Meituan/Dianping’s edge‑AI re‑ranking system moves large‑scale deep‑learning models onto users’ devices, using dense networks and cloud‑served embeddings, advanced feedback‑sequence and multi‑view attention models, and aggressive compression to deliver real‑time, privacy‑preserving search personalization that boosts click‑through rates by up to 0.43 %.
This article explains how to convert a TensorFlow image‑classification model to TensorFlow Lite, apply different quantization techniques, benchmark the resulting models on a Raspberry Pi 4, and compare latency, size, and accuracy to demonstrate the trade‑offs of edge AI deployment.
With the rapid rise of edge computing, deploying AI models for tasks like object detection, OCR, and speech recognition on resource‑constrained devices faces speed challenges; the upgraded Paddle Lite inference engine and PaddleSlim compression tools claim up to 23% faster inference and significant model size reductions, offering a practical solution.
This article explains how Alibaba’s local‑life platforms leverage edge‑side AI to run machine‑learning inference on users’ devices, detailing the concept, advantages, technical architecture, and concrete implementations such as user feature extraction, intelligent recommendation, and smart push, while outlining future directions.
The article outlines how MNN Workbench, Alibaba’s open‑source edge‑AI platform, integrates professional training capabilities, cloud‑based PAI‑DLC resources, multi‑window debugging, and visual Git Flow to streamline end‑to‑end model development, deployment, and iteration for developers of varying expertise.
This talk explains how Ant Group’s frontend engineers built edge‑AI services that run directly in browsers, boosting real‑time performance, preserving privacy, and cutting cloud costs, while showcasing two real‑world cases—pet identification and screen‑break insurance—and detailing the WebGL‑based engine optimizations that lifted device coverage from 30% to 93%.
Ant’s self‑developed xNN‑OCR demonstrates how advanced OCR can run offline on smartphones by combining GAN‑based data synthesis, lightweight ShuffleNet‑inspired detection, NAS‑optimized recognition, and aggressive model compression, delivering near‑real‑time accuracy for diverse mobile scenarios while preserving privacy and low cost.
This article explains how AI is extending into front‑end development, defines edge AI, outlines its application scenarios, discusses advantages and limitations, reviews web‑based inference frameworks and hardware acceleration, and details model compression techniques for deploying AI directly in browsers.
This article explains how a high‑traffic map service captures road features using client‑side computer‑vision models, details the deployment of many CNNs with the lightweight MNN engine on memory‑constrained devices, and shares practical memory‑saving techniques, inference scheduling, and error‑analysis methods.
This article explains the rise of edge computing, outlines its layered architecture, examines industry trends, describes cloud‑native fundamentals, and details how the OpenYurt platform solves integration challenges with features like unitization, edge autonomy, seamless conversion, and cloud‑edge collaboration, illustrated by edge‑AI and video‑to‑cloud case studies.
The 2021 report analyzes the scope of AI chips, examines global and Chinese market dynamics, profiles typical AI chip manufacturers, and provides concise overviews of cloud and edge AI chip segments while highlighting current challenges and future trends shaping the industry.
The article reviews deep‑model compression methods—ADMM‑based structured pruning, low‑bit quantization, and teacher‑student knowledge distillation—and their automated AutoCompress workflow, demonstrating how these techniques shrink neural networks enough to run real‑time driver‑monitoring and other intelligent cockpit functions on resource‑limited automotive hardware while preserving accuracy.
This article explains the background of on‑device AI, introduces the Mobile Machine Learning (MML) framework and its layered architecture, details the core utilities such as model decryption and task scheduling, and provides a step‑by‑step code guide for initializing, preprocessing, inference, post‑processing, and releasing resources on mobile platforms.
Paddle.js is Baidu’s lightweight JavaScript inference engine that transforms Paddle models into web‑compatible formats, enabling fast, privacy‑preserving AI features such as face detection, gesture recognition and content filtering directly in browsers via WebGL/WebAssembly, with only 201 KB code and broad compatibility.
Tencent Cloud’s AIoT solution combines edge AI processing with a cloud‑edge collaboration framework, using container‑orchestrated microservices, AI chips and IoT connectivity to cut latency to milliseconds, lower bandwidth by sending only structured data, and enable real‑time applications such as smart retail, manufacturing, agriculture and building security.
Alibaba’s open‑source MNN is a lightweight, high‑performance deep‑learning inference engine optimized for edge devices, supporting multiple model formats and backends, offering portability across iOS, Android, and IoT, with detailed architecture, performance benchmarks, roadmap, and real‑world application examples.
This article explains how the lightweight xNN-OCR engine achieves high accuracy and real‑time performance on mobile devices through deep‑learning model compression, novel detection and recognition techniques, and showcases its practical applications such as bank‑card, gas‑meter, license‑plate, and ID recognition.
The article analyzes the growing bottlenecks in compute architecture and memory, explores high‑bandwidth communication, near‑data processing, and in‑memory computing techniques, evaluates their advantages, challenges, and future prospects, and highlights key industry players driving the shift toward integrated compute‑storage chips.
The talk outlines Taobao Live’s rapid growth and three‑layer interactive architecture—dynamic AI‑driven marketing tools, human‑computer interaction features such as facial and gesture recognition, and intelligent operations that score fan intimacy—to deliver low‑latency, AI‑enhanced streaming with innovations like virtual backgrounds, product recognition, and an automated live‑assistant.
In an exclusive interview, Alibaba AI Lab's distinguished scientist Dr. Wang Gang discusses the lab's research on multimodal AI, edge computing, AI hardware, bio‑inspired cognition, quantum‑deep‑learning integration, and the challenges of moving from recognition to true understanding, while also outlining Alibaba's AI talent recruitment plans.