AI News
4922 articles in this category (Page 106 of 206)
Building a Production-Grade Agentic AI System with Hybrid Retrieval and Episodic Memory
A tutorial on building an ultra-advanced agentic AI workflow with hybrid retrieval, provenance-first citations, repair loops, and episodic memory, achieving a 99% success rate in retrieving relevant information.
New Data Tool Helps Orgs Prioritize Exploited Flaws Smarter
KEV Collider combines data from multiple open source vulnerability frameworks to help cybersecurity teams assess which issues need their attention first, with over 48,100 vulnerabilities reported in 2025.
Malicious NGINX Configurations Enable Large-Scale Web Traffic Hijacking Campaign
React2Shell exploitation uses malicious NGINX configurations to hijack web traffic, targeting 1,083 unique source IP addresses and affecting Asian TLDs, government domains, and Baota panels.
Elevating Voices in AI: Microsoft Research Launches Paza & PazaBench
Microsoft Research unveils Paza, a human-centered speech pipeline, and PazaBench, the first leaderboard for low-resource languages, covering 39 African languages and 52 models.
Rethinking Imitation Learning with Predictive Inverse Dynamics Models
Predictive Inverse Dynamics Models often outperform standard Behavior Cloning in imitation learning, achieving comparable performance with as few as one-fifth the demonstrations required by BC.
Cyber Threats Evolve with Increased Operational Efficiency
Threat actors are leveraging automation, prebuilt frameworks, and reusable infrastructure to cut time between access and impact, with over 10,000 infected IP addresses globally tied to the SystemBC malware operation.