OneRanker: Unified Generation and Ranking with One Model in Industrial Advertising Recommendation

TL;DR

This paper introduces OneRanker, a unified model that integrates generation and ranking for advertising recommendations, improving business metrics by aligning interests and values end-to-end in industrial deployment.

Contribution

We propose a deep integrated architecture with value-aware multi-task decoupling, target awareness mechanisms, and consistency guarantees for unified generation and ranking.

Findings

Significant GMV increase (+1.34%) in Tencent's advertising system.

Effective separation of interest coverage and value optimization.

Successful end-to-end optimization with consistency constraints.

Abstract

The end-to-end generative paradigm is revolutionizing advertising recommendation systems, driving a shift from traditional cascaded architectures towards unified modeling. However, practical deployment faces three core challenges: the misalignment between interest objectives and business value, the target-agnostic limitation of generative processes, and the disconnection between generation and ranking stages. Existing solutions often fall into a dilemma where single-stage fusion induces optimization tension, while stage decoupling causes irreversible information loss. To address this, we propose OneRanker, achieving architectural-level deep integration of generation and ranking. First, we design a value-aware multi-task decoupling architecture. By leveraging task token sequences and causal mask, we separate interest coverage and value optimization spaces within shared representations, effectively alleviating target conflicts. Second, we construct a coarse-to-fine collaborative target awareness mechanism, utilizing Fake Item Tokens for implicit awareness during generation and a ranking decoder for explicit value alignment at the candidate level. Finally, we propose input-output dual-side consistency guarantees. Through Key/Value pass-through mechanisms and Distribution Consistency (DC) Constraint Loss, we achieve end-to-end collaborative optimization between generation and ranking. The full deployment on Tencent's WeiXin channels advertising system has shown a significant improvement in key business metrics (GMV - Normal +1.34\%), providing a new paradigm with industrial feasibility for generative advertising recommendations.