Author

Alibaba International Intelligent Technology

Alibaba International Tech – Official channel of the Intelligent Technology team, sharing cutting‑edge AI applications and innovations in Alibaba's global e‑commerce business.

Articles

Likes

Views

Comments

Latest from Alibaba International Intelligent Technology

24 recent articles

Alibaba International Intelligent Technology

Mar 27, 2026 · Artificial Intelligence

How AI Agents Transform International Advertising Platforms

The article analyzes the characteristics of large language models, outlines three evolution directions—interaction redesign, creative productivity, and intelligent ad operations—and details Lazada's multi‑agent architecture, design principles, workflow, and evaluation metrics for deploying AI agents that automate and optimize ad‑campaign management.

AI AgentAdvertising PlatformChatbot

0 likes · 33 min read

How AI Agents Transform International Advertising Platforms

Alibaba International Intelligent Technology

Mar 20, 2026 · Artificial Intelligence

From Manual Troubleshooting to AI Automation: Building an Intelligent Diagnosis System for Lazada Ads

The Lazada advertising engine team designed a multi‑agent AI diagnosis platform that transforms noisy, multi‑source alerts into fast, accurate root‑cause analyses, achieving over 70% correct‑diagnosis rate, under 20% false‑alarm rate, and reducing investigation time from minutes to seconds.

AI diagnosisLLMadvertising operations

0 likes · 22 min read

From Manual Troubleshooting to AI Automation: Building an Intelligent Diagnosis System for Lazada Ads

Alibaba International Intelligent Technology

Mar 5, 2026 · Artificial Intelligence

Engineering Exploration of Generative Recall: Leveraging Large Models for Next‑Gen Recommendation Retrieval

The article analyzes the limitations of traditional ID‑based and vector recall, proposes a generative Semantic‑ID‑based recall framework (ASGR), details a series of inference‑time optimizations—including a custom SDPA‑enabled optimizer, novel beam search, static‑cache compilation, tree‑aware attention, sliding‑window attention, quantization, ONNX/Optimum conversion, and TensorRT‑LLM integration—and reports concrete latency and throughput gains that enable large‑scale, low‑latency recommendation serving.

Large Language Modelbeam searchgenerative recall

0 likes · 25 min read

Engineering Exploration of Generative Recall: Leveraging Large Models for Next‑Gen Recommendation Retrieval

Alibaba International Intelligent Technology

Feb 27, 2026 · Artificial Intelligence

A New Dual‑Tower Multi‑Objective Recall Framework (CSMF) Boosts Efficiency Without Extra Parameters

The paper introduces CSMF, a cascaded selective‑mask fine‑tuning framework for dual‑tower embedding‑based retrieval that sequentially optimizes exposure, click and conversion goals, incorporates cumulative percentile pruning and adaptive margin loss, and achieves measurable gains in ad revenue and CTR without increasing model size or latency.

cascaded selective maskdual-towerembedding-based retrieval

0 likes · 15 min read

A New Dual‑Tower Multi‑Objective Recall Framework (CSMF) Boosts Efficiency Without Extra Parameters

Alibaba International Intelligent Technology

Jan 13, 2026 · Artificial Intelligence

How Multimodal Large Models Boost International Product Information Understanding

The article details how AliExpress leverages a multimodal large‑model pipeline to automatically fill missing product attributes, discover schema gaps, and generate rich application tags, describing the technical challenges, training stages, experimental results, and business impact of the solution.

chain of thoughtcurriculum learninge‑commerce AI

0 likes · 28 min read

How Multimodal Large Models Boost International Product Information Understanding

Alibaba International Intelligent Technology

Jan 5, 2026 · Artificial Intelligence

Decoupled Multimodal Fusion (DMF) Boosts User Interest Modeling for CTR Prediction

The DMF framework introduces a modality‑enriched Decoupled Target Attention (DTA) and a Complementary Modality Modeling (CMM) strategy that together close the semantic gap between ID and multimodal features, delivering up to 5.3% CTCVR lift, 7.43% GMV increase, and a three‑fold throughput gain in large‑scale e‑commerce recommendation scenarios.

A/B testingCMMCTR prediction

0 likes · 13 min read

Decoupled Multimodal Fusion (DMF) Boosts User Interest Modeling for CTR Prediction

Alibaba International Intelligent Technology

Dec 31, 2025 · Artificial Intelligence

Mitigating Negative Transfer in Multi‑Target Cross‑Domain Recommendation with Unbiased Information Extraction and Adaptation (UIEA)

The paper, accepted at AAAI 2025, proposes UIEA—a three‑stage method that addresses data imbalance and negative transfer in multi‑target cross‑domain recommendation by extracting unbiased shared representations and adapting them with a user‑item attention module, achieving significant gains on Amazon, Douban, and IE datasets.

UIEAcross-domain recommendationdistributionally robust optimization

0 likes · 14 min read

Mitigating Negative Transfer in Multi‑Target Cross‑Domain Recommendation with Unbiased Information Extraction and Adaptation (UIEA)

Alibaba International Intelligent Technology

Dec 22, 2025 · Artificial Intelligence

Balancing Semantics and Efficiency: A Large‑Scale Personalized Generative Retrieval Method (ICDM 2025)

The paper proposes Hi‑Gen, a generative retrieval framework for large‑scale e‑commerce that jointly models semantic relevance and efficiency through discriminative product vectors, category‑guided hierarchical clustering, and a position‑aware loss, achieving more accurate and faster personalized recall.

generative retrievalhierarchical clusteringpersonalized e-commerce search

0 likes · 11 min read

Balancing Semantics and Efficiency: A Large‑Scale Personalized Generative Retrieval Method (ICDM 2025)

Alibaba International Intelligent Technology

Dec 8, 2025 · Artificial Intelligence

Breaking Homogenization: Redesigning Multi‑Scenario Recommendation by Uncovering Knowledge‑Sharing Traps

The paper reveals that knowledge‑sharing across recommendation domains causes homogenized results that boost per‑scene accuracy yet shrink overall GMV, and proposes the DPOMR algorithm with manual rules and an industrial‑grade reference model to restore domain diversity and improve platform‑wide order volume.

A/B testingDPOMRe-commerce

0 likes · 13 min read

Breaking Homogenization: Redesigning Multi‑Scenario Recommendation by Uncovering Knowledge‑Sharing Traps

Alibaba International Intelligent Technology

Dec 1, 2025 · Artificial Intelligence

Alibaba’s AI Team Sponsors CIKM 2025 and Launches the AnalyticCup Competition

The article reports that CIKM 2025 in Seoul featured three Alibaba International Intelligent Technology papers on multimodal recommendation and dynamic reserve pricing, and that the team organized the AnalyticCup competition and a workshop to advance multilingual e‑commerce search using large language models.

CIKM 2025Dynamic Reserve PriceMultilingual Search

0 likes · 8 min read

Alibaba’s AI Team Sponsors CIKM 2025 and Launches the AnalyticCup Competition