Chuan He
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chuan He has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Liang Liu
Google, Mountain View, USA
4 shared publications - Yuening Li
Google, Mountain View, USA
4 shared publications - Diego Uribe Mora
YouTube, Google, Mountain View, CA, USA
3 shared publications - Ruixiao Sun
YouTube, Google, Mountain View, CA, USA
2 shared publications - Yuanzhen Lin
YouTube, Google, Mountain View, CA, USA
2 shared publications - Zhimeng Jiang
YouTube, Google, Mountain View, CA, USA
2 shared publications
Latest Publications
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1500-1505
Soft Curriculum Learning for Optimizing Fresh and Generalized Recommendations
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1500-1505
Open AccessSoft Curriculum Learning for Optimizing Fresh and Generalized Recommendations
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1199-1205
Interest Sequence for User Modeling in Industrial Short-Form Video Recommendation
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1199-1205
Open AccessInterest Sequence for User Modeling in Industrial Short-Form Video Recommendation
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7456-7464
Addressing Intent Dissonance in Cross-Domain Distillation on YouTube
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7456-7464
Open AccessAddressing Intent Dissonance in Cross-Domain Distillation on YouTube
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4902-4906
Beyond Item IDs: Scaling Short-Form-Video Recommendation via Semantic-Native Long Sequence Modeling
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4902-4906
Open AccessBeyond Item IDs: Scaling Short-Form-Video Recommendation via Semantic-Native Long Sequence Modeling
- Open Access
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 832-834
Short-form Video Needs Long-term Interests: An Industrial Solution for Serving Large User Sequence Models
Sequential models are invaluable for powering personalized recommendation systems. In the context of short-form video (SFV) feeds, where user behavior history is typically longer, systems must be able to understand users’ long-term interests. However, deploying large sequence models to extensive web-scale applications faces challenges due to high serving cost. To address this, we propose an industrial framework designed for efficiently serving large user sequence models. Specifically, the proposed infrastructure decouples serving of the user sequence model and the main recommendation model, with the user sequence model being served offline (asynchronously) with periodical refresh. The proposed infrastructure is also model-agnostic; thus, it can be used to support any type of user sequence models (even LLMs) with controllable costs. Empirical results show that large user models deployed with our framework significantly and consistently enhance the quality of the main recommendation model with minimal serving costs increase.
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 832-834
Open AccessShort-form Video Needs Long-term Interests: An Industrial Solution for Serving Large User Sequence Models
Sequential models are invaluable for powering personalized recommendation systems. In the context of short-form video (SFV) feeds, where user behavior history is typically longer, systems must be able to understand users’ long-term interests. However, deploying large sequence models to extensive web-scale applications faces challenges due to high serving cost. To address this, we propose an industrial framework designed for efficiently serving large user sequence models. Specifically, the proposed infrastructure decouples serving of the user sequence model and the main recommendation model, with the user sequence model being served offline (asynchronously) with periodical refresh. The proposed infrastructure is also model-agnostic; thus, it can be used to support any type of user sequence models (even LLMs) with controllable costs. Empirical results show that large user models deployed with our framework significantly and consistently enhance the quality of the main recommendation model with minimal serving costs increase.