Chengcheng Guo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chengcheng Guo has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Kuo Cai
Kuaishou Technology Beijing China
6 shared publications - Qiang Luo
Kuaishou Technology, China
6 shared publications - Guorui Zhou
Kuaishou Technology Beijing China
5 shared publications - Kun Gai
Kuaishou Technology yu_qing
4 shared publications - Ruiming Tang
Kuaishou Technology, China
4 shared publications - Han Li
Kuaishou Technology, China
3 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
OneLive: Dynamically Unified Generative Framework for Live-Streaming Recommendation
Live-streaming recommender system serves as critical infrastructure that bridges the patterns of real-time interactions between users and authors. Similar to traditional industrial recommender systems, live-streaming recommendation also relies on cascade architectures to support large-scale concurrency. Recent advances in generative recommendation unify the multi-stage recommendation process with Transformer-based architectures, offering improved scalability and higher computational efficiency. However, the inherent complexity of live-streaming prevents the direct transfer of these methods to live-streaming scenario, where continuously evolving content, limited lifecycles, strict real-time constraints, and heterogeneous multi-objectives introduce unique challenges that invalidate static tokenization and conventional model framework. To address these issues, we propose OneLive, a dynamically unified generative recommendation framework tailored for live-streaming scenario. OneLive integrates four key components: (i) A Dynamic Tokenizer that continuously encodes evolving real-time live content fused with behavior signal through residual quantization; (ii) A Time-Aware Gated Attention mechanism that explicitly models temporal dynamics for timely decision making; (iii) An efficient decoder-only generative architecture enhanced with Sequential MTP and QK Norm for stable training and accelerated inference; (iv) A Unified Multi-Objective Alignment Framework reinforces policy optimization for personalized preferences.
Open AccessOneLive: Dynamically Unified Generative Framework for Live-Streaming Recommendation
Live-streaming recommender system serves as critical infrastructure that bridges the patterns of real-time interactions between users and authors. Similar to traditional industrial recommender systems, live-streaming recommendation also relies on cascade architectures to support large-scale concurrency. Recent advances in generative recommendation unify the multi-stage recommendation process with Transformer-based architectures, offering improved scalability and higher computational efficiency. However, the inherent complexity of live-streaming prevents the direct transfer of these methods to live-streaming scenario, where continuously evolving content, limited lifecycles, strict real-time constraints, and heterogeneous multi-objectives introduce unique challenges that invalidate static tokenization and conventional model framework. To address these issues, we propose OneLive, a dynamically unified generative recommendation framework tailored for live-streaming scenario. OneLive integrates four key components: (i) A Dynamic Tokenizer that continuously encodes evolving real-time live content fused with behavior signal through residual quantization; (ii) A Time-Aware Gated Attention mechanism that explicitly models temporal dynamics for timely decision making; (iii) An efficient decoder-only generative architecture enhanced with Sequential MTP and QK Norm for stable training and accelerated inference; (iv) A Unified Multi-Objective Alignment Framework reinforces policy optimization for personalized preferences.
- Open Access
GLASS: A Generative Recommender for Long-sequence Modeling via SID-Tier and Semantic Search
Leveraging long-term user behavioral patterns is a key trajectory for enhancing the accuracy of modern recommender systems. While generative recommender systems have emerged as a transformative paradigm, they face hurdles in effectively modeling extensive historical sequences. To address this challenge, we propose GLASS, a novel framework that integrates long-term user interests into the generative process via SID-Tier and Semantic Search. We first introduce SID-Tier, a module that maps long-term interactions into a unified interest vector to enhance the prediction of the initial SID token. Unlike traditional retrieval models that struggle with massive item spaces, SID-Tier leverages the compact nature of the semantic codebook to incorporate cross features between the user's long-term history and candidate semantic codes. Furthermore, we present semantic hard search, which utilizes generated coarse-grained semantic ID as dynamic keys to extract relevant historical behaviors, which are then fused via an adaptive gated fusion module to recalibrate the trajectory of subsequent fine-grained tokens. To address the inherent data sparsity in semantic hard search, we propose two strategies: semantic neighbor augmentation and codebook resizing. Extensive experiments on two large-scale real-world datasets, TAOBAO-MM and KuaiRec, demonstrate that GLASS outperforms state-of-the-art baselines, achieving significant gains in recommendation quality. Our codes are made publicly available to facilitate further research in generative recommendation.
