Youhua Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Youhua Li has a total of 62 co-authors. Here are the top co-authors by number of shared publications:
- Junchen Fu
University of Glasgow, Glasgow, United Kingdom
9 shared publications - Yongxin Ni
National University of Singapore, Singapore, Singapore
9 shared publications - Hanwen Du
The Ohio State University, Columbus, USA
6 shared publications - Chunxiao Li
University of Science and Technology of China, Hefei, China
4 shared publications - Ersheng Ni
The University of Queensland, Brisbane, Australia
4 shared publications - Sibo Xu
Wuhan University, Wuhan, China
4 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5269-5280
ClinSDT: LLM-Encoded Clinical Semantic Guidance for Sepsis Treatment via Decision Transformer
Offline sepsis treatment aims to learn treatment policies from retrospective ICU trajectories. Decision Transformer-based methods provide a natural sequence modeling framework for this task, but they mainly rely on raw physiological states and historical clinician actions. Such raw trajectory tokens may not explicitly capture clinical semantics that clinicians use in practice, such as patient severity, recent treatment response, and current risk priorities. To address this limitation, we propose ClinSDT, an LLM-assisted Decision Transformer framework for offline sepsis treatment. ClinSDT uses a frozen LLM as a semantic bridge rather than a treatment decision maker. It constructs three clinical semantic views from ICU trajectories, namely Profile, Context, and Advisory, and inserts their encoded representations as independent tokens into a Decision Transformer policy. To support policy refinement and rollout, ClinSDT further trains a Treatment-Response Forecaster to estimate the next physiological state, SAPS-II change, and predictive uncertainty from state--action inputs. In the second training stage, the forecaster screens local counterfactual treatment candidates, and only low-uncertainty candidates with lower predicted SAPS-II increase are distilled into the policy after semantic regeneration. During inference, ClinSDT performs closed-loop treatment rollout by refreshing semantic inputs from the currently available patient state. Experiments on MIMIC-III and MIMIC-IV show that ClinSDT achieves consistent relative improvements over representative imitation learning, offline reinforcement learning, and Decision Transformer baselines under the same rollout protocol. Code and data are available at ClinSDT.
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5269-5280
Open AccessClinSDT: LLM-Encoded Clinical Semantic Guidance for Sepsis Treatment via Decision Transformer
Offline sepsis treatment aims to learn treatment policies from retrospective ICU trajectories. Decision Transformer-based methods provide a natural sequence modeling framework for this task, but they mainly rely on raw physiological states and historical clinician actions. Such raw trajectory tokens may not explicitly capture clinical semantics that clinicians use in practice, such as patient severity, recent treatment response, and current risk priorities. To address this limitation, we propose ClinSDT, an LLM-assisted Decision Transformer framework for offline sepsis treatment. ClinSDT uses a frozen LLM as a semantic bridge rather than a treatment decision maker. It constructs three clinical semantic views from ICU trajectories, namely Profile, Context, and Advisory, and inserts their encoded representations as independent tokens into a Decision Transformer policy. To support policy refinement and rollout, ClinSDT further trains a Treatment-Response Forecaster to estimate the next physiological state, SAPS-II change, and predictive uncertainty from state--action inputs. In the second training stage, the forecaster screens local counterfactual treatment candidates, and only low-uncertainty candidates with lower predicted SAPS-II increase are distilled into the policy after semantic regeneration. During inference, ClinSDT performs closed-loop treatment rollout by refreshing semantic inputs from the currently available patient state. Experiments on MIMIC-III and MIMIC-IV show that ClinSDT achieves consistent relative improvements over representative imitation learning, offline reinforcement learning, and Decision Transformer baselines under the same rollout protocol. Code and data are available at ClinSDT.
