Yuekui Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yuekui Yang has a total of 92 co-authors. Here are the top co-authors by number of shared publications:
- Shaoping Ma
Department of Computer Science and Technology Tsinghua University
7 shared publications Haiyang Wu
6 shared publications- Haiyang Wu
Tencent Inc., Beijing, China
4 shared publications - Deyi Ji3 shared publications
- Tianrun Chen
Zhejiang University, Hangzhou, China
3 shared publications - Yang Zhang
Machine Learning Platform Department, Tencent TEG
3 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8310-8318
LFM4Ads: Large Foundation Model for Ads Recommendation
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8310-8318
Open AccessLFM4Ads: Large Foundation Model for Ads Recommendation
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1641-1653
UniTraj: Cross-Domain Long-Sequence Modeling for Commercial Recommendation
Long-sequence modeling is increasingly important in recommender systems for capturing users’ evolving and long-term interests. In advertising, however, user interaction histories are often highly sparse due to limited exposure opportunities, making ad-only behavior sequences insufficient for effective long-sequence recommendation. To address this limitation, we propose UniTraj, a practical framework that extends sequence construction beyond the advertising domain by incorporating behaviors from content-consumption scenarios, forming unified commercial trajectories across domains and scenarios. Such unified trajectories provide richer behavioral context, but also introduce substantial heterogeneity in feature taxonomy, behavioral semantics, and optimization targets. In particular, they raise three key challenges: interference among fields from different domains and scenarios, target-specific conflicts in temporal and semantic patterns, and complex high-order dependencies across heterogeneous behavioral signals. To tackle these challenges, UniTraj adopts a two-stage design. In the first stage, it combines hierarchical hard search with a decoupled embedding-based soft search module to retrieve relevant behaviors under complex feature hierarchies while reducing conflicts between retrieval and representation learning. In the second stage, it introduces several decoupled sequence modeling components, including Decoupled Side Information Temporal Interest Networks for mitigating cross-field interference, target-decoupled positional encoding and target-decoupled SASRec for capturing target-aware temporal dynamics, and Deep TIN for modeling high-order behavioral correlations. We deploy UniTraj in a large-scale online advertising system and observe consistent improvements in online business metrics across multiple commercial scenarios. The results demonstrate the effectiveness of unified cross-domain behavior modeling for long-sequence recommendation in sparse advertising environments.
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1641-1653
Open AccessUniTraj: Cross-Domain Long-Sequence Modeling for Commercial Recommendation
Long-sequence modeling is increasingly important in recommender systems for capturing users’ evolving and long-term interests. In advertising, however, user interaction histories are often highly sparse due to limited exposure opportunities, making ad-only behavior sequences insufficient for effective long-sequence recommendation. To address this limitation, we propose UniTraj, a practical framework that extends sequence construction beyond the advertising domain by incorporating behaviors from content-consumption scenarios, forming unified commercial trajectories across domains and scenarios. Such unified trajectories provide richer behavioral context, but also introduce substantial heterogeneity in feature taxonomy, behavioral semantics, and optimization targets. In particular, they raise three key challenges: interference among fields from different domains and scenarios, target-specific conflicts in temporal and semantic patterns, and complex high-order dependencies across heterogeneous behavioral signals. To tackle these challenges, UniTraj adopts a two-stage design. In the first stage, it combines hierarchical hard search with a decoupled embedding-based soft search module to retrieve relevant behaviors under complex feature hierarchies while reducing conflicts between retrieval and representation learning. In the second stage, it introduces several decoupled sequence modeling components, including Decoupled Side Information Temporal Interest Networks for mitigating cross-field interference, target-decoupled positional encoding and target-decoupled SASRec for capturing target-aware temporal dynamics, and Deep TIN for modeling high-order behavioral correlations. We deploy UniTraj in a large-scale online advertising system and observe consistent improvements in online business metrics across multiple commercial scenarios. The results demonstrate the effectiveness of unified cross-domain behavior modeling for long-sequence recommendation in sparse advertising environments.
