Zhaojie Liu

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.

Yunheng Li, Hangyi Kuang, Hengrui Zhang et al.

Multimodal Chain-of-Thought (CoT) reasoning requires large vision-language models to construct reasoning trajectories that interleave perceptual grounding with multi-step inference. However, existing Reinforcement Learning with Verifiable Rewards (RLVR) methods typically optimize reasoning at a coarse granularity, treating CoT uniformly without distinguishing their varying degrees of visual grounding. In this work, we conduct a token-level analysis of multimodal reasoning trajectories and show that successful reasoning is characterized by structured token dynamics reflecting both perceptual grounding and exploratory inference. Building upon this analysis, we propose Perception-Exploration Policy Optimization (PEPO), which derives a perception prior from hidden state similarity and integrates it with token entropy through a smooth gating mechanism to produce token-level advantages. PEPO integrates seamlessly with existing RLVR frameworks such as GRPO and DAPO, requiring neither additional supervision nor auxiliary branches. Extensive experiments across diverse multimodal benchmarks demonstrate consistent and robust improvements over strong RL baselines, spanning geometry reasoning, visual grounding, visual puzzle solving, and few-shot classification, while maintaining stable training dynamics. Code: https://github.com/xzxxntxdy/PEPO

Mingming Ha, Guanchen Wang, Linxun Chen et al.

In recent years, the scaling laws of recommendation models have attracted increasing attention, which govern the relationship between performance and parameters/FLOPs of recommenders. Currently, there are three mainstream architectures for achieving scaling in recommendation models, namely attention-based, TokenMixer-based, and factorization-machine-based methods, which exhibit fundamental differences in both design philosophy and architectural structure. In this paper, we propose a unified scaling architecture for recommendation systems, namely \textbf{UniMixer}, to improve scaling efficiency and establish a unified theoretical framework that unifies the mainstream scaling blocks. By transforming the rule-based TokenMixer to an equivalent parameterized structure, we construct a generalized parameterized feature mixing module that allows the token mixing patterns to be optimized and learned during model training. Meanwhile, the generalized parameterized token mixing removes the constraint in TokenMixer that requires the number of heads to be equal to the number of tokens. Furthermore, we establish a unified scaling module design framework for recommender systems, which bridges the connections among attention-based, TokenMixer-based, and factorization-machine-based methods. To further boost scaling ROI, a lightweight UniMixing module is designed, \textbf{UniMixing-Lite}, which further compresses the model parameters and computational cost while significantly improve the model performance. The scaling curves are shown in the following figure. Extensive offline and online experiments are conducted to verify the superior scaling abilities of \textbf{UniMixer}.

Ruochen Yang, Xiaodong Li, Jiawei Sheng et al.

Multi-behavior sequential recommendation (MBSR) aims to learn the dynamic and heterogeneous interactions of users' multi-behavior sequences, so as to capture user preferences under target behavior for the next interacted item prediction. Unlike previous methods that adopt unidirectional modeling by mapping auxiliary behaviors to target behavior, recent concerns are shifting from behavior-fixed to behavior-specific recommendation. However, these methods still ignore the user's latent preference that underlying decision-making, leading to suboptimal solutions. Meanwhile, due to the asymmetric deterministic between items and behaviors, discriminative paradigm based on preference scoring is unsuitable to capture the uncertainty from low-entropy behaviors to high-entropy items, failing to provide efficient and diverse recommendation. To address these challenges, we propose \textbf{FatsMB}, a framework based diffusion model that guides preference generation \textit{\textbf{F}rom Behavior-\textbf{A}gnostic \textbf{T}o Behavior-\textbf{S}pecific} in latent spaces, enabling diverse and accurate \textit{\textbf{M}ulti-\textbf{B}ehavior Sequential Recommendation}. Specifically, we design a Multi-Behavior AutoEncoder (MBAE) to construct a unified user latent preference space, facilitating interaction and collaboration across Behaviors, within Behavior-aware RoPE (BaRoPE) employed for multiple information fusion. Subsequently, we conduct target behavior-specific preference transfer in the latent space, enriching with informative priors. A Multi-Condition Guided Layer Normalization (MCGLN) is introduced for the denoising. Extensive experiments on real-world datasets demonstrate the effectiveness of our model.

Yusheng Huang, Shuang Yang, Zhaojie Liu et al.

Generative recommendation (GR) has emerged as a widely adopted paradigm in industrial sequential recommendation. Current GR systems follow a similar pipeline: tokenization for item indexing, next-token prediction as the training objective and auto-regressive decoding for next-item generation. However, existing GR research mainly focuses on architecture design and empirical performance optimization, with few rigorous theoretical explanations for the working mechanism of auto-regressive next-token prediction in recommendation scenarios. In this work, we formally prove that \textbf{the k-token auto-regressive next-token prediction (AR-NTP) paradigm is strictly mathematically equivalent to full-item-vocabulary maximum likelihood estimation (FV-MLE)}, under the core premise of a bijective mapping between items and their corresponding k-token sequences. We further show that this equivalence holds for both cascaded and parallel tokenizations, the two most widely used schemes in industrial GR systems. Our result provides the first formal theoretical foundation for the dominant industrial GR paradigm, and offers principled guidance for future GR system optimization.

