Maolin Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Maolin Wang has a total of 167 co-authors. Here are the top co-authors by number of shared publications:
- Xiangyu Zhao
City University of Hong Kong, Kowloon Tong, Hong Kong
28 shared publications - Wanyu Wang
City University of Hong Kong, Hong Kong, Hong Kong
10 shared publications - Pengyue Jia
City University of Hong Kong, Hong Kong, China
9 shared publications - Ruocheng Guo
Intuit, Mountain View, USA
8 shared publications - Sheng Zhang
City University of Hong Kong, Hong Kong, China
6 shared publications - Yuhao Wang
City University of Hong Kong, Hong Kong, Hong Kong
6 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3113-3124
M2DNA: Multi-Modal Dual-Stream Representation Learning with Joint Relational Modeling for DNA Sequence Clustering
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3113-3124
Open AccessM2DNA: Multi-Modal Dual-Stream Representation Learning with Joint Relational Modeling for DNA Sequence Clustering
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1048-1059
Learning a Single Token to Replace Long System Prompts in LLMs
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1048-1059
Open AccessLearning a Single Token to Replace Long System Prompts in LLMs
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6277-6288
R 2 -Searcher: Calibrating Retrieval and Reasoning Boundaries for Agentic Search
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6277-6288
Open AccessR 2 -Searcher: Calibrating Retrieval and Reasoning Boundaries for Agentic Search
- Open Access
- 30 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 59 (1) , 1-20
Multi-Task Deep Recommender Systems: A Survey
Multi-task learning (MTL) aims at learning related tasks in a unified model to achieve mutual improvement among tasks considering their shared knowledge. It is an important topic in recommendation due to the demand for multi-task prediction considering performance and efficiency. Although MTL has been well studied and developed, there is still a lack of systematic review in the recommendation community. To fill the gap, we provide a comprehensive review of existing multi-task deep recommender systems (MTDRS) in this survey. To be specific, the problem definition of MTDRS is first given, and it is compared with other related areas. Next, the development of MTDRS is depicted and the taxonomy is introduced from the task relation and methodology aspects. Specifically, the task relation is categorized into parallel, cascaded, and auxiliary with main, while the methodology is grouped into parameter sharing, optimization, and training mechanism. The survey concludes by summarizing the application and public datasets of MTDRS and highlighting the challenges and future directions of the field.
- 30 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 59 (1) , 1-20
Open AccessMulti-Task Deep Recommender Systems: A Survey
Multi-task learning (MTL) aims at learning related tasks in a unified model to achieve mutual improvement among tasks considering their shared knowledge. It is an important topic in recommendation due to the demand for multi-task prediction considering performance and efficiency. Although MTL has been well studied and developed, there is still a lack of systematic review in the recommendation community. To fill the gap, we provide a comprehensive review of existing multi-task deep recommender systems (MTDRS) in this survey. To be specific, the problem definition of MTDRS is first given, and it is compared with other related areas. Next, the development of MTDRS is depicted and the taxonomy is introduced from the task relation and methodology aspects. Specifically, the task relation is categorized into parallel, cascaded, and auxiliary with main, while the methodology is grouped into parameter sharing, optimization, and training mechanism. The survey concludes by summarizing the application and public datasets of MTDRS and highlighting the challenges and future directions of the field.
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1623-1631
UNIQUE: A Unified Retrieval and Ranking System for Large-Scale Feed Recommendation
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1623-1631
Open AccessUNIQUE: A Unified Retrieval and Ranking System for Large-Scale Feed Recommendation
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 4951-4962
A Serial Two-Stage Framework for Robust Multimodal Fake News Detection via Adaptive Reasoning
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 4951-4962
Open AccessA Serial Two-Stage Framework for Robust Multimodal Fake News Detection via Adaptive Reasoning
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7866-7877
HIVE: Hierarchical Generation of Integrated and Varied Ensembles for Efficient Out-of-Distribution Generalization
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 7866-7877
Open AccessHIVE: Hierarchical Generation of Integrated and Varied Ensembles for Efficient Out-of-Distribution Generalization
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 2769-2779
Rethinking Semantic–Collaborative Integration: Why Alignment Is Not Enough
Large language models (LLMs) have become an important semantic infrastructure for modern recommender systems. A prevailing paradigm integrates LLM-derived semantic embeddings with collaborative representations via representation alignment, implicitly assuming that the two views encode a shared latent entity and that stronger alignment yields better results. We formalize this assumption as the global low-complexity alignment hypothesis and argue that it is stronger than necessary and often structurally mismatched with real-world recommendation settings. We propose a complementary perspective in which semantic and collaborative representations are treated as partially shared yet fundamentally heterogeneous views, each containing both shared and view-specific factors. Under this shared-plus-private latent structure, enforcing global geometric alignment may distort local structure, suppress view-specific signals, and reduce informational diversity. To support this perspective, we develop complementarity-aware diagnostics that quantify overlap, unique-hit contribution, and theoretical fusion upper bounds. Empirical analyses on sparse recommendation benchmarks reveal low item-level agreement between semantic and collaborative views and substantial oracle fusion gains, indicating strong complementarity. Furthermore, controlled alignment probes show that low-capacity mappings capture only shared components and fail to recover full collaborative geometry, especially under distribution shift. These findings suggest that alignment should not be treated as the default integration principle. We advocate a shift from alignment-centric modeling to complementarity fusion-centric, complementarity-aware design, where shared factors are selectively integrated while private signals are preserved. This reframing provides a principled foundation for the next generation of LLM-enhanced recommender systems.
