Qiang Luo

OneRec Team, Biao Yang, Boyang Ding et al.

Generative recommendation models in the OneRec family have been widely deployed in many real-world services, such as short-video, live-streaming, advertising, and e-commerce. However, these generative models can only benefit from the scaling advantage, while their reasoning ability is hard to activate, since we cannot construct meaningful Chain-of-Thought (CoT) sequences consisting of itemic tokens only. Inspired by the success of the reasoning-style ``think before answer'' paradigm in the LLM field, we conduct preliminary studies (i.e., OneRec-Think, OpenOneRec) to explore reasoning capability in generative recommendation. Nevertheless, we notice an unexpected phenomenon: the thinking mode does not show advantages over the non-thinking mode. Drawing insights from recent findings on CoT robustness in multi-modal language models, we argue that effective reasoning in recommendation rests on two factors: perception, the ability to ground itemic tokens in their underlying language semantics, and cognition, the ability to reorganize a user's behavior sequence into coherent latent interest points. We therefore propose OneReason, which includes: (1) strong itemic token perception in pre-training, (2) a three-level cognition-enhanced CoT format for recommendation tasks in SFT, and (3) a specialize-then-unify training recipe in RL to enhance the thinking ability.

Yijia Sun, Shanshan Huang, Zhiyuan Guan et al.

Industrial-scale recommender systems rely on a cascade pipeline in which the retrieval stage must return a high-recall candidate set from billions of items under tight latency. Existing solutions ei- ther (i) suffer from limited expressiveness in capturing fine-grained user-item interactions, as seen in decoupled dual-tower architectures that rely on separate encoders, or generative models that lack precise target-aware matching capabilities, or (ii) build structured indices (tree, graph, quantization) whose item-centric topologies struggle to incorporate dynamic user preferences and incur prohibitive construction and maintenance costs. We present GRank, a novel structured-index-free retrieval paradigm that seamlessly unifies target-aware learning with user-centric retrieval. Our key innovations include: (1) A target-aware Generator trained to perform personalized candidate generation via GPU-accelerated MIPS, eliminating semantic drift and maintenance costs of structured indexing; (2) A lightweight but powerful Ranker that performs fine-grained, candidate-specific inference on small subsets; (3) An end-to-end multi-task learning framework that ensures semantic consistency between generation and ranking objectives. Extensive experiments on two public benchmarks and a billion-item production corpus demonstrate that GRank improves Recall@500 by over 30% and 1.7$\times$ the P99 QPS of state-of-the-art tree- and graph-based retrievers. GRank has been fully deployed in production in our recommendation platform since Q2 2025, serving 400 million active users with 99.95% service availability. Online A/B tests confirm significant improvements in core engagement metrics, with Total App Usage Time increasing by 0.160% in the main app and 0.165% in the Lite version.

Zhao Liu, Yichen Zhu, Yiqing Yang et al.

Generative recommendation (GR) is an emerging paradigm that represents each item via a tokenizer as an n-digit semantic ID (SID) and predicts the next item by autoregressively generating its SID conditioned on the user's history. However, two structural properties of SIDs make ARMs ill-suited. First, intra-item consistency: the n digits jointly specify one item, yet the left-to-right causality trains each digit only under its prefix and blocks bidirectional cross-digit evidence, collapsing supervision to a single causal path. Second, inter-digit heterogeneity: digits differ in semantic granularity and predictability, while the uniform next-token objective assigns equal weight to all digits, overtraining easy digits and undertraining hard digits. To address these two issues, we propose DiffGRM, a diffusion-based GR model that replaces the autoregressive decoder with a masked discrete diffusion model (MDM), thereby enabling bidirectional context and any-order parallel generation of SID digits for recommendation. Specifically, we tailor DiffGRM in three aspects: (1) tokenization with Parallel Semantic Encoding (PSE) to decouple digits and balance per-digit information; (2) training with On-policy Coherent Noising (OCN) that prioritizes uncertain digits via coherent masking to concentrate supervision on high-value signals; and (3) inference with Confidence-guided Parallel Denoising (CPD) that fills higher-confidence digits first and generates diverse Top-K candidates. Experiments show consistent gains over strong generative and discriminative recommendation baselines on multiple datasets, improving NDCG@10 by 6.9%-15.5%. Code is available at https://github.com/liuzhao09/DiffGRM.

Chi Liu, Jiangxia Cao, Rui Huang et al.