- Open Access
Efficient Cross-Architecture Knowledge Transfer for Large-Scale Online User Response Prediction
Deploying new architectures in large-scale user response prediction systems incurs high model switching costs due to expensive retraining on massive historical data and performance degradation under data retention constraints. Existing knowledge distillation methods struggle with architectural heterogeneity and the prohibitive cost of transferring large embedding tables. We propose CrossAdapt, a two-stage framework for efficient cross-architecture knowledge transfer. The offline stage enables rapid embedding transfer via dimension-adaptive projections without iterative training, combined with progressive network distillation and strategic sampling to reduce computational cost. The online stage introduces asymmetric co-distillation, where students update frequently while teachers update infrequently, together with a distribution-aware adaptation mechanism that dynamically balances historical knowledge preservation and fast adaptation to evolving data. Experiments on three public datasets show that CrossAdapt achieves 0.27-0.43% AUC improvements while reducing training time by 43-71%. Large-scale deployment on Tencent WeChat Channels (~10M daily samples) further demonstrates its effectiveness, significantly mitigating AUC degradation, LogLoss increase, and prediction bias compared to standard distillation baselines.
Open AccessEfficient Cross-Architecture Knowledge Transfer for Large-Scale Online User Response Prediction
Deploying new architectures in large-scale user response prediction systems incurs high model switching costs due to expensive retraining on massive historical data and performance degradation under data retention constraints. Existing knowledge distillation methods struggle with architectural heterogeneity and the prohibitive cost of transferring large embedding tables. We propose CrossAdapt, a two-stage framework for efficient cross-architecture knowledge transfer. The offline stage enables rapid embedding transfer via dimension-adaptive projections without iterative training, combined with progressive network distillation and strategic sampling to reduce computational cost. The online stage introduces asymmetric co-distillation, where students update frequently while teachers update infrequently, together with a distribution-aware adaptation mechanism that dynamically balances historical knowledge preservation and fast adaptation to evolving data. Experiments on three public datasets show that CrossAdapt achieves 0.27-0.43% AUC improvements while reducing training time by 43-71%. Large-scale deployment on Tencent WeChat Channels (~10M daily samples) further demonstrates its effectiveness, significantly mitigating AUC degradation, LogLoss increase, and prediction bias compared to standard distillation baselines.
- Open Access
RAVEN++: Pinpointing Fine-Grained Violations in Advertisement Videos with Active Reinforcement Reasoning
Advertising (Ad) is a cornerstone of the digital economy, yet the moderation of video advertisements remains a significant challenge due to their complexity and the need for precise violation localization. While recent advancements, such as the RAVEN model, have improved coarse-grained violation detection, critical gaps persist in fine-grained understanding, explainability, and generalization. To address these limitations, we propose RAVEN++, a novel framework that introduces three key innovations: 1) Active Reinforcement Learning (RL), which dynamically adapts training to samples of varying difficulty; 2) Fine-Grained Violation Understanding, achieved through hierarchical reward functions and reasoning distillation; and 3) Progressive Multi-Stage Training, which systematically combines knowledge injection, curriculum-based passive RL, and active RL. Extensive experiments on both public and proprietary datasets, on both offline scenarios and online deployed A/B Testing, demonstrate that RAVEN++ outperforms general-purpose LLMs and specialized models like RAVEN in terms of fine-grained violation understanding, reasoning capabilities, and generalization ability.
Open AccessRAVEN++: Pinpointing Fine-Grained Violations in Advertisement Videos with Active Reinforcement Reasoning
Advertising (Ad) is a cornerstone of the digital economy, yet the moderation of video advertisements remains a significant challenge due to their complexity and the need for precise violation localization. While recent advancements, such as the RAVEN model, have improved coarse-grained violation detection, critical gaps persist in fine-grained understanding, explainability, and generalization. To address these limitations, we propose RAVEN++, a novel framework that introduces three key innovations: 1) Active Reinforcement Learning (RL), which dynamically adapts training to samples of varying difficulty; 2) Fine-Grained Violation Understanding, achieved through hierarchical reward functions and reasoning distillation; and 3) Progressive Multi-Stage Training, which systematically combines knowledge injection, curriculum-based passive RL, and active RL. Extensive experiments on both public and proprietary datasets, on both offline scenarios and online deployed A/B Testing, demonstrate that RAVEN++ outperforms general-purpose LLMs and specialized models like RAVEN in terms of fine-grained violation understanding, reasoning capabilities, and generalization ability.
