2026-05-推荐算法论文阅读清单
Sequence Modeling Papers
Summary Statistics
- Total Papers: 11
- Companies: 5
ByteDance (4 papers)
| # | Paper Title | Authors | Year | Focus |
|---|---|---|---|---|
| 1 | OneTrans: Unified Feature Interaction and Sequence Modeling with One Transformer in Industrial Recommender | Zhaoqi Zhang, Haolei Pei, Jun Guo, et al. | 2026 | Recommendation Systems, Sequence Modeling |
| 2 | HyFormer: Revisiting the Roles of Sequence Modeling and Feature Interaction in CTR Prediction | Yunwen Huang, Shiyong Hong, Xijun Xiao, et al. | 2026 | CTR Prediction, Sequence Modeling |
| 3 | TokenMixer-Large: Scaling Up Large Ranking Models in Industrial Recommenders | Yuchen Jiang, Jie Zhu, Xintian Han, et al. | 2026 | Ranking Models, Scaling Laws |
| 4 | RankMixer: Scaling Up Ranking Models in Industrial Recommenders | Jie Zhu, Zhifang Fan, Xiaoxie Zhu, et al. | 2025 | Ranking Models, Scaling Laws |
Alibaba (2 papers)
| # | Paper Title | Authors | Year | Focus |
|---|---|---|---|---|
| 1 | HHFT: Hierarchical Heterogeneous Feature Transformer for Recommendation Systems | Liren Yu, Wenming Zhang, Silu Zhou, et al. | 2025 | Recommendation Systems, Feature Interaction |
| 2 | FAT: From Scaling to Structured Expressivity - Rethinking Transformers for CTR Prediction | Bencheng Yan, Yuejie Lei, Zhiyuan Zeng, et al. | 2025 | CTR Prediction, Transformers |
Meta (2 papers)
| # | Paper Title | Authors | Year | Focus |
|---|---|---|---|---|
| 1 | LLaTTE: Scaling Laws for Multi-Stage Sequence Modeling in Large-Scale Ads Recommendation | Lee Xiong, Zhirong Chen, Rahul Mayuranath, et al. | 2026 | Ads Recommendation, Scaling Laws |
| 2 | InterFormer: Effective Heterogeneous Interaction Learning for Click-Through Rate Prediction | Zhichen Zeng, Xiaolong Liu, Mengyue Hang, et al. | 2025 | CTR Prediction, Heterogeneous Interaction |
Google (1 paper)
| # | Paper Title | Authors | Year | Focus |
|---|---|---|---|---|
| 1 | HiFormer: Heterogeneous Feature Interactions Learning with Transformers for Recommender Systems | Huan Gui, Ruoxi Wang, Ke Yin, et al. | 2023 | Recommendation Systems, Feature Interaction |
Kuaishou (1 paper)
| # | Paper Title | Authors | Year | Focus |
|---|---|---|---|---|
| 1 | UniMixer: A Unified Architecture for Scaling Laws in Recommendation Systems | Mingming Ha, Guanchen Wang, Linxun Chen, et al. | 2026 | Recommendation Systems, Scaling Laws |
Key Research Topics
By Topic Frequency
- Scaling Laws: 5 papers (RankMixer, TokenMixer-Large, UniMixer, LLaTTE, FAT)
- Recommendation Systems: 5 papers (HHFT, OneTrans, HyFormer, UniMixer, HiFormer)
- CTR Prediction: 4 papers (HyFormer, FAT, InterFormer, HHFT)
- Feature Interaction: 4 papers (HHFT, OneTrans, HiFormer, InterFormer)
- Sequence Modeling: 3 papers (OneTrans, HyFormer, LLaTTE)
- Ranking Models: 2 papers (RankMixer, TokenMixer-Large)
By Year
- 2026: 5 papers (OneTrans, HyFormer, TokenMixer-Large, LLaTTE, UniMixer)
- 2025: 4 papers (RankMixer, HHFT, FAT, InterFormer)
- 2023: 1 paper (HiFormer)
Notes
- ByteDance leads with 4 papers, focusing on ranking models and sequence modeling
- Alibaba and Meta each contribute 2 papers on CTR prediction and recommendation systems
- Google and Kuaishou each have 1 paper on recommendation systems
- Scaling laws is the dominant research direction across companies
- Most papers are from 2025-2026, indicating recent focus on industrial applications
本博客所有文章除特别声明外,均采用 CC BY-NC-SA 4.0 许可协议。转载请注明来自 Baisen's Blog!











