mlsanityData to 7 Oct 2026

JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications

arXiv 2606.28070 ↗First posted 26 Jun 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

JD.com, one of the world's largest e-commerce platforms, serves over 700 million active users and millions of merchants, with a catalog of tens of billions of SKUs. At this scale, high-quality, structured item knowledge underpins a better consumer experience, lower management costs, and higher operational efficiency-yet producing and serving it poses three industrial-scale challenges: fast-emerging concepts, high-quality knowledge production for massive SKUs, and diverse downstream requirements. To address these challenges, we present the JD Oxygen AI Item Center (Oxygen AIIC), an industrial-scale platform built on LLMs/VLMs for item-knowledge production and service. Oxygen AIIC is built around four core pillars: (i) ontology engineering driven by efficient human-AI collaboration, which supports the dynamic evolution and agile expansion of an ontology with millions of entries; (ii) a "Semantic Search then Discrimination"(S2D) knowledge identification architecture that, combined with throughput improvement strategies, enables scalable, extensible, and high-throughput AI Item Library production for tens of billions of SKUs; (iii) self-evolving item-understanding LLMs/VLMs that improve in a stable and controllable manner, enabling knowledge production with 94.2% precision and 82.8% recall; and (iv) a unified item tunnel that serves as the data and service hub. Oxygen AIIC now covers tens of thousands of JD categories and processes hundreds of millions of item updates per day on Huawei Ascend NPUs. It has accumulated hundreds of billions of item-knowledge assets. Deployed across core business scenarios-including search, recommendation, operations, category planning-Oxygen AIIC has delivered measurable gains at scale. Search-traffic coverage reaches 80.4%, item-information quality issues drop by 37%, the automated fill rate of core attributes during item listing exceeds 80%.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 65 of its 104 references that are in the map. First posted on arXiv 26 Jun 2026.

Builds on

65 of 104 references.

References · 65

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  7. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  8. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  9. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  10. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  11. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  12. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
38 more
  1. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  2. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  3. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,548
  4. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  5. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
  6. 2024Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Servecited by 507
  7. 2023DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretrainingcited by 385
  8. 2024Self-Preference Bias in LLM-as-a-Judgecited by 248
  9. 2022Unified Structure Generation for Universal Information Extractioncited by 220
  10. 2023InstructUIE: Multi-task Instruction Tuning for Unified Information Extractioncited by 167
  11. 2020Continual Lifelong Learning in Natural Language Processing: A Surveycited by 152
  12. 2024An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4cited by 90
  13. 2023LLMs4OL: Large Language Models for Ontology Learningcited by 75
  14. 2024Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Constructioncited by 70
  15. 2024Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracycited by 66
  16. 2018OpenTag: Open Attribute Value Extraction from Product Profiles [Deep Learning, Active Learning, Named Entity Recognition]cited by 62
  17. 2021MAVE: A Product Dataset for Multi-source Attribute Value Extractioncited by 53
  18. 2019Semantic Product Searchcited by 51
  19. 2018TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clusteringcited by 48
  20. 2024eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Datacited by 44
  21. 2020Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Productcited by 39
  22. 2020TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced Graph Neural Networkcited by 37
  23. 2019Product Knowledge Graph Embedding for E-commercecited by 36
  24. 2021AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decodingcited by 32
  25. 2019HiExpan: Task-Guided Taxonomy Construction by Hierarchical Tree Expansioncited by 31
  26. 2020STEAM: Self-Supervised Taxonomy Expansion with Mini-Pathscited by 31
  27. 2020AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Typescited by 31
  28. 2020AliCoCo: Alibaba E-commerce Cognitive Concept Netcited by 23
  29. 2025Ontology Generation using Large Language Modelscited by 23
  30. 2025AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corporacited by 23
  31. 2020Octet: Online Catalog Taxonomy Enrichment with Self-Supervisioncited by 22
  32. 2024Using LLMs for the Extraction and Normalization of Product Attribute Valuescited by 20
  33. 2021PAM: Understanding Product Images in Cross Product Category Attribute Extractioncited by 18
  34. 2023Ontology engineering with Large Language Modelscited by 17
  35. 2022Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product Attribute Extractioncited by 12
  36. 2024LLMs4Life: Large Language Models for Ontology Learning in Life Sciencescited by 12
  37. 2023Large Scale Generative Multimodal Attribute Extraction for E-commerce Attributescited by 11
  38. 2023A Unified Generative Approach to Product Attribute-Value Identificationcited by 10

50 most cited of 65 All 65 (JSON)

Built on by

Not cited yet.