- Open Access
RAVEN: Robust Advertisement Video Violation Temporal Grounding via Reinforcement Reasoning
Advertisement (Ad) video violation detection is critical for ensuring platform compliance, but existing methods struggle with precise temporal grounding, noisy annotations, and limited generalization. We propose RAVEN, a novel framework that integrates curriculum reinforcement learning with multimodal large language models (MLLMs) to enhance reasoning and cognitive capabilities for violation detection. RAVEN employs a progressive training strategy, combining precisely and coarsely annotated data, and leverages Group Relative Policy Optimization (GRPO) to develop emergent reasoning abilities without explicit reasoning annotations. Multiple hierarchical sophisticated reward mechanism ensures precise temporal grounding and consistent category prediction. Experiments on industrial datasets and public benchmarks show that RAVEN achieves superior performances in violation category accuracy and temporal interval localization. We also design a pipeline to deploy the RAVEN on the online Ad services, and online A/B testing further validates its practical applicability, with significant improvements in precision and recall. RAVEN also demonstrates strong generalization, mitigating the catastrophic forgetting issue associated with supervised fine-tuning.
Open AccessRAVEN: Robust Advertisement Video Violation Temporal Grounding via Reinforcement Reasoning
Advertisement (Ad) video violation detection is critical for ensuring platform compliance, but existing methods struggle with precise temporal grounding, noisy annotations, and limited generalization. We propose RAVEN, a novel framework that integrates curriculum reinforcement learning with multimodal large language models (MLLMs) to enhance reasoning and cognitive capabilities for violation detection. RAVEN employs a progressive training strategy, combining precisely and coarsely annotated data, and leverages Group Relative Policy Optimization (GRPO) to develop emergent reasoning abilities without explicit reasoning annotations. Multiple hierarchical sophisticated reward mechanism ensures precise temporal grounding and consistent category prediction. Experiments on industrial datasets and public benchmarks show that RAVEN achieves superior performances in violation category accuracy and temporal interval localization. We also design a pipeline to deploy the RAVEN on the online Ad services, and online A/B testing further validates its practical applicability, with significant improvements in precision and recall. RAVEN also demonstrates strong generalization, mitigating the catastrophic forgetting issue associated with supervised fine-tuning.
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1789-1798
CD-CDR: Conditional Diffusion-based Item Generation for Cross-Domain Recommendation
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1789-1798
Open AccessCD-CDR: Conditional Diffusion-based Item Generation for Cross-Domain Recommendation
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 2076-2084
Explainable Multi-Modality Alignment for Transferable Recommendation
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 2076-2084
Open AccessExplainable Multi-Modality Alignment for Transferable Recommendation
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39  (11) , 11708-11716
Behavior Importance-Aware Graph Neural Architecture Search for Cross-Domain Recommendation
Cross-domain recommendation (CDR) mitigates data sparsity and cold-start issues in recommendation systems. While recent CDR approaches using graph neural networks (GNNs) capture complex user-item interactions, they rely on manually designed architectures that are often suboptimal and labor-intensive. Additionally, extracting valuable behavioral information from source domains to improve target domain recommendations remains challenging. To address these challenges, we propose Behavior importance-aware Graph Neural Architecture Search (BiGNAS), a framework that jointly optimizes GNN architecture and data importance for CDR. BiGNAS introduces two key components: a Cross-Domain Customized Supernetwork and a Graph-Based Behavior Importance Perceptron. The supernetwork, as a one-shot, retrain-free module, automatically searches the optimal GNN architecture for each domain without the need for retraining. The perceptron uses auxiliary learning to dynamically assess the importance of source domain behaviors, thereby improving target domain recommendations. Extensive experiments on benchmark CDR datasets and a large-scale industry advertising dataset demonstrate that BiGNAS consistently outperforms state-of-the-art baselines. To the best of our knowledge, this is the first work to jointly optimize GNN architecture and behavior data importance for cross-domain recommendation.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39  (11) , 11708-11716
Open AccessBehavior Importance-Aware Graph Neural Architecture Search for Cross-Domain Recommendation
