Quan Lu
Research Subjects
Quan Lu has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Ning Jiang
Mashang Consumer Finance Co., Ltd, Chongqing, China
6 shared publications - Zulong Chen
Alibaba Group, Hangzhou, China
5 shared publications - Wanjie Tao
Mashang Consumer Finance Co., Ltd, Chongqing, China and Nanjing University of Aeronautics and Astronautics, Nanjing, China
4 shared publications - Liangyue Li
Alibaba Group, Hangzhou, China
3 shared publications - Qun Dai
Nanjing University of Aeronautics and Astronautics, Nanjing, China
3 shared publications - Fan Wu
Shanghai Jiao Tong University, Shanghai, China
2 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8531-8538
Beyond End-to-End: A Low-Latency, Retrieval-Augmented Chain-of-Thought for Scalable and Explainable Industrial Recommendation
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8531-8538
Open AccessBeyond End-to-End: A Low-Latency, Retrieval-Augmented Chain-of-Thought for Scalable and Explainable Industrial Recommendation
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7874-7879
FailSafe-RAG: Evidence-State-Aware Generation under Retrieval Failures
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7874-7879
Open AccessFailSafe-RAG: Evidence-State-Aware Generation under Retrieval Failures
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4869-4873
NBA-Net: Next-Behavior-Aware Network for Intent Recommendation
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4869-4873
Open AccessNBA-Net: Next-Behavior-Aware Network for Intent Recommendation
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 8609-8612
Rethinking MoE with Retrieval-Memory Synergy: Towards Efficient Expert Coordination
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 8609-8612
Open AccessRethinking MoE with Retrieval-Memory Synergy: Towards Efficient Expert Coordination
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4464-4473
Referring Expression Instance Retrieval and A Strong End-to-End Baseline
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4464-4473
Open AccessReferring Expression Instance Retrieval and A Strong End-to-End Baseline
- 25 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 2570-2581
PMMTalk$:$ Speech-Driven 3D Facial Animation From Complementary Pseudo Multi-Modal Features
Speech-driven 3D facial animation has improved a lot recently while most related works only utilize acoustic modality and neglect the influence of visual and textual cues, leading to unsatisfactory results in terms of precision and coherence. We argue that visual and textual cues are not trivial information. Therefore, we present a novel framework, namely PMMTalk, using complementary P seudo M ulti- M odal features for improving the accuracy of facial animation. The framework entails three modules: PMMTalk encoder, cross-modal alignment module, and PMMTalk decoder. Specifically, the PMMTalk encoder employs the off-the-shelf talking head generation architecture and speech recognition technology to extract visual and textual information from speech, respectively. Following this, the cross-modal alignment module aligns the audio-image-text features at temporal and semantic levels. Subsequently, the PMMTalk decoder is employed to predict lip-syncing facial blendshape coefficients. Contrary to prior methods, PMMTalk only requires an additional random reference face image but yields more accurate results. Additionally, it is artist-friendly as it seamlessly integrates into standard animation production workflows by introducing facial blendshape coefficients. Finally, given the scarcity of 3D talking face datasets, we introduce a large-scale 3D C hinese A udio- V isual F acial A nimation (3D-CAVFA) dataset. Extensive experiments and user studies show that our approach outperforms the state of the art. Codes and datasets are available at PMMTalk.
