How LLMs Are Transforming Long-Term Cross-Domain Interest Modeling for Recommendations

The Datafun Summit 2025 talk by JD’s algorithm engineer Tian Mingyang explains how generative AI is driving a paradigm shift in recommendation systems, detailing the limits of traditional models, the new dynamic cross‑domain inference chain technique, joint engineering‑algorithm optimizations, and the remaining challenges for future deployment.

AICross-Domain ModelingEngineering Optimization

0 likes · 32 min read

How LLMs Are Transforming Long-Term Cross-Domain Interest Modeling for Recommendations

Zhihu Tech Column

Jan 17, 2025 · Artificial Intelligence

Zhihu Direct Answer: Product Overview and Technical Practices

This article summarizes the key technical insights from Zhihu Direct Answer, an AI-powered search product, covering its product overview, RAG framework, query understanding, retrieval strategies, chunking, reranking, generation techniques, evaluation methods, and engineering optimizations for cost and performance.

AI searchEngineering OptimizationGeneration

0 likes · 13 min read

Zhihu Direct Answer: Product Overview and Technical Practices

21CTO

Nov 2, 2023 · Cloud Computing

How X Cut Cloud Costs by 60%: Inside the ‘CloudExit’ Strategy

X's engineering team achieved a 60% reduction in monthly cloud costs through a comprehensive CloudExit strategy that moved media and blob storage on‑premises, cut code lines, closed data centers, built a GPU super‑computer, and optimized networking, saving over $60 million annually.

Cloud Cost ReductionEngineering Optimizationcloud migration

0 likes · 11 min read

How X Cut Cloud Costs by 60%: Inside the ‘CloudExit’ Strategy

NetEase Yanxuan Technology Product Team

Sep 19, 2022 · Mobile Development

NetEase Yanxuan iOS App Architecture Evolution: A Case Study in Modularization and Engineering Optimization

The article details how NetEase Yanxuan’s massive iOS codebase was refactored through modularization and layered architecture—splitting the main project, isolating business modules, automating dependency analysis, binaryizing core libraries, and cleaning unused resources—resulting in reduced coupling, a 6% faster compile time, and a sustainable CI‑driven development workflow.

App Architecture EvolutionCode DecouplingComponent-based Development

0 likes · 18 min read

NetEase Yanxuan iOS App Architecture Evolution: A Case Study in Modularization and Engineering Optimization