Token Factory: Efficiently Integrating Diverse Signals into Large Recommendation Models

[Submitted on 17 Jun 2026 (v1), last revised 27 Jul 2026 (this version, v3)]

View PDF HTML (experimental)

Abstract:Large Recommendation Models (LRMs) have demonstrated promising capabilities in industry-scale recommendation tasks. However, holistically integrating traditional signals into these transformer-based architectures effectively and efficiently remains a major challenge. Conventional approaches that “textualize” these signals directly or create discrete item representations often lead to excessively long prompts, substantial memory footprints, and high computational overhead. To overcome these limitations, we propose “Token Factory”, a framework designed to transform traditional signals into “soft tokens” that can be directly processed by LRMs. This approach enables efficient integration and compression of heterogeneous input features, preventing prompt length explosion while enhancing model performance. We detail the architecture of Token Factory and present experimental results validating its effectiveness in a production-scale recommendation environment.

Submission history

From: Shao-Chuan Wang [view email]
[v1] Wed, 17 Jun 2026 22:27:36 UTC (4,083 KB)
[v2] Sat, 20 Jun 2026 05:30:35 UTC (4,083 KB)
[v3] Mon, 27 Jul 2026 23:16:22 UTC (5,119 KB)