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6724-6735
On the Role of Language Representations in Auto-Bidding: Findings and Implications
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6724-6735
Open AccessOn the Role of Language Representations in Auto-Bidding: Findings and Implications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2708-2718
Risk-Aware Reranking for Agentic Tool Retrieval
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2708-2718
Open AccessRisk-Aware Reranking for Agentic Tool Retrieval
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5922-5933
Recommender System as Slow and Fast Thinkers
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5922-5933
Open AccessRecommender System as Slow and Fast Thinkers
- 27 April 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 344
Interpretable knowledge tracing via explicit–implicit alignment
- 27 April 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 344
Interpretable knowledge tracing via explicit–implicit alignment
- Open Access
- 2 February 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (2) , 1-19
Bridging NIP and MLM: A Unified Meta-Learning Framework for Sequential Recommendation
Sequential Recommender Systems (SRSs) predict items of interest for users based on their historical interactions. Two key popular paradigms for SRs are unidirectional Next Item Prediction (NIP) and bidirectional Masked Language Modeling (MLM). NIP performs well in recommendation tasks but is constrained by its reliance on prior information and a rigid temporal order assumption, limiting its ability to capture dynamic personalized preferences. MLM, on the other hand, enhances sequence representation and personalization by leveraging bidirectional context, but its objective is misaligned with recommendation tasks. To this end, we develop MetaSR, a meta-learning-based SR approach that ingeniously combines both paradigms into a unified framework to enhance personalized sequential recommendation. Specifically, we treat the mask prediction task in MLM as the inner-loop task (i.e., the support set), adjusting mask items dynamically to generate sequences that match individual behavioral patterns to capture personalized user preferences. In the outer loop (i.e., the query set), we adopt the NIP paradigm to directly train MetaSR toward the SR target. The joint training bridges the gap between MLM and SRs tasks, also overcoming NIP’s limitations in capturing dynamic personalized preferences. Furthermore, to improve the overall efficiency, we develop a reinforcement learning-based Adaptive Masked Sequence Selection (AMSS) mechanism, automatically selecting the optimal masking prediction tasks within the meta-learning support set to accelerate the meta-learning and achieve better personalization. Experiments on multiple public benchmark datasets show that MetaSR significantly outperforms existing SRs models. The dataset and codes are available at MetaSR .
- 2 February 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (2) , 1-19
Open AccessBridging NIP and MLM: A Unified Meta-Learning Framework for Sequential Recommendation
Sequential Recommender Systems (SRSs) predict items of interest for users based on their historical interactions. Two key popular paradigms for SRs are unidirectional Next Item Prediction (NIP) and bidirectional Masked Language Modeling (MLM). NIP performs well in recommendation tasks but is constrained by its reliance on prior information and a rigid temporal order assumption, limiting its ability to capture dynamic personalized preferences. MLM, on the other hand, enhances sequence representation and personalization by leveraging bidirectional context, but its objective is misaligned with recommendation tasks. To this end, we develop MetaSR, a meta-learning-based SR approach that ingeniously combines both paradigms into a unified framework to enhance personalized sequential recommendation. Specifically, we treat the mask prediction task in MLM as the inner-loop task (i.e., the support set), adjusting mask items dynamically to generate sequences that match individual behavioral patterns to capture personalized user preferences. In the outer loop (i.e., the query set), we adopt the NIP paradigm to directly train MetaSR toward the SR target. The joint training bridges the gap between MLM and SRs tasks, also overcoming NIP’s limitations in capturing dynamic personalized preferences. Furthermore, to improve the overall efficiency, we develop a reinforcement learning-based Adaptive Masked Sequence Selection (AMSS) mechanism, automatically selecting the optimal masking prediction tasks within the meta-learning support set to accelerate the meta-learning and achieve better personalization. Experiments on multiple public benchmark datasets show that MetaSR significantly outperforms existing SRs models. The dataset and codes are available at MetaSR .
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 4571-4581
Frequency-Decoupled Distillation for Efficient Multimodal Recommendation
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 4571-4581
Open AccessFrequency-Decoupled Distillation for Efficient Multimodal Recommendation
- Top Cited PapersOpen Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6486-6491
A Content-Driven Micro-Video Recommendation Dataset at Scale
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6486-6491
Top Cited PapersOpen AccessA Content-Driven Micro-Video Recommendation Dataset at Scale
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 2801-2810
AMBER: Adaptive Meta Balanced Paradigm for Heterogeneous Graph-Based Knowledge Tracing
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 2801-2810
Open AccessAMBER: Adaptive Meta Balanced Paradigm for Heterogeneous Graph-Based Knowledge Tracing
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 2464-2475
Bridging the Gap: Teacher-Assisted Wasserstein Knowledge Distillation for Efficient Multi-Modal Recommendation
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 2464-2475
Open AccessBridging the Gap: Teacher-Assisted Wasserstein Knowledge Distillation for Efficient Multi-Modal Recommendation