Hongwei Zhang, Qiqiang Zhong, Jiangxia Cao et al.

Modeling ultra-long user sequences involves a difficult trade-off between efficiency and effectiveness. While current paradigms rely on either item-specific search or item-agnostic compression, we propose UxSID, a framework exploring a third path: semantic-group shared interest memory. By utilizing Semantic IDs (SIDs) and a dual-level attention strategy, UxSID captures target-aware preferences without the heavy cost of item-specific models. This end-to-end architecture balances computational parsimony with semantic awareness, achieving state-of-the-art performance and a 0.337% revenue lift in large-scale advertising A/B test.

Xinchen Luo, Jiangxia Cao, Tianyu Sun et al.

In recent years, with the significant evolution of multi-modal large models, many recommender researchers realized the potential of multi-modal information for user interest modeling. In industry, a wide-used modeling architecture is a cascading paradigm: (1) first pre-training a multi-modal model to provide omnipotent representations for downstream services; (2) The downstream recommendation model takes the multi-modal representation as additional input to fit real user-item behaviours. Although such paradigm achieves remarkable improvements, however, there still exist two problems that limit model performance: (1) Representation Unmatching: The pre-trained multi-modal model is always supervised by the classic NLP/CV tasks, while the recommendation models are supervised by real user-item interaction. As a result, the two fundamentally different tasks' goals were relatively separate, and there was a lack of consistent objective on their representations; (2) Representation Unlearning: The generated multi-modal representations are always stored in cache store and serve as extra fixed input of recommendation model, thus could not be updated by recommendation model gradient, further unfriendly for downstream training. Inspired by the two difficulties challenges in downstream tasks usage, we introduce a quantitative multi-modal framework to customize the specialized and trainable multi-modal information for different downstream models.

Tianbao Ma, Ruochen Yang, Chengen Li et al.

User retention is a key metric to measure long-term engagement in modern platforms. In real-time bidding (RTB) advertising system for user re-engagement, the retention model is required to predict future revisit probability at bidding time, before the user converts and consumes any content. Although post-conversion content, termed Onboarding Content, provides highly informative signals for retention prediction, directly using it in training causes severe feature leakage and creates a gap between training and serving. To address this issue, we propose OCARM, a two-stage distillation-aligned framework for Onboarding Content Augmented Retention Modeling, enabling the model to implicitly capture future content using only observable features during inference. In the first stage, we deliberately expose onboarding content to train a hierarchical encoder that produces teacher representations. In the second stage, a user encoder is aligned with the frozen teacher through distillation, allowing the model to approximate the inaccessible onboarding signals without leakage. Extensive offline experiments and online A/B tests demonstrate that our framework achieves consistent improvements in a real-world growth scenario.

Guanchen Wang, Mingming Ha, Tianbao Ma et al.

In recent years, there has been growing interest in leveraging the impressive generalization capabilities and reasoning ability of large language models (LLMs) to improve the performance of recommenders. With this operation, recommenders can access and learn the additional world knowledge and reasoning information via LLMs. However, in general, for different users and items, the world knowledge derived from LLMs suffers from issues of hallucination, content redundant, and information homogenization. Directly feeding the generated response embeddings into the recommendation model can lead to unavoidable performance deterioration. To address these challenges, we propose a Knowledge Selection \& Exploitation Recommendation (KSER) framework, which effectively select and extracts the high-quality knowledge from LLMs. The framework consists of two key components: a knowledge filtering module and a embedding spaces alignment module. In the knowledge filtering module, a Embedding Selection Filter Network (ESFNet) is designed to assign adaptive weights to different knowledge chunks in different knowledge fields. In the space alignment module, an attention-based architecture is proposed to align the semantic embeddings from LLMs with the feature space used to train the recommendation models. In addition, two training strategies--\textbf{all-parameters training} and \textbf{extractor-only training}--are proposed to flexibly adapt to different downstream tasks and application scenarios, where the extractor-only training strategy offers a novel perspective on knowledge-augmented recommendation. Experimental results validate the necessity and effectiveness of both the knowledge filtering and alignment modules, and further demonstrate the efficiency and effectiveness of the extractor-only training strategy.

Wentao Ouyang, Xiuwu Zhang, Shukui Ren et al.