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 2769-2779
Open AccessRethinking Semantic–Collaborative Integration: Why Alignment Is Not Enough
Large language models (LLMs) have become an important semantic infrastructure for modern recommender systems. A prevailing paradigm integrates LLM-derived semantic embeddings with collaborative representations via representation alignment, implicitly assuming that the two views encode a shared latent entity and that stronger alignment yields better results. We formalize this assumption as the global low-complexity alignment hypothesis and argue that it is stronger than necessary and often structurally mismatched with real-world recommendation settings. We propose a complementary perspective in which semantic and collaborative representations are treated as partially shared yet fundamentally heterogeneous views, each containing both shared and view-specific factors. Under this shared-plus-private latent structure, enforcing global geometric alignment may distort local structure, suppress view-specific signals, and reduce informational diversity. To support this perspective, we develop complementarity-aware diagnostics that quantify overlap, unique-hit contribution, and theoretical fusion upper bounds. Empirical analyses on sparse recommendation benchmarks reveal low item-level agreement between semantic and collaborative views and substantial oracle fusion gains, indicating strong complementarity. Furthermore, controlled alignment probes show that low-capacity mappings capture only shared components and fail to recover full collaborative geometry, especially under distribution shift. These findings suggest that alignment should not be treated as the default integration principle. We advocate a shift from alignment-centric modeling to complementarity fusion-centric, complementarity-aware design, where shared factors are selectively integrated while private signals are preserved. This reframing provides a principled foundation for the next generation of LLM-enhanced recommender systems.
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 2084-2095
ProEchoMem: Enhancing Long Video Understanding via Multi-Trace Probe-Echo Memory
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 2084-2095
Open AccessProEchoMem: Enhancing Long Video Understanding via Multi-Trace Probe-Echo Memory
- Open Access
- 30 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (5) , 1-55
Embedding in Recommender Systems: A Survey
Recommender systems have become an essential component of many online platforms, providing personalized recommendations to users. A crucial aspect is embedding techniques that convert the high-dimensional discrete features, such as user and item IDs, into low-dimensional continuous vectors, which can enhance the recommendation performance. Embedding techniques have revolutionized the capture of complex entity relationships, generating significant research interest. This survey presents a comprehensive analysis of recent advances in recommender system embedding techniques. We examine centralized embedding approaches across matrix, sequential, and graph structures. In matrix-based scenarios, collaborative filtering generates embeddings that effectively model user-item preferences, particularly in sparse data environments. For sequential data, we explore various approaches including recurrent neural networks and self-supervised methods such as contrastive and generative learning. In graph-structured contexts, we analyze techniques like node2vec that leverage network relationships, along with applicable self-supervised methods. Our survey addresses critical scalability challenges in embedding methods and explores innovative directions in recommender systems. We introduce emerging approaches, including AutoML, hashing techniques, and quantization methods, to enhance performance while reducing computational complexity. Additionally, we examine the promising role of Large Language Models (LLMs) in embedding enhancement. Through detailed discussion of various architectures and methodologies, this survey aims to provide a thorough overview of state-of-the-art embedding techniques in recommender systems, while highlighting key challenges and future research directions. To facilitate development, evaluation, and comparison of embedding-based recommender systems, we provide an open source repository ( https://github.com/Applied-Machine-Learning-Lab/Embedding-in-Recommender-Systems ).
- 30 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (5) , 1-55
Open AccessEmbedding in Recommender Systems: A Survey
Recommender systems have become an essential component of many online platforms, providing personalized recommendations to users. A crucial aspect is embedding techniques that convert the high-dimensional discrete features, such as user and item IDs, into low-dimensional continuous vectors, which can enhance the recommendation performance. Embedding techniques have revolutionized the capture of complex entity relationships, generating significant research interest. This survey presents a comprehensive analysis of recent advances in recommender system embedding techniques. We examine centralized embedding approaches across matrix, sequential, and graph structures. In matrix-based scenarios, collaborative filtering generates embeddings that effectively model user-item preferences, particularly in sparse data environments. For sequential data, we explore various approaches including recurrent neural networks and self-supervised methods such as contrastive and generative learning. In graph-structured contexts, we analyze techniques like node2vec that leverage network relationships, along with applicable self-supervised methods. Our survey addresses critical scalability challenges in embedding methods and explores innovative directions in recommender systems. We introduce emerging approaches, including AutoML, hashing techniques, and quantization methods, to enhance performance while reducing computational complexity. Additionally, we examine the promising role of Large Language Models (LLMs) in embedding enhancement. Through detailed discussion of various architectures and methodologies, this survey aims to provide a thorough overview of state-of-the-art embedding techniques in recommender systems, while highlighting key challenges and future research directions. To facilitate development, evaluation, and comparison of embedding-based recommender systems, we provide an open source repository ( https://github.com/Applied-Machine-Learning-Lab/Embedding-in-Recommender-Systems ).