English(EN) Generative End-to-end Ad Retrieval at Douyin

抖音广告部署GEAR实现生成式端到端广告检索

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-30 09:00

研究人员开发了GEAR，一个新颖的端到端框架，旨在克服生成式广告检索系统中的关键瓶颈。该框架解决了表示崩溃和项目冲突问题，这些问题阻碍了大规模推荐系统的稳定适应和精确性。GEAR通过联合优化分词器、生成器和重排器来实现这一点，并采用了BasisVQ等创新技术来实现稳定的码本参数化，以及上下文条件重排头来消除项目歧义。该系统目前已部署在抖音广告上，服务于数亿日活跃用户，并在在线A/B测试中取得了显著的改进。 AI

影响增强了生成式广告检索系统的可扩展性和精确性，影响了抖音等大规模平台。

排序理由关于广告检索新框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.IR (Information Retrieval) 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 关于广告检索新框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, product, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 3 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Xiang Sun · 2026-09-30 09:00

抖音的生成式端到端广告检索

Generative retrieval reformulates recommendation as the generation of discrete item tokens. However, scaling this paradigm to real-world recommender systems reveals two critical bottlenecks: 1) Representation collapse, where the item tokenizer converges to degenerate results unde…

本文如何被排名

报道来源 [1]

抖音的生成式端到端广告检索

相关实体

相关话题