edge ai
30 articles about edge ai in AI news
Edge AI Breakthrough: Qwen3.5 2B Runs Locally on iPhone 17 Pro, Redefining On-Device Intelligence
Alibaba's Qwen3.5 2B model now runs locally on iPhone 17 Pro devices, marking a significant breakthrough in edge AI. This development enables sophisticated language processing without cloud dependency, potentially transforming mobile AI applications and user privacy paradigms.
Edge AI for Loss Prevention: Adaptive Pose-Based Detection for Luxury Retail Security
A new periodic adaptation framework enables edge devices to autonomously detect shoplifting behaviors from pose data, offering a scalable, privacy-preserving solution for luxury retail security with 91.6% outperformance over static models.
Google's Nano-Banana 2: The Edge AI Revolution That Puts 4K Image Generation in Your Pocket
Google has officially unveiled Nano-Banana 2, a specialized AI model delivering sub-second 4K image synthesis with advanced subject consistency entirely on-device. This breakthrough represents a strategic pivot toward edge computing, challenging the cloud-centric paradigm of current generative AI.
Google's TensorFlow 2.21 Revolutionizes Edge AI with Unified LiteRT Framework
Google has launched TensorFlow 2.21, marking LiteRT's transition to a production-ready universal on-device inference framework. This major update delivers faster GPU performance, new NPU acceleration, and seamless PyTorch edge deployment, effectively replacing TensorFlow Lite for mobile and edge applications.
GitNexus Open Sources Codebase Knowledge Graph Engine for AI Agents
GitNexus, an open-source knowledge graph engine, autonomously indexes codebases to map dependencies and execution flows. It integrates with Claude Code, Cursor, and Windsurf via MCP to give AI agents architectural awareness, preventing breaking changes.
Zero-Shot Cross-Domain Knowledge Distillation: A YouTube-to-Music Case Study
Google researchers detail a case study transferring knowledge from YouTube's massive video recommender to a smaller music app, using zero-shot cross-domain distillation to boost ranking models without training a dedicated teacher. This offers a practical blueprint for improving low-traffic AI systems.
New Research Proposes FilterRAG and ML-FilterRAG to Defend Against Knowledge Poisoning Attacks in RAG Systems
Researchers propose two novel defense methods, FilterRAG and ML-FilterRAG, to mitigate 'PoisonedRAG' attacks where adversaries inject malicious texts into a knowledge source to manipulate an LLM's output. The defenses identify and filter adversarial content, maintaining performance close to clean RAG systems.
Microsoft's Satya Nadella Details Internal 'Lean for Knowledge Work' AI Initiative
Microsoft CEO Satya Nadella described the company's internal application of AI to streamline knowledge work, framing it as a 'Lean' manufacturing-style efficiency push for cognitive tasks. The initiative focuses on using AI to reduce process friction and improve productivity across internal operations.
Edge Computing in Retail 2026: Examples, Benefits, and a Guide
Shopify outlines the strategic shift toward edge computing in retail, detailing its benefits—real-time personalization, inventory management, and enhanced in-store experiences—and providing a practical implementation guide for 2026.
Future-Proof Your AI Search: Why Static Knowledge Bases Fail Luxury Retail
New research reveals AI retrieval benchmarks degrade over time as information changes. For luxury brands using AI for product recommendations and clienteling, this means static knowledge bases become stale, hurting customer experience and sales.
Anthropic's Stealth Education Revolution: Free AI Curriculum Democratizes Technical Knowledge
Anthropic has launched a comprehensive, completely free AI curriculum designed to make technical AI education accessible to everyone. The curriculum covers fundamentals to advanced topics without tuition, waitlists, or prerequisites, potentially reshaping how AI knowledge is distributed.
Multimodal Knowledge Graphs Unlock Next-Generation AI Training Data
Researchers have developed MMKG-RDS, a novel framework that synthesizes high-quality reasoning training data by mining multimodal knowledge graphs. The system addresses critical limitations in existing data synthesis methods and improves model reasoning accuracy by 9.2% with minimal training samples.
NullClaw: The 1MB AI Agent Revolutionizing Edge Computing
NullClaw, a fully autonomous AI agent written in Zig, runs on just 1MB RAM and 678KB binary size, enabling AI deployment on $5 hardware with <2ms startup times. This breakthrough eliminates traditional runtime bloat and opens new possibilities for edge computing.
Google's AI Edge Gallery Arrives on iPhone: A Privacy-First Revolution in On-Device Intelligence
Google AI Edge Gallery has launched on iOS, bringing true on-device function calling to iPhones for the first time. Powered by the compact 270M parameter FunctionGemma model, it enables natural voice commands to trigger phone actions like calendar events and flashlight toggles—completely offline.