In large-scale content recommendation systems, retrieval serves as the initial stage in the pipeline, responsible for selecting thousands of candidate items from billions of options to pass on to ranking modules. Traditionally, the dominant retrieval method has been Embedding-Based Retrieval (EBR) using a Deep Neural Network (DNN) dual-tower structure. However, applying transformer in retrieval tasks has been the focus of recent research, though real-world industrial deployment still presents significant challenges. In this paper, we introduce KuaiFormer, a novel transformer-based retrieval framework deployed in a large-scale content recommendation system. KuaiFormer fundamentally redefines the retrieval process by shifting from conventional score estimation tasks (such as click-through rate estimate) to a transformer-driven Next Action Prediction paradigm. This shift enables more effective real-time interest acquisition and multi-interest extraction, significantly enhancing retrieval performance. KuaiFormer has been successfully integrated into Kuaishou App's short-video recommendation system since May 2024, serving over 400 million daily active users and resulting in a marked increase in average daily usage time of Kuaishou users. We provide insights into both the technical and business aspects of deploying transformer in large-scale recommendation systems, addressing practical challenges encountered during industrial implementation. Our findings offer valuable guidance for engineers and researchers aiming to leverage transformer models to optimize large-scale content recommendation systems.

Zhipeng Wei, Kuo Cai, Junda She et al.

Local life service is a vital scenario in Kuaishou App, where video recommendation is intrinsically linked with store's location information. Thus, recommendation in our scenario is challenging because we should take into account user's interest and real-time location at the same time. In the face of such complex scenarios, end-to-end generative recommendation has emerged as a new paradigm, such as OneRec in the short video scenario, OneSug in the search scenario, and EGA in the advertising scenario. However, in local life service, an end-to-end generative recommendation model has not yet been developed as there are some key challenges to be solved. The first challenge is how to make full use of geographic information. The second challenge is how to balance multiple objectives, including user interests, the distance between user and stores, and some other business objectives. To address the challenges, we propose OneLoc. Specifically, we leverage geographic information from different perspectives: (1) geo-aware semantic ID incorporates both video and geographic information for tokenization, (2) geo-aware self-attention in the encoder leverages both video location similarity and user's real-time location, and (3) neighbor-aware prompt captures rich context information surrounding users for generation. To balance multiple objectives, we use reinforcement learning and propose two reward functions, i.e., geographic reward and GMV reward. With the above design, OneLoc achieves outstanding offline and online performance. In fact, OneLoc has been deployed in local life service of Kuaishou App. It serves 400 million active users daily, achieving 21.016% and 17.891% improvements in terms of gross merchandise value (GMV) and orders numbers.

Zihan Wang, Jiaze Chen, Zhicheng Liu et al.

Competitive programming has emerged as a critical benchmark for evaluating the reasoning and coding capabilities of Large Language Models (LLMs). Despite impressive progress on existing benchmarks, we argue that current evaluations overstate model proficiency, masking a substantial gap between LLMs and elite human programmers. This gap arises from two key limitations: insufficient difficulty and scope of benchmark problems, and evaluation bias from low-quality test cases. To address these shortcomings, we present AetherCode, a new benchmark that draws problems from premier programming competitions such as IOI and ICPC, offering broader coverage and higher difficulty. AetherCode further incorporates comprehensive, expert-validated test suites built through a hybrid of automated generation and human curation, ensuring rigorous and reliable assessment. By combining challenging problem design with robust evaluation, AetherCode provides a more faithful measure of LLM capabilities and sets a new standard for future research in code reasoning.

Chengcheng Guo, Junda She, Kuo Cai et al.

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.

Chi Liu, Jiangxia Cao, Rui Huang et al.

Recommendation systems (RecSys) are designed to connect users with relevant items from a vast pool of candidates while aligning with the business goals of the platform. A typical industrial RecSys is composed of two main stages, retrieval and ranking: (1) the retrieval stage aims at searching hundreds of item candidates satisfied user interests; (2) based on the retrieved items, the ranking stage aims at selecting the best dozen items by multiple targets estimation for each item candidate, including classification and regression targets. Compared with ranking model, the retrieval model absence of item candidate information during inference, therefore retrieval models are often trained by classification target only (e.g., click-through rate), but failed to incorporate regression target (e.g., the expected watch-time), which limit the effectiveness of retrieval. In this paper, we propose the Controllable Retrieval Model (CRM), which integrates regression information as conditional features into the two-tower retrieval paradigm. This modification enables the retrieval stage could fulfill the target gap with ranking model, enhancing the retrieval model ability to search item candidates satisfied the user interests and condition effectively. We validate the effectiveness of CRM through real-world A/B testing and demonstrate its successful deployment in Kuaishou short-video recommendation system, which serves over 400 million users.

Ningyu Xu, Qi Zhang, Chao Du et al.

People acquire concepts through rich physical and social experiences and use them to understand and navigate the world. In contrast, large language models (LLMs), trained solely through next-token prediction on text, exhibit strikingly human-like behaviors. Are these models developing concepts akin to those of humans? If so, how are such concepts represented, organized, and related to behavior? Here, we address these questions by investigating the representations formed by LLMs during an in-context concept inference task. We found that LLMs can flexibly derive concepts from linguistic descriptions in relation to contextual cues about other concepts. The derived representations converge toward a shared, context-independent structure, and alignment with this structure reliably predicts model performance across various understanding and reasoning tasks. Moreover, the convergent representations effectively capture human behavioral judgments and closely align with neural activity patterns in the human brain, providing evidence for biological plausibility. Together, these findings establish that structured, human-like conceptual representations can emerge purely from language prediction without real-world grounding, highlighting the role of conceptual structure in understanding intelligent behavior. More broadly, our work suggests that LLMs offer a tangible window into the nature of human concepts and lays the groundwork for advancing alignment between artificial and human intelligence.

