Jintai Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Jintai Chen has a total of 184 co-authors. Here are the top co-authors by number of shared publications:
- Danny Z. Chen
University of Notre Dame
27 shared publications - Jian Wu
Zhejiang University, Hangzhou, China
27 shared publications Jian Wu
The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
10 shared publicationsYixuan Wu
Zhejiang University
8 shared publicationsHongxia Xu
7 shared publications- Haochao Ying
School of Public Health, Zhejiang University, Hangzhou, China
6 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 17450-17456
EEGBind: Detecting Source-Level Interictal Epileptiform Discharges via EEG-Centric Multimodal Binding
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 17450-17456
Open AccessEEGBind: Detecting Source-Level Interictal Epileptiform Discharges via EEG-Centric Multimodal Binding
- 25 September 2026
- Published by Springer Nature
- p. 587-597
Text as a Compass: Semantic-Navigated 3D Bone Collapse Prediction via Orthogonal Micro-volume Primitives
- 25 September 2026
- Published by Springer Nature
- p. 587-597
Text as a Compass: Semantic-Navigated 3D Bone Collapse Prediction via Orthogonal Micro-volume Primitives
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13304-13307
Toward Generalist Models for Structured Data: Fundamentals, Emerging Trends and Applications
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13304-13307
Open AccessToward Generalist Models for Structured Data: Fundamentals, Emerging Trends and Applications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 5350-5360
PHASE: Physiology-Aware Hyperspectral Reconstruction via Object-to-Human Domain Adaptation
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 5350-5360
Open AccessPHASE: Physiology-Aware Hyperspectral Reconstruction via Object-to-Human Domain Adaptation
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13020-13031
APCyc: Property-Informed Design of Cyclic Peptides via Automated Cyclization
Cyclic peptides represent a promising class of therapeutic compounds in modern drug discovery, often offering improved stability and binding affinity. However, the de novo design of cyclic peptides remains challenging because methods must identify pocket-adaptive cyclization patterns and linkage sites while simultaneously controlling drug-relevant properties. This challenge is particularly pronounced for recent generative models trained predominantly on linear peptide data, which may fail to capture cyclization-specific constraints. To address the limitation, we introduce APCyc, a target-aware de novo cyclic peptide generation framework that explicitly models cyclization and jointly optimizes multiple essential physicochemical properties. By using an expanded residue vocabulary and explicitly encoding cyclization-site and linkage-type information, APCyc learns cyclization-aware representations and leverages Bayesian posterior guidance to steer sampling toward cyclic peptides satisfying multiple property objectives. Experimental results demonstrate that our model learns target-dependent cyclization preferences, and enables effective and controllable multi-property optimization for cyclic peptide design. The source code of this paper is available at https://github.com/HKUSTGZ-ML4Health-Lab/APCyc.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13020-13031
Open AccessAPCyc: Property-Informed Design of Cyclic Peptides via Automated Cyclization
Cyclic peptides represent a promising class of therapeutic compounds in modern drug discovery, often offering improved stability and binding affinity. However, the de novo design of cyclic peptides remains challenging because methods must identify pocket-adaptive cyclization patterns and linkage sites while simultaneously controlling drug-relevant properties. This challenge is particularly pronounced for recent generative models trained predominantly on linear peptide data, which may fail to capture cyclization-specific constraints. To address the limitation, we introduce APCyc, a target-aware de novo cyclic peptide generation framework that explicitly models cyclization and jointly optimizes multiple essential physicochemical properties. By using an expanded residue vocabulary and explicitly encoding cyclization-site and linkage-type information, APCyc learns cyclization-aware representations and leverages Bayesian posterior guidance to steer sampling toward cyclic peptides satisfying multiple property objectives. Experimental results demonstrate that our model learns target-dependent cyclization preferences, and enables effective and controllable multi-property optimization for cyclic peptide design. The source code of this paper is available at https://github.com/HKUSTGZ-ML4Health-Lab/APCyc.