Click-through rate (CTR) prediction is one of the most central tasks in online advertising systems. Recent deep learning-based models that exploit feature embedding and high-order data nonlinearity have shown dramatic successes in CTR prediction. However, these models work poorly on cold-start ads with new IDs, whose embeddings are not well learned yet. In this paper, we propose Graph Meta Embedding (GME) models that can rapidly learn how to generate desirable initial embeddings for new ad IDs based on graph neural networks and meta learning. Previous works address this problem from the new ad itself, but ignore possibly useful information contained in existing old ads. In contrast, GMEs simultaneously consider two information sources: the new ad and existing old ads. For the new ad, GMEs exploit its associated attributes. For existing old ads, GMEs first build a graph to connect them with new ads, and then adaptively distill useful information. We propose three specific GMEs from different perspectives to explore what kind of information to use and how to distill information. In particular, GME-P uses Pre-trained neighbor ID embeddings, GME-G uses Generated neighbor ID embeddings and GME-A uses neighbor Attributes. Experimental results on three real-world datasets show that GMEs can significantly improve the prediction performance in both cold-start (i.e., no training data is available) and warm-up (i.e., a small number of training samples are collected) scenarios over five major deep learning-based CTR prediction models. GMEs can be applied to conversion rate (CVR) prediction as well.

Wentao Ouyang, Xiuwu Zhang, Lei Zhao et al.

Click-through rate (CTR) prediction is a critical task in online advertising systems. Existing works mainly address the single-domain CTR prediction problem and model aspects such as feature interaction, user behavior history and contextual information. Nevertheless, ads are usually displayed with natural content, which offers an opportunity for cross-domain CTR prediction. In this paper, we address this problem and leverage auxiliary data from a source domain to improve the CTR prediction performance of a target domain. Our study is based on UC Toutiao (a news feed service integrated with the UC Browser App, serving hundreds of millions of users daily), where the source domain is the news and the target domain is the ad. In order to effectively leverage news data for predicting CTRs of ads, we propose the Mixed Interest Network (MiNet) which jointly models three types of user interest: 1) long-term interest across domains, 2) short-term interest from the source domain and 3) short-term interest in the target domain. MiNet contains two levels of attentions, where the item-level attention can adaptively distill useful information from clicked news / ads and the interest-level attention can adaptively fuse different interest representations. Offline experiments show that MiNet outperforms several state-of-the-art methods for CTR prediction. We have deployed MiNet in UC Toutiao and the A/B test results show that the online CTR is also improved substantially. MiNet now serves the main ad traffic in UC Toutiao.

Wentao Ouyang, Xiuwu Zhang, Shukui Ren et al.

Click-through rate (CTR) prediction is a critical task in online advertising systems. Models like Deep Neural Networks (DNNs) are simple but stateless. They consider each target ad independently and cannot directly extract useful information contained in users' historical ad impressions and clicks. In contrast, models like Recurrent Neural Networks (RNNs) are stateful but complex. They model temporal dependency between users' sequential behaviors and can achieve improved prediction performance than DNNs. However, both the offline training and online prediction process of RNNs are much more complex and time-consuming. In this paper, we propose Memory Augmented DNN (MA-DNN) for practical CTR prediction services. In particular, we create two external memory vectors for each user, memorizing high-level abstractions of what a user possibly likes and dislikes. The proposed MA-DNN achieves a good compromise between DNN and RNN. It is as simple as DNN, but has certain ability to exploit useful information contained in users' historical behaviors as RNN. Both offline and online experiments demonstrate the effectiveness of MA-DNN for practical CTR prediction services. Actually, the memory component can be augmented to other models as well (e.g., the Wide&Deep model).

Wentao Ouyang, Xiuwu Zhang, Shukui Ren et al.

Click-through rate (CTR) prediction is a critical task in online advertising systems. Most existing methods mainly model the feature-CTR relationship and suffer from the data sparsity issue. In this paper, we propose DeepMCP, which models other types of relationships in order to learn more informative and statistically reliable feature representations, and in consequence to improve the performance of CTR prediction. In particular, DeepMCP contains three parts: a matching subnet, a correlation subnet and a prediction subnet. These subnets model the user-ad, ad-ad and feature-CTR relationship respectively. When these subnets are jointly optimized under the supervision of the target labels, the learned feature representations have both good prediction powers and good representation abilities. Experiments on two large-scale datasets demonstrate that DeepMCP outperforms several state-of-the-art models for CTR prediction.

Wentao Ouyang, Xiuwu Zhang, Li Li et al.

Click-through rate (CTR) prediction is a critical task in online advertising systems. A large body of research considers each ad independently, but ignores its relationship to other ads that may impact the CTR. In this paper, we investigate various types of auxiliary ads for improving the CTR prediction of the target ad. In particular, we explore auxiliary ads from two viewpoints: one is from the spatial domain, where we consider the contextual ads shown above the target ad on the same page; the other is from the temporal domain, where we consider historically clicked and unclicked ads of the user. The intuitions are that ads shown together may influence each other, clicked ads reflect a user's preferences, and unclicked ads may indicate what a user dislikes to certain extent. In order to effectively utilize these auxiliary data, we propose the Deep Spatio-Temporal neural Networks (DSTNs) for CTR prediction. Our model is able to learn the interactions between each type of auxiliary data and the target ad, to emphasize more important hidden information, and to fuse heterogeneous data in a unified framework. Offline experiments on one public dataset and two industrial datasets show that DSTNs outperform several state-of-the-art methods for CTR prediction. We have deployed the best-performing DSTN in Shenma Search, which is the second largest search engine in China. The A/B test results show that the online CTR is also significantly improved compared to our last serving model.