source frameworks.
-
/articles/ai-infrastructure-aggregating-agentic-traffic/en/smallimage/ai-infrastructure-aggregating-agentic-traffic-thumbnail-1755682463373.jpg)
The Missing Layer in AI Infrastructure: Aggregating Agentic Traffic
In this article, author Eyal Solomon discusses AI Gateways, the outbound proxy servers that intercept and manage AI-agent-initiated traffic in real time to enforce policies and provide central management.
-
/articles/personalized-content-pagination-prefetching/en/smallimage/personalized-content-pagination-prefetching-thumbnail-1748248589509.jpg)
Faster, Smoother, More Engaging: Personalized Content Pagination
Dynamic content loading powered by AI transforms user experiences by personalizing delivery based on user's behavior and network conditions. By analyzing scroll depth, speed, and dwell time, we optimize loading times, enhance engagement, and reduce infrastructure costs, especially on devices with poor internet connectivity.