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 12715-12726
Caduceus: MoE Foundation Models for Unifying Biological and Natural Language
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 12715-12726
Open AccessCaduceus: MoE Foundation Models for Unifying Biological and Natural Language
- 23 July 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (8) , 361
Federated Learning Meets Test-Time Adaptation: Methods, Challenges, and Future Directions
- 23 July 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (8) , 361
Federated Learning Meets Test-Time Adaptation: Methods, Challenges, and Future Directions
- Open Access
- 28 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 58-61
Generalist Model for Structured Data: Foundations, Frontiers and Applications
Structured data constitutes one of the most ubiquitous data modalities in web-scale and enterprise applications, supporting tasks such as recommendation, forecasting, and user behavior analysis. Conventional modeling paradigms—ranging from generalized linear models and gradient boosting to deep structured networks—have provided strong baselines for predictive analytics and decision support. However, the recent emergence of foundation models and in-context learning (ICL) has sparked a new paradigm for structured modeling, moving from dataset-specific training toward universal, adaptable inference. Emerging structured foundation models illustrate how large-scale pretraining, synthetic data generation, and ICL-based inference can extend foundation-model principles to structured data. These developments open new possibilities for multi-task learning, zero-shot inference, and knowledge transfer across diverse structured settings. Yet, the space of structured foundation models remains largely unexplored, with open questions surrounding data generation, multi-task setting, pretraining objectives, and evaluation standards. This tutorial will provide a structured overview of both conventional modeling and recent ICL-based approaches. Participants will gain a comprehensive understanding of established methods, current advances in foundation models, and open research challenges. In particular, we will offer an in-depth introduction to structured ICL and review the most representative foundation models in this field. Several key topics in this field will be discussed, including pretraining data generation, multi-task learning, and other emerging directions in the modeling of structured data. This tutorial aims to bridge conventional machine learning and the emerging foundation-model paradigm, providing attendees with conceptual and practical insights into structured data modeling in the era of generalist foundation models.
- 28 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 58-61
Open AccessGeneralist Model for Structured Data: Foundations, Frontiers and Applications
Structured data constitutes one of the most ubiquitous data modalities in web-scale and enterprise applications, supporting tasks such as recommendation, forecasting, and user behavior analysis. Conventional modeling paradigms—ranging from generalized linear models and gradient boosting to deep structured networks—have provided strong baselines for predictive analytics and decision support. However, the recent emergence of foundation models and in-context learning (ICL) has sparked a new paradigm for structured modeling, moving from dataset-specific training toward universal, adaptable inference. Emerging structured foundation models illustrate how large-scale pretraining, synthetic data generation, and ICL-based inference can extend foundation-model principles to structured data. These developments open new possibilities for multi-task learning, zero-shot inference, and knowledge transfer across diverse structured settings. Yet, the space of structured foundation models remains largely unexplored, with open questions surrounding data generation, multi-task setting, pretraining objectives, and evaluation standards. This tutorial will provide a structured overview of both conventional modeling and recent ICL-based approaches. Participants will gain a comprehensive understanding of established methods, current advances in foundation models, and open research challenges. In particular, we will offer an in-depth introduction to structured ICL and review the most representative foundation models in this field. Several key topics in this field will be discussed, including pretraining data generation, multi-task learning, and other emerging directions in the modeling of structured data. This tutorial aims to bridge conventional machine learning and the emerging foundation-model paradigm, providing attendees with conceptual and practical insights into structured data modeling in the era of generalist foundation models.
- Open Access
Med-Scout: Curing MLLMs' Geometric Blindness in Medical Perception via Geometry-Aware RL Post-Training
Despite recent Multimodal Large Language Models (MLLMs)' linguistic prowess in medical diagnosis, we find even state-of-the-art MLLMs suffer from a critical perceptual deficit: geometric blindness. This failure to ground outputs in objective geometric constraints leads to plausible yet factually incorrect hallucinations, rooted in training paradigms that prioritize linguistic fluency over geometric fidelity. This paper introduces Med-Scout, a novel framework that "cures" this blindness via Reinforcement Learning (RL) that leverages the intrinsic geometric logic latent within unlabeled medical images. Instead of relying on costly expert annotations, Med-Scout derives verifiable supervision signals through three strategic proxy tasks: Hierarchical Scale Localization, Topological Jigsaw Reconstruction, and Anomaly Consistency Detection. To rigorously quantify this deficit, we present Med-Scout-Bench, a new benchmark specifically designed to evaluate geometric perception. Extensive evaluations show that Med-Scout significantly mitigates geometric blindness, outperforming leading proprietary and open-source MLLMs by over 40% on our benchmark. Furthermore, this enhanced geometric perception generalizes to broader medical understanding, achieving superior results on radiological and comprehensive medical VQA tasks.
