Over 10,000 engineers powering China’s leading lifestyle services e‑commerce platform. Supporting hundreds of millions of consumers, millions of merchants across 2,000+ industries. This is the public channel for the tech teams behind Meituan, Dianping, Meituan Waimai, Meituan Select, and related services.
This article reviews four ACL 2024 papers authored by Meituan’s research team—covering training cost reduction, speculative decoding, code generation optimization, and instruction fine‑tuning—while also announcing a live sharing session at the conference.
Meituan’s five long papers accepted at KDD 2024 introduce a dual‑intent model for search‑recommendation, a joint auction mechanism for ads, a robust ATE estimator for heavy‑tailed metrics, a decision‑focused causal learning framework for marketing, and an efficient on‑demand order‑pooling system for real‑time courier assignments.
Multithreaded programming splits tasks across logical and hardware threads to exploit multicore CPUs, requiring careful use of synchronization primitives such as mutexes, read‑write locks, condition variables, and lock‑free atomics, while avoiding pitfalls like race conditions, deadlocks, and false sharing for correct, high‑performance software.
Meituan’s search advertising has progressed from rule‑based keyword mining to hierarchical recall that partitions traffic and supply, and now to generative recall using large language models, chain‑of‑thought generation, diffusion‑enhanced multimodal vectors, and knowledge distillation, expanding the decision space while tackling compute and ROI challenges.
The article highlights three Meituan research papers accepted at SIGIR 2024—covering deep automated mechanism design for ad auction, a retrieval‑enhanced vertical federated recommendation framework, and disentangled contrastive hypergraph learning for next POI recommendation—and announces an online sharing event where the authors will present their work.
Meituan’s Tech Salon Session 77 describes how the company built a generic JavaScript‑hooking SDK packaged as an NPM module to give mini‑programs on platforms such as WeChat, Alipay and Kuaishou observable and controllable capabilities across UI, storage, network and system layers, enabling automated cache management, request mocking, state inspection and visual diff testing, which the ticket team leveraged to achieve over 30 % test scenario coverage, 100 % page coverage and discover hundreds of defects, while outlining future plans to stabilize and expand the framework.
At a recent Meituan Robotics Institute symposium, experts detailed the company’s fourth‑generation drone safety architecture with redundant subsystems and intelligent parachutes, discussed PHM advances for fault prediction, showcased all‑weather close‑range UAV positioning across Chinese cities, and presented flexible tactile‑vision fusion research for object recognition and robotic grasping.
Meituan enhances Apache Spark by integrating the Gluten‑Velox vectorized execution engine, converting row‑wise operations to columnar SIMD processing, which yields over 40 % memory savings and up to 13 % faster runtimes across thousands of ETL jobs, while addressing stability, ORC support, shuffle redesign, and off‑heap memory optimization.
Meituan's tech team highlights seven CVPR 2024 papers—spanning OCR pre‑training, long‑tail semi‑supervised learning, visual AIGC, audio‑visual segmentation and synthetic‑data detection—provides detailed abstracts and experimental results, and announces an online author‑talk session on June 27.
This article walks through the application of Domain-Driven Design (DDD) in a B‑side marketing platform, detailing how strategic design defines use cases and unified language, tactical design maps concepts to object models, and code architecture organizes implementations, illustrated with concrete examples, diagrams, and practical guidelines.