Open AccessGLASS: A Generative Recommender for Long-sequence Modeling via SID-Tier and Semantic Search
Leveraging long-term user behavioral patterns is a key trajectory for enhancing the accuracy of modern recommender systems. While generative recommender systems have emerged as a transformative paradigm, they face hurdles in effectively modeling extensive historical sequences. To address this challenge, we propose GLASS, a novel framework that integrates long-term user interests into the generative process via SID-Tier and Semantic Search. We first introduce SID-Tier, a module that maps long-term interactions into a unified interest vector to enhance the prediction of the initial SID token. Unlike traditional retrieval models that struggle with massive item spaces, SID-Tier leverages the compact nature of the semantic codebook to incorporate cross features between the user's long-term history and candidate semantic codes. Furthermore, we present semantic hard search, which utilizes generated coarse-grained semantic ID as dynamic keys to extract relevant historical behaviors, which are then fused via an adaptive gated fusion module to recalibrate the trajectory of subsequent fine-grained tokens. To address the inherent data sparsity in semantic hard search, we propose two strategies: semantic neighbor augmentation and codebook resizing. Extensive experiments on two large-scale real-world datasets, TAOBAO-MM and KuaiRec, demonstrate that GLASS outperforms state-of-the-art baselines, achieving significant gains in recommendation quality. Our codes are made publicly available to facilitate further research in generative recommendation.
- 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.
- Open Access
MISS: Multi-Modal Tree Indexing and Searching with Lifelong Sequential Behavior for Retrieval Recommendation
Large-scale industrial recommendation systems typically employ a two-stage paradigm of retrieval and ranking to handle huge amounts of information. Recent research focuses on improving the performance of retrieval model. A promising way is to introduce extensive information about users and items. On one hand, lifelong sequential behavior is valuable. Existing lifelong behavior modeling methods in ranking stage focus on the interaction of lifelong behavior and candidate items from retrieval stage. In retrieval stage, it is difficult to utilize lifelong behavior because of a large corpus of candidate items. On the other hand, existing retrieval methods mostly relay on interaction information, potentially disregarding valuable multi-modal information. To solve these problems, we represent the pioneering exploration of leveraging multi-modal information and lifelong sequence model within the advanced tree-based retrieval model. We propose Multi-modal Indexing and Searching with lifelong Sequence (MISS), which contains a multi-modal index tree and a multi-modal lifelong sequence modeling module. Specifically, for better index structure, we propose multi-modal index tree, which is built using the multi-modal embedding to precisely represent item similarity. To precisely capture diverse user interests in user lifelong sequence, we propose collaborative general search unit (Co-GSU) and multi-modal general search unit (MM-GSU) for multi-perspective interests searching.
Open AccessMISS: Multi-Modal Tree Indexing and Searching with Lifelong Sequential Behavior for Retrieval Recommendation
Large-scale industrial recommendation systems typically employ a two-stage paradigm of retrieval and ranking to handle huge amounts of information. Recent research focuses on improving the performance of retrieval model. A promising way is to introduce extensive information about users and items. On one hand, lifelong sequential behavior is valuable. Existing lifelong behavior modeling methods in ranking stage focus on the interaction of lifelong behavior and candidate items from retrieval stage. In retrieval stage, it is difficult to utilize lifelong behavior because of a large corpus of candidate items. On the other hand, existing retrieval methods mostly relay on interaction information, potentially disregarding valuable multi-modal information. To solve these problems, we represent the pioneering exploration of leveraging multi-modal information and lifelong sequence model within the advanced tree-based retrieval model. We propose Multi-modal Indexing and Searching with lifelong Sequence (MISS), which contains a multi-modal index tree and a multi-modal lifelong sequence modeling module. Specifically, for better index structure, we propose multi-modal index tree, which is built using the multi-modal embedding to precisely represent item similarity. To precisely capture diverse user interests in user lifelong sequence, we propose collaborative general search unit (Co-GSU) and multi-modal general search unit (MM-GSU) for multi-perspective interests searching.