Trump's AI Energy Summit: Tech Giants Pledge to Self-Generate Power Amid Grid Concerns
Former President Donald Trump is convening Amazon, Google, Meta, Microsoft, xAI, Oracle, and OpenAI at the White House to sign a 'Rate Payer Protection Pledge,' committing them to generate or purchase their own electricity for new AI data centers, signaling a major shift in how tech's energy demands are addressed.
GitNexus Revolutionizes Code Exploration: Browser-Based AI Transforms GitHub Repositories into Interactive Knowledge Graphs
A new tool called GitNexus transforms any GitHub repository into an interactive knowledge graph with AI chat capabilities, running entirely in the browser without backend infrastructure. This breakthrough enables developers to visualize and query complex codebases through intuitive graph interfaces and natural language conversations.
How Anthropic's Team Uses Skills as Knowledge Containers (And What It Means For Your CLAUDE.md)
Learn how to use Claude Code skills not just for automation but as living knowledge bases, following patterns from Anthropic's own engineering team.
ReXInTheWild Benchmark Reveals VLMs Struggle with Medical Photos: Gemini-3 Leads at 78%, MedGemma Trails at 37%
Researchers introduced ReXInTheWild, a benchmark of 955 clinician-verified questions based on 484 real medical photographs. Leading multimodal models show wide performance gaps, with Gemini-3 scoring 78% accuracy while the specialized MedGemma model achieved only 37%.
EpisTwin: A Neuro-Symbolic Framework for Personal AI Using Knowledge Graphs
Researchers propose EpisTwin, a neuro-symbolic architecture that builds a Personal Knowledge Graph from fragmented user data to enable complex, verifiable reasoning. It addresses limitations of standard RAG by capturing semantic topology and temporal dependencies.
Andrej Karpathy's Personal Knowledge Management System Uses LLM Embeddings Without RAG for 400K-Word Research Base
AI researcher Andrej Karpathy has developed a personal knowledge management system that processes 400,000 words of research notes using LLM embeddings rather than traditional RAG architecture. The system enables semantic search, summarization, and content generation directly from his Obsidian vault.
Federated RAG: A New Architecture for Secure, Multi-Silo Knowledge Retrieval
Researchers propose a secure Federated Retrieval-Augmented Generation (RAG) system using Flower and confidential compute. It enables LLMs to query knowledge across private data silos without centralizing sensitive documents, addressing a major barrier for enterprise AI.
Claude Code Plugin 'Understand' Generates Interactive Knowledge Graphs from Codebases
A new Claude Code plugin called 'Understand' automatically analyzes any codebase to create an interactive knowledge graph. It enables developers to query code in plain English, visualize dependencies, and generate onboarding guides.
New Research Diagnoses LLMs' Struggle with Multiple Knowledge Updates in Context
A new arXiv paper reveals a persistent bias in LLMs when facts are updated multiple times within a long context. Models increasingly favor the earliest version, failing to track the latest state—a critical flaw for dynamic knowledge tasks.
Understanding the Interplay between LLMs' Utilisation of Parametric and Contextual Knowledge: A keynote at ECIR 2025
A keynote at ECIR 2025 will present research on how Large Language Models (LLMs) balance their internal, parametric knowledge with external, contextual information. This is critical for deploying reliable AI in knowledge-intensive tasks where models must correctly use provided context, not just their training data.
Knowledge-RAG v3.0: The Local RAG MCP Server That Finally Just Works
Knowledge-RAG v3.0 eliminates Docker/Ollama setup, adds hybrid search with cross-encoder reranking, and auto-indexes your docs—making private RAG in Claude Code a one-command install.
Feynman: A Knowledge-Infused Diagramming Agent That Enhances Vision-Language Model Performance on Diagrams
Researchers introduced Feynman, an agent that uses external knowledge to improve vision-language models' understanding of diagrams. It outperforms GPT-4V and Gemini on diagram QA tasks.
Reinforcement Learning Ushers in New Era of Autonomous Knowledge Agents
Researchers are developing knowledge agents powered by reinforcement learning that can autonomously gather, process, and apply information. These systems represent a significant evolution beyond traditional language models toward more independent problem-solving capabilities.
VMLOPS's 'Basics' Repository Hits 98k Stars as AI Engineers Seek Foundational Systems Knowledge
A viral GitHub repository aggregating foundational resources for distributed systems, latency, and security has reached 98,000 stars. It addresses a widespread gap in formal AI and ML engineering education, where critical production skills are often learned reactively during outages.
LLMs Show 'Privileged Access' to Own Policies in Introspect-Bench, Explaining Self-Knowledge via Attention Diffusion
Researchers formalize LLM introspection as computation over model parameters, showing frontier models outperform peers at predicting their own behavior. The study provides causal evidence for how introspection emerges via attention diffusion without explicit training.
Qodo AI Code Review Tool Claims Major Edge Over Anthropic's Claude in Performance and Cost
A new AI-powered code review tool called Qodo reportedly outperforms Anthropic's Claude Code Review by 19% in recall accuracy while costing ten times less per review, potentially reshaping the landscape of automated development assistance.