Official platform of JD Retail Technology, delivering insightful R&D news and a deep look into the lives and work of technologists.
This article examines JD.com's migration of its massive traffic data processing from a dual Lambda architecture to an integrated lakehouse solution, detailing the challenges, innovative optimizations with Flink and Hudi, performance gains, cost reductions, and future directions for real‑time data handling.
This article details the evolution, architecture, performance optimizations, and open‑source progress of Taro on HarmonyOS, illustrating how a unified front‑end framework enables efficient multi‑platform development and delivers native‑level performance for complex applications.
At the 2025 AI Innovation & Entrepreneurship Conference in Hangzhou, JD.com’s chief scientists unveiled a billion‑parameter time‑series large model and end‑to‑end inventory algorithms that dramatically boost demand forecasting, dynamic allocation, and overall supply‑chain efficiency, illustrating how AI can transform global logistics networks.
This article presents a comprehensive approach that combines causal inference, large language models, and retrieval‑augmented generation to automate e‑commerce price recommendation, detailing the three‑step workflow, challenges across product categories, the RAG architecture, process‑reward‑guided tree search, reinforcement learning refinements, and experimental results showing significant accuracy and speed improvements.
This article showcases five JD Retail Technology research papers accepted at SIGIR 2025, covering graph‑based cohort modeling, causal optimal transport post‑event modeling, an autonomous domain‑oriented relevance engine, a multi‑objective bidword generation model, and hierarchical long‑term user behavior modeling, all advancing e‑commerce CTR prediction and advertising.
This article details JD Retail Technology’s AI‑driven virtual try‑on system that combines a 12B Flux‑Fill diffusion model with a high‑quality virtual model library and integrates with the JingMai A/B testing platform, cutting production costs to zero, slashing cycle time to half a day, and increasing order conversion rates by over 80% during the 618 shopping festival.
JD’s algorithm engineer describes how a three‑layer PODM‑MI re‑ranking framework, combining Gaussian preference modeling, mutual‑information optimization, and utility‑matrix fusion, overcame the hourglass bottleneck in generative retrieval, dramatically improving search diversity, user experience, and generating over ten million additional orders.
At the 2025 Huawei Developer Conference, JD’s team demonstrated how integrating the Cangjie language into HarmonyOS mini‑programs can halve API execution time, reduce main‑thread load, and improve cold‑start performance by over 20%, offering a high‑performance, cross‑platform development solution.
JoyGen introduces a two‑stage framework that generates high‑quality talking‑face videos by synchronizing lip movements with input audio using 3DMM‑based identity and expression coefficients, depth‑aware supervision, and a newly built high‑resolution Chinese speaking‑face dataset, achieving state‑of‑the‑art performance on multiple benchmarks.
The article details JD Retail’s collaboration with Tsinghua University to build the xLLM edge‑cloud unified large‑model inference framework, addressing e‑commerce AI challenges such as diverse inputs, task scheduling, model compression, and cost, while outlining future research directions and performance gains.
