cs.IRNov 14, 2026

TokenFormer V2: Breaking the Resolution-Complexity Dilemma in Unified Recommendation

Authors: Kaihui Wu, Guoming Li, Liang Guo, Yifeng Zhou, Yuehong Hu, Junwei Pan, Zhixiang Feng, Chengguo Yin, 

Organizations: Tencent Inc. · The Hong Kong Polytechnic University

Abstract

Industrial recommendation faces a resolution--complexity dilemma: dense interactions make detailed modeling of long behavior histories expensive, while compact history summaries restrict the evidence available to prediction. A unified backbone must preserve rich behavioral details within strict serving budgets. We introduce TokenFormer V2, a unified architecture that explicitly decouples representation resolution from interaction density. Its group-wise token layout jointly encodes behavior segments with non-sequential context, expands interaction ranges via hierarchical group merging, and coordinates distributed groups through NS Fusion and Global Sync modules. Through this local--global decomposition paradigm, computation is concentrated on structured interactions while preserving fine-grained evidence, ensuring that every encoded event remains directly accessible to the Full-Resolution Readout module. On the Tencent Advertising Algorithm Competition 2026 (TAAC 2026) benchmark, TokenFormer V2 achieves top-ranking accuracy among unified recommendation baselines while using \textbf{5.1×\times fewer FLOPs} than leading baselines, sustaining its advantage across long histories and imbalanced behavior domains. Furthermore, in billion-parameter evaluations on WeChat Channels advertising, it consistently outperforms state-of-the-art industrial baselines, yielding up to a +0.07 pp overall AUC gain. In live online A/B testing against the production model, TokenFormer V2 delivers a statistically significant 2.33% increase in GMV. These results establish TokenFormer V2 as a battle-tested blueprint for scalable, full-resolution behavior modeling in industrial recommendation.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. TokenFormer: Unify the Multi-Field and Sequential Recommendation Worlds

    Apr 15, 2026Yifeng Zhou, Yuehong Hu, Zhixiang Feng +9Recommender SystemsSequential Recommendation