Yu Zhou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yu Zhou has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Chengcheng Guo
Kuaishou Technology Beijing China
3 shared publications - Guorui Zhou
Kuaishou Technology Beijing China
3 shared publications - Kuo Cai
Kuaishou Technology Beijing China
3 shared publications - Qiang Luo
Kuaishou Technology, China
3 shared publications - Han Li
Kuaishou Technology, China
2 shared publications - Ji Liu
Kuaishou Technology, China
2 shared publications
Latest Publications
- Open Access
GEMs: Breaking the Long-Sequence Barrier in Generative Recommendation with a Multi-Stream Decoder
While generative recommendations (GR) possess strong sequential reasoning capabilities, they face significant challenges when processing extremely long user behavior sequences: the high computational cost forces practical sequence lengths to be limited, preventing models from capturing users' lifelong interests; meanwhile, the inherent "recency bias" of attention mechanisms further weakens learning from long-term history. To overcome this bottleneck, we propose GEMs (Generative rEcommendation with a Multi-stream decoder), a novel and unified framework designed to break the long-sequence barrier by capturing users' lifelong interaction sequences through a multi-stream perspective. Specifically, GEMs partitions user behaviors into three temporal streams$\unicode{x2014}$Recent, Mid-term, and Lifecycle$\unicode{x2014}$and employs tailored inference schemes for each: a one-stage real-time extractor for immediate dynamics, a lightweight indexer for cross attention to balance accuracy and cost for mid-term sequences, and a two-stage offline-online compression module for lifelong modeling. These streams are integrated via a parameter-free fusion strategy to enable holistic interest representation. Extensive experiments on large-scale industrial datasets demonstrate that GEMs significantly outperforms state-of-the-art methods in recommendation accuracy. Notably, GEMs is the first lifelong GR framework successfully deployed in a high-concurrency industrial environment, achieving superior inference efficiency while processing user sequences of over 100,000 interactions.
Open AccessGEMs: Breaking the Long-Sequence Barrier in Generative Recommendation with a Multi-Stream Decoder
While generative recommendations (GR) possess strong sequential reasoning capabilities, they face significant challenges when processing extremely long user behavior sequences: the high computational cost forces practical sequence lengths to be limited, preventing models from capturing users' lifelong interests; meanwhile, the inherent "recency bias" of attention mechanisms further weakens learning from long-term history. To overcome this bottleneck, we propose GEMs (Generative rEcommendation with a Multi-stream decoder), a novel and unified framework designed to break the long-sequence barrier by capturing users' lifelong interaction sequences through a multi-stream perspective. Specifically, GEMs partitions user behaviors into three temporal streams$\unicode{x2014}$Recent, Mid-term, and Lifecycle$\unicode{x2014}$and employs tailored inference schemes for each: a one-stage real-time extractor for immediate dynamics, a lightweight indexer for cross attention to balance accuracy and cost for mid-term sequences, and a two-stage offline-online compression module for lifelong modeling. These streams are integrated via a parameter-free fusion strategy to enable holistic interest representation. Extensive experiments on large-scale industrial datasets demonstrate that GEMs significantly outperforms state-of-the-art methods in recommendation accuracy. Notably, GEMs is the first lifelong GR framework successfully deployed in a high-concurrency industrial environment, achieving superior inference efficiency while processing user sequences of over 100,000 interactions.
- Open Access
PROMISE: Process Reward Models Unlock Test-Time Scaling Laws in Generative Recommendations
Generative Recommendation has emerged as a promising paradigm, reformulating recommendation as a sequence-to-sequence generation task over hierarchical Semantic IDs. However, existing methods suffer from a critical issue we term Semantic Drift, where errors in early, high-level tokens irreversibly divert the generation trajectory into irrelevant semantic subspaces. Inspired by Process Reward Models (PRMs) that enhance reasoning in Large Language Models, we propose Promise, a novel framework that integrates dense, step-by-step verification into generative models. Promise features a lightweight PRM to assess the quality of intermediate inference steps, coupled with a PRM-guided Beam Search strategy that leverages dense feedback to dynamically prune erroneous branches. Crucially, our approach unlocks Test-Time Scaling Laws for recommender systems: by increasing inference compute, smaller models can match or surpass larger models. Extensive offline experiments and online A/B tests on a large-scale platform demonstrate that Promise effectively mitigates Semantic Drift, significantly improving recommendation accuracy while enabling efficient deployment.