Open AccessMed-Scout: Curing MLLMs' Geometric Blindness in Medical Perception via Geometry-Aware RL Post-Training
Despite recent Multimodal Large Language Models (MLLMs)' linguistic prowess in medical diagnosis, we find even state-of-the-art MLLMs suffer from a critical perceptual deficit: geometric blindness. This failure to ground outputs in objective geometric constraints leads to plausible yet factually incorrect hallucinations, rooted in training paradigms that prioritize linguistic fluency over geometric fidelity. This paper introduces Med-Scout, a novel framework that "cures" this blindness via Reinforcement Learning (RL) that leverages the intrinsic geometric logic latent within unlabeled medical images. Instead of relying on costly expert annotations, Med-Scout derives verifiable supervision signals through three strategic proxy tasks: Hierarchical Scale Localization, Topological Jigsaw Reconstruction, and Anomaly Consistency Detection. To rigorously quantify this deficit, we present Med-Scout-Bench, a new benchmark specifically designed to evaluate geometric perception. Extensive evaluations show that Med-Scout significantly mitigates geometric blindness, outperforming leading proprietary and open-source MLLMs by over 40% on our benchmark. Furthermore, this enhanced geometric perception generalizes to broader medical understanding, achieving superior results on radiological and comprehensive medical VQA tasks.
- 3 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- Vol. 12 (2) , 600-611
Versatile and Risk-Sensitive Cardiac Diagnosis via Graph-Based ECG Signal Representation
Despite the rapid advancements of electrocardiogram (ECG) signal diagnosis and analysis methods through deep learning, two major hurdles still limit their clinical adoption: the lack of versatility in processing ECG signals with diverse configurations, and the inadequate detection of risk signals due to sample imbalances. Addressing these challenges, we introduce VersAtile and Risk-Sensitive cardiac diagnosis (VARS), an innovative approach that employs a graph-based representation to uniformly model heterogeneous ECG signals. VARS stands out by transforming ECG signals into versatile graph structures that capture critical diagnostic features, irrespective of signal diversity in the lead count, sampling frequency, and duration. This graph-centric formulation also enhances diagnostic sensitivity, enabling precise localization and identification of abnormal ECG patterns that often elude standard analysis methods. To facilitate representation transformation, our approach integrates denoising reconstruction with contrastive learning to preserve raw ECG information while highlighting pathognomonic patterns. We rigorously evaluate the efficacy of VARS on three distinct ECG datasets, encompassing a range of structural variations. The results demonstrate that VARS not only consistently surpasses existing state-of-the-art models across all these datasets but also exhibits substantial improvement in identifying risk signals. Additionally, VARS offers interpretability by pinpointing the exact waveforms that lead to specific model outputs, thereby assisting clinicians in making informed decisions. These findings suggest that our VARS will likely emerge as an invaluable tool for comprehensive cardiac health assessment.
- 3 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- Vol. 12 (2) , 600-611
Versatile and Risk-Sensitive Cardiac Diagnosis via Graph-Based ECG Signal Representation
Despite the rapid advancements of electrocardiogram (ECG) signal diagnosis and analysis methods through deep learning, two major hurdles still limit their clinical adoption: the lack of versatility in processing ECG signals with diverse configurations, and the inadequate detection of risk signals due to sample imbalances. Addressing these challenges, we introduce VersAtile and Risk-Sensitive cardiac diagnosis (VARS), an innovative approach that employs a graph-based representation to uniformly model heterogeneous ECG signals. VARS stands out by transforming ECG signals into versatile graph structures that capture critical diagnostic features, irrespective of signal diversity in the lead count, sampling frequency, and duration. This graph-centric formulation also enhances diagnostic sensitivity, enabling precise localization and identification of abnormal ECG patterns that often elude standard analysis methods. To facilitate representation transformation, our approach integrates denoising reconstruction with contrastive learning to preserve raw ECG information while highlighting pathognomonic patterns. We rigorously evaluate the efficacy of VARS on three distinct ECG datasets, encompassing a range of structural variations. The results demonstrate that VARS not only consistently surpasses existing state-of-the-art models across all these datasets but also exhibits substantial improvement in identifying risk signals. Additionally, VARS offers interpretability by pinpointing the exact waveforms that lead to specific model outputs, thereby assisting clinicians in making informed decisions. These findings suggest that our VARS will likely emerge as an invaluable tool for comprehensive cardiac health assessment.