- 25 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 2570-2581
PMMTalk$:$ Speech-Driven 3D Facial Animation From Complementary Pseudo Multi-Modal Features
Speech-driven 3D facial animation has improved a lot recently while most related works only utilize acoustic modality and neglect the influence of visual and textual cues, leading to unsatisfactory results in terms of precision and coherence. We argue that visual and textual cues are not trivial information. Therefore, we present a novel framework, namely PMMTalk, using complementary P seudo M ulti- M odal features for improving the accuracy of facial animation. The framework entails three modules: PMMTalk encoder, cross-modal alignment module, and PMMTalk decoder. Specifically, the PMMTalk encoder employs the off-the-shelf talking head generation architecture and speech recognition technology to extract visual and textual information from speech, respectively. Following this, the cross-modal alignment module aligns the audio-image-text features at temporal and semantic levels. Subsequently, the PMMTalk decoder is employed to predict lip-syncing facial blendshape coefficients. Contrary to prior methods, PMMTalk only requires an additional random reference face image but yields more accurate results. Additionally, it is artist-friendly as it seamlessly integrates into standard animation production workflows by introducing facial blendshape coefficients. Finally, given the scarcity of 3D talking face datasets, we introduce a large-scale 3D C hinese A udio- V isual F acial A nimation (3D-CAVFA) dataset. Extensive experiments and user studies show that our approach outperforms the state of the art. Codes and datasets are available at PMMTalk.
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 2085-2094
MERIT: A Merchant Incentive Ranking Model for Hotel Search & Ranking
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 2085-2094
Open AccessMERIT: A Merchant Incentive Ranking Model for Hotel Search & Ranking
- Open Access
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 779-789
LINet: A Location and Intention-Aware Neural Network for Hotel Group Recommendation
Motivated by the collaboration with Fliggy1, a leading Online Travel Platform (OTP), we investigate an important but less explored research topic about optimizing the quality of hotel supply, namely selecting potential profitable hotels in advance to build up adequate room inventory. We formulate a WWW problem, i.e., within a specific time period (When) and potential travel area (Where), which hotels should be recommended to a certain group of users with similar travel intentions (Why). We identify three critical challenges in solving the WWW problem: user groups generation, travel data sparsity and utilization of hotel recommendation information (e.g., period, location and intention). To this end, we propose LINet, a Location and Intention-aware neural Network for hotel group recommendation. Specifically, LINet first identifies user travel intentions for user groups generalization, and then characterizes the group preferences by jointly considering historical user-hotel interaction and spatio-temporal features of hotels. For data sparsity, we develop a graph neural network, which employs long-term data, and further design an auxiliary loss function of location that efficiently exploits data within the same and across different locations. Both offline and online experiments demonstrate the effectiveness of LINet when compared with state-of-the-art methods. LINet has been successfully deployed on Fliggy to retrieve high quality hotels for business development, serving hundreds of hotel operation scenarios and thousands of hotel operators.
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 779-789
Open AccessLINet: A Location and Intention-Aware Neural Network for Hotel Group Recommendation
Motivated by the collaboration with Fliggy1, a leading Online Travel Platform (OTP), we investigate an important but less explored research topic about optimizing the quality of hotel supply, namely selecting potential profitable hotels in advance to build up adequate room inventory. We formulate a WWW problem, i.e., within a specific time period (When) and potential travel area (Where), which hotels should be recommended to a certain group of users with similar travel intentions (Why). We identify three critical challenges in solving the WWW problem: user groups generation, travel data sparsity and utilization of hotel recommendation information (e.g., period, location and intention). To this end, we propose LINet, a Location and Intention-aware neural Network for hotel group recommendation. Specifically, LINet first identifies user travel intentions for user groups generalization, and then characterizes the group preferences by jointly considering historical user-hotel interaction and spatio-temporal features of hotels. For data sparsity, we develop a graph neural network, which employs long-term data, and further design an auxiliary loss function of location that efficiently exploits data within the same and across different locations. Both offline and online experiments demonstrate the effectiveness of LINet when compared with state-of-the-art methods. LINet has been successfully deployed on Fliggy to retrieve high quality hotels for business development, serving hundreds of hotel operation scenarios and thousands of hotel operators.