Cross-domain recommendation (CDR) mitigates data sparsity and cold-start issues in recommendation systems. While recent CDR approaches using graph neural networks (GNNs) capture complex user-item interactions, they rely on manually designed architectures that are often suboptimal and labor-intensive. Additionally, extracting valuable behavioral information from source domains to improve target domain recommendations remains challenging. To address these challenges, we propose Behavior importance-aware Graph Neural Architecture Search (BiGNAS), a framework that jointly optimizes GNN architecture and data importance for CDR. BiGNAS introduces two key components: a Cross-Domain Customized Supernetwork and a Graph-Based Behavior Importance Perceptron. The supernetwork, as a one-shot, retrain-free module, automatically searches the optimal GNN architecture for each domain without the need for retraining. The perceptron uses auxiliary learning to dynamically assess the importance of source domain behaviors, thereby improving target domain recommendations. Extensive experiments on benchmark CDR datasets and a large-scale industry advertising dataset demonstrate that BiGNAS consistently outperforms state-of-the-art baselines. To the best of our knowledge, this is the first work to jointly optimize GNN architecture and behavior data importance for cross-domain recommendation.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 1-10
RAVEN++: Pinpointing Fine-Grained Violations in Advertisement Videos with Active Reinforcement Reasoning
Deyi Ji, Yuekui Yang, Liqun Liu, Peng Shu, Haiyang Wu, Shaogang Tang, Xudong Chen, Shaoping Ma, Tianrun Chen, Lanyun Zhu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 1-10
Open AccessRAVEN++: Pinpointing Fine-Grained Violations in Advertisement Videos with Active Reinforcement Reasoning
Deyi Ji, Yuekui Yang, Liqun Liu, Peng Shu, Haiyang Wu, Shaogang Tang, Xudong Chen, Shaoping Ma, Tianrun Chen, Lanyun Zhu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track. 2025.
- Open Access
AdaS&S: a One-Shot Supernet Approach for Automatic Embedding Size Search in Deep Recommender System
Deep Learning Recommendation Model(DLRM)s utilize the embedding layer to represent various categorical features. Traditional DLRMs adopt unified embedding size for all features, leading to suboptimal performance and redundant parameters. Thus, lots of Automatic Embedding size Search (AES) works focus on obtaining mixed embedding sizes with strong model performance. However, previous AES works can hardly address several challenges together: (1) The search results of embedding sizes are unstable; (2) Recommendation effect with AES results is unsatisfactory; (3) Memory cost of embeddings is uncontrollable. To address these challenges, we propose a novel one-shot AES framework called AdaS&S, in which a supernet encompassing various candidate embeddings is built and AES is performed as searching network architectures within it. Our framework contains two main stages: In the first stage, we decouple training parameters from searching embedding sizes, and propose the Adaptive Sampling method to yield a well-trained supernet, which further helps to produce stable AES results. In the second stage, to obtain embedding sizes that benefits the model effect, we design a reinforcement learning search process which utilizes the supernet trained previously. Meanwhile, to adapt searching to specific resource constraint, we introduce the resource competition penalty to balance the model effectiveness and memory cost of embeddings. We conduct extensive experiments on public datasets to show the superiority of AdaS&S. Our method could improve AUC by about 0.3% while saving about 20% of model parameters. Empirical analysis also shows that the stability of searching results in AdaS&S significantly exceeds other methods.
Open AccessAdaS&S: a One-Shot Supernet Approach for Automatic Embedding Size Search in Deep Recommender System
Deep Learning Recommendation Model(DLRM)s utilize the embedding layer to represent various categorical features. Traditional DLRMs adopt unified embedding size for all features, leading to suboptimal performance and redundant parameters. Thus, lots of Automatic Embedding size Search (AES) works focus on obtaining mixed embedding sizes with strong model performance. However, previous AES works can hardly address several challenges together: (1) The search results of embedding sizes are unstable; (2) Recommendation effect with AES results is unsatisfactory; (3) Memory cost of embeddings is uncontrollable. To address these challenges, we propose a novel one-shot AES framework called AdaS&S, in which a supernet encompassing various candidate embeddings is built and AES is performed as searching network architectures within it. Our framework contains two main stages: In the first stage, we decouple training parameters from searching embedding sizes, and propose the Adaptive Sampling method to yield a well-trained supernet, which further helps to produce stable AES results. In the second stage, to obtain embedding sizes that benefits the model effect, we design a reinforcement learning search process which utilizes the supernet trained previously. Meanwhile, to adapt searching to specific resource constraint, we introduce the resource competition penalty to balance the model effectiveness and memory cost of embeddings. We conduct extensive experiments on public datasets to show the superiority of AdaS&S. Our method could improve AUC by about 0.3% while saving about 20% of model parameters. Empirical analysis also shows that the stability of searching results in AdaS&S significantly exceeds other methods.