Yijia Sun, Shanshan Huang, Linxiao Che et al.

Modern industrial recommendation systems encounter a core challenge of multi-stage optimization misalignment: a significant semantic gap exists between the multi-objective optimization paradigm widely used in the ranking phase and the single-objective modeling in the retrieve phase. Although the mainstream industry solution achieves multi-objective coverage through parallel multi-path single-objective retrieval, this approach leads to linear growth of training and serving resources with the number of objectives and has inherent limitations in handling loosely coupled objectives. This paper proposes the MPFormer, a dynamic multi-task Transformer framework, which systematically addresses the aforementioned issues through three innovative mechanisms. First, an objective-conditioned transformer that jointly encodes user behavior sequences and multi-task semantics through learnable attention modulation; second, personalized target weights are introduced to achieve dynamic adjustment of retrieval results; finally, user personalization information is incorporated into token representations and the Transformer structure to further enhance the model's representation ability. This framework has been successfully integrated into Kuaishou short video recommendation system, stably serving over 400 million daily active users. It significantly improves user daily engagement and system operational efficiency. Practical deployment verification shows that, compared with traditional solutions, it effectively optimizes the iterative paradigm of multi-objective retrieval while maintaining service response speed, providing a scalable multi-objective solution for industrial recommendation systems.

Chuanyin Wang, Yifei Zhang, Neng Gao et al.

Personalized federated learning is extensively utilized in scenarios characterized by data heterogeneity, facilitating more efficient and automated local training on data-owning terminals. This includes the automated selection of high-performance model parameters for upload, thereby enhancing the overall training process. However, it entails significant risks of privacy leakage. Existing studies have attempted to mitigate these risks by utilizing differential privacy. Nevertheless, these studies present two major limitations: (1) The integration of differential privacy into personalized federated learning lacks sufficient personalization, leading to the introduction of excessive noise into the model. (2) It fails to adequately control the spatial scope of model update information, resulting in a suboptimal balance between data privacy and model effectiveness in differential privacy federated learning. In this paper, we propose a differentially private personalized federated learning approach that employs dynamically sparsified client updates through reparameterization and adaptive norm(DP-pFedDSU). Reparameterization training effectively selects personalized client update information, thereby reducing the quantity of updates. This approach minimizes the introduction of noise to the greatest extent possible. Additionally, dynamic adaptive norm refers to controlling the norm space of model updates during the training process, mitigating the negative impact of clipping on the update information. These strategies substantially enhance the effective integration of differential privacy and personalized federated learning. Experimental results on EMNIST, CIFAR-10, and CIFAR-100 demonstrate that our proposed scheme achieves superior performance and is well-suited for more complex personalized federated learning scenarios.

Yule Wang, Qiang Luo, Yue Ding et al.

In this paper, we propose a novel model named DemiNet (short for DEpendency-Aware Multi-Interest Network) to address the above two issues. To be specific, we first consider various dependency types between item nodes and perform dependency-aware heterogeneous attention for denoising and obtaining accurate sequence item representations. Secondly, for multiple interests extraction, multi-head attention is conducted on top of the graph embedding. To filter out noisy inter-item correlations and enhance the robustness of extracted interests, self-supervised interest learning is introduced to the above two steps. Thirdly, to aggregate the multiple interests, interest experts corresponding to different interest routes give rating scores respectively, while a specialized network assigns the confidence of each score. Experimental results on three real-world datasets demonstrate that the proposed DemiNet significantly improves the overall recommendation performance over several state-of-the-art baselines. Further studies verify the efficacy and interpretability benefits brought by the fine-grained user interest modeling.

Xiang-Rong Sheng, Liqin Zhao, Guorui Zhou et al.

Traditional industrial recommenders are usually trained on a single business domain and then serve for this domain. However, in large commercial platforms, it is often the case that the recommenders need to make click-through rate (CTR) predictions for multiple business domains. Different domains have overlapping user groups and items. Thus, there exist commonalities. Since the specific user groups have disparity and the user behaviors may change in various business domains, there also have distinctions. The distinctions result in domain-specific data distributions, making it hard for a single shared model to work well on all domains. To learn an effective and efficient CTR model to handle multiple domains simultaneously, we present Star Topology Adaptive Recommender (STAR). Concretely, STAR has the star topology, which consists of the shared centered parameters and domain-specific parameters. The shared parameters are applied to learn commonalities of all domains, and the domain-specific parameters capture domain distinction for more refined prediction. Given requests from different business domains, STAR can adapt its parameters conditioned on the domain characteristics. The experimental result from production data validates the superiority of the proposed STAR model. Since 2020, STAR has been deployed in the display advertising system of Alibaba, obtaining averaging 8.0% improvement on CTR and 6.0% on RPM (Revenue Per Mille).