- Open Access
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 452-456
What Image do You Need? A Two-stage Framework for Image Selection in E-commerce
In e-commerce, images are widely used to display more intuitive information about items. Image selection significantly affects the user’s click-through rate (CTR). Most existing work considers the CTR as the target to find an appropriate image. However, these methods are challenging to deploy online efficiently. Also, the selected images may not relate to the item but are profitable to CTR, resulting in the undesirable phenomenon of enticing users to click on the item. To address these issues, we propose a novel two-stage pipeline method with content-based recall model and CTR-based ranking model. The first is realized as a joint method based on the title-image matching model and multi-modal knowledge graph embedding learning model. The second is a CTR-based visually aware scoring model, incorporating the entity textual information and entity images. Experimental results show the effectiveness and efficiency of our method in offline evaluations. After a month of online A/B testing on a travel platform Fliggy, the relative improvement of our method is 5% with respect to seller selection on CTCVR in the searching scenario, and our method further improves pCTR from 3.48% of human pick to 3.53% in the recommendation scenario.
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 452-456
Open AccessWhat Image do You Need? A Two-stage Framework for Image Selection in E-commerce
In e-commerce, images are widely used to display more intuitive information about items. Image selection significantly affects the user’s click-through rate (CTR). Most existing work considers the CTR as the target to find an appropriate image. However, these methods are challenging to deploy online efficiently. Also, the selected images may not relate to the item but are profitable to CTR, resulting in the undesirable phenomenon of enticing users to click on the item. To address these issues, we propose a novel two-stage pipeline method with content-based recall model and CTR-based ranking model. The first is realized as a joint method based on the title-image matching model and multi-modal knowledge graph embedding learning model. The second is a CTR-based visually aware scoring model, incorporating the entity textual information and entity images. Experimental results show the effectiveness and efficiency of our method in offline evaluations. After a month of online A/B testing on a travel platform Fliggy, the relative improvement of our method is 5% with respect to seller selection on CTCVR in the searching scenario, and our method further improves pCTR from 3.48% of human pick to 3.53% in the recommendation scenario.
- Open Access
- 23 March 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 41 (4) , 1-28
On the Vulnerability of Graph Learning-based Collaborative Filtering
Graph learning-based collaborative filtering (GLCF), which is built upon the message-passing mechanism of graph neural networks (GNNs), has received great recent attention and exhibited superior performance in recommender systems. However, although GNNs can be easily compromised by adversarial attacks as shown by the prior work, little attention has been paid to the vulnerability of GLCF. Questions like can GLCF models be just as easily fooled as GNNs remain largely unexplored. In this article, we propose to study the vulnerability of GLCF. Specifically, we first propose an adversarial attack against CLCF. Considering the unique challenges of attacking GLCF, we propose to adopt the greedy strategy in searching for the local optimal perturbations and design a reasonable attacking utility function to handle the non-differentiable ranking-oriented metrics. Next, we propose a defense to robustify GCLF. The defense is based on the observation that attacks usually introduce suspicious interactions into the graph to manipulate the message-passing process. We then propose to measure the suspicious score of each interaction and further reduce the message weight of suspicious interactions. We also give a theoretical guarantee of its robustness. Experimental results on three benchmark datasets show the effectiveness of both our attack and defense.
- 23 March 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 41 (4) , 1-28
Open AccessOn the Vulnerability of Graph Learning-based Collaborative Filtering
Graph learning-based collaborative filtering (GLCF), which is built upon the message-passing mechanism of graph neural networks (GNNs), has received great recent attention and exhibited superior performance in recommender systems. However, although GNNs can be easily compromised by adversarial attacks as shown by the prior work, little attention has been paid to the vulnerability of GLCF. Questions like can GLCF models be just as easily fooled as GNNs remain largely unexplored. In this article, we propose to study the vulnerability of GLCF. Specifically, we first propose an adversarial attack against CLCF. Considering the unique challenges of attacking GLCF, we propose to adopt the greedy strategy in searching for the local optimal perturbations and design a reasonable attacking utility function to handle the non-differentiable ranking-oriented metrics. Next, we propose a defense to robustify GCLF. The defense is based on the observation that attacks usually introduce suspicious interactions into the graph to manipulate the message-passing process. We then propose to measure the suspicious score of each interaction and further reduce the message weight of suspicious interactions. We also give a theoretical guarantee of its robustness. Experimental results on three benchmark datasets show the effectiveness of both our attack and defense.