Open AccessPROMISE: Process Reward Models Unlock Test-Time Scaling Laws in Generative Recommendations
Generative Recommendation has emerged as a promising paradigm, reformulating recommendation as a sequence-to-sequence generation task over hierarchical Semantic IDs. However, existing methods suffer from a critical issue we term Semantic Drift, where errors in early, high-level tokens irreversibly divert the generation trajectory into irrelevant semantic subspaces. Inspired by Process Reward Models (PRMs) that enhance reasoning in Large Language Models, we propose Promise, a novel framework that integrates dense, step-by-step verification into generative models. Promise features a lightweight PRM to assess the quality of intermediate inference steps, coupled with a PRM-guided Beam Search strategy that leverages dense feedback to dynamically prune erroneous branches. Crucially, our approach unlocks Test-Time Scaling Laws for recommender systems: by increasing inference compute, smaller models can match or surpass larger models. Extensive offline experiments and online A/B tests on a large-scale platform demonstrate that Promise effectively mitigates Semantic Drift, significantly improving recommendation accuracy while enabling efficient deployment.
- Open Access
- 4 December 2025
- Published by MDPI AG in Preprints.org
A Survey of Generative Recommendation from a Tri-Decoupled Perspective: Tokenization, Architecture, and Optimization
The recommender systems community is witnessing a rapid shift from multi-stage cascaded discriminative pipelines (retrieval, ranking, and re-ranking) toward unified generative frameworks that directly generate items. Compared with traditional discriminative models, generative recommender systems offer the potential to mitigate cascaded error propagation, improve hardware utilization through unified architectures, and optimize beyond local user behaviors. This emerging paradigm has been catalyzed by the rise of generative models and the demand for end-to-end architectures that significantly improve Model FLOPS Utilization (MFU). In this survey, we provide a comprehensive analysis of generative recommendation through tri-decoupled perspective of tokenization, architecture, and optimization, three foundational components that collectively define existing generative systems. We trace the evolution of tokenization from sparse ID- and text-based encodings to semantic identifiers that balance vocabulary efficiency with semantic expressiveness; analyze encoder–decoder, decoder-only, and diffusion-based architectures that increasingly adopt unified, scalable, and efficient backbones; and review the transition from supervised next-token prediction to reinforcement learning–based preference alignment enabling multi-dimensional preference optimization. We further summarize practical deployments across cascade stages and application scenarios, and examine key open challenges. Taken together, this survey is intended to serve as a foundational reference for the research community and as an actionable blueprint for industrial practitioners building next-generation generative recommender systems. To support ongoing research, we maintain a living repository https://github.com/Kuaishou-RecModel/Tri-Decoupled-GenRec}{https://github.com/Kuaishou-RecModel/Tri-Decoupled-GenRec that continuously tracks emerging literature and reference implementations.
- 4 December 2025
- Published by MDPI AG in Preprints.org
Open AccessA Survey of Generative Recommendation from a Tri-Decoupled Perspective: Tokenization, Architecture, and Optimization
The recommender systems community is witnessing a rapid shift from multi-stage cascaded discriminative pipelines (retrieval, ranking, and re-ranking) toward unified generative frameworks that directly generate items. Compared with traditional discriminative models, generative recommender systems offer the potential to mitigate cascaded error propagation, improve hardware utilization through unified architectures, and optimize beyond local user behaviors. This emerging paradigm has been catalyzed by the rise of generative models and the demand for end-to-end architectures that significantly improve Model FLOPS Utilization (MFU). In this survey, we provide a comprehensive analysis of generative recommendation through tri-decoupled perspective of tokenization, architecture, and optimization, three foundational components that collectively define existing generative systems. We trace the evolution of tokenization from sparse ID- and text-based encodings to semantic identifiers that balance vocabulary efficiency with semantic expressiveness; analyze encoder–decoder, decoder-only, and diffusion-based architectures that increasingly adopt unified, scalable, and efficient backbones; and review the transition from supervised next-token prediction to reinforcement learning–based preference alignment enabling multi-dimensional preference optimization. We further summarize practical deployments across cascade stages and application scenarios, and examine key open challenges. Taken together, this survey is intended to serve as a foundational reference for the research community and as an actionable blueprint for industrial practitioners building next-generation generative recommender systems. To support ongoing research, we maintain a living repository https://github.com/Kuaishou-RecModel/Tri-Decoupled-GenRec}{https://github.com/Kuaishou-RecModel/Tri-Decoupled-GenRec that continuously tracks emerging literature and reference implementations.