Mingyuan Meng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mingyuan Meng has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
- Jinman Kim
The University of Sydney
18 shared publications - Lei Bi
School of Resource Environment and Safety Engineering University of South China 421001 Hengyang China
15 shared publications - Dagan Feng
Biomedical and Multimedia Information Technology Research Group, School of Computer Science, The University of Sydney, Sydney, NSW, Australia
11 shared publications - Shuchang Ye
The University of Sydney
5 shared publications Dagan Feng
4 shared publications- Michael Fulham
University of Sydney
4 shared publications
Latest Publications
- Open Access
- 29 October 2026
- Published by MDPI AG in Preprints.org
AI4AI: Toward AI-Discovered Superintelligence
Artificial intelligence (AI) is reshaping how AI itself is developed. From designing learning algorithms to automating research workflows and evaluation, this expanding role has fueled the rapid growth of AI for AI (AI4AI). Yet a fundamental question remains: as AI takes on more research tasks, which decisions does it actually control? Even systems that execute entire research workflows may still rely on humans to define research goals, allowable modifications, and criteria for success. Existing taxonomies, typically organized by technique or target artifact, offer limited insight into these differences in research responsibility. This survey presents a unified, control-centered perspective on AI4AI, viewing its evolution as a progressive transfer of control over three key decisions in the discovery loop: search direction, search space, and evaluation signal. We introduce an L0–L3 control-source framework, complemented by full responsibility profiles, to characterize different forms of human–AI research responsibility without conflating control with overall capability or end-to-end autonomy. This perspective unifies research across AI4AI Learning, Inference, Data, and Infrastructure, while motivating an evaluation framework that goes beyond downstream performance to assess decision quality, discovery efficiency, transfer, evaluator independence, and robustness under optimization. Looking further ahead, AI4AI may enable recursive self-improvement, where advances in AI enhance the process of making subsequent discoveries. If sustained and independently validated, such improvements could offer a pathway toward superintelligence. By connecting research autonomy with the conditions for reliable and cumulative progress, this survey provides a unified foundation for understanding the evolution and long-term potential of AI4AI.
- 29 October 2026
- Published by MDPI AG in Preprints.org
Open AccessAI4AI: Toward AI-Discovered Superintelligence
Artificial intelligence (AI) is reshaping how AI itself is developed. From designing learning algorithms to automating research workflows and evaluation, this expanding role has fueled the rapid growth of AI for AI (AI4AI). Yet a fundamental question remains: as AI takes on more research tasks, which decisions does it actually control? Even systems that execute entire research workflows may still rely on humans to define research goals, allowable modifications, and criteria for success. Existing taxonomies, typically organized by technique or target artifact, offer limited insight into these differences in research responsibility. This survey presents a unified, control-centered perspective on AI4AI, viewing its evolution as a progressive transfer of control over three key decisions in the discovery loop: search direction, search space, and evaluation signal. We introduce an L0–L3 control-source framework, complemented by full responsibility profiles, to characterize different forms of human–AI research responsibility without conflating control with overall capability or end-to-end autonomy. This perspective unifies research across AI4AI Learning, Inference, Data, and Infrastructure, while motivating an evaluation framework that goes beyond downstream performance to assess decision quality, discovery efficiency, transfer, evaluator independence, and robustness under optimization. Looking further ahead, AI4AI may enable recursive self-improvement, where advances in AI enhance the process of making subsequent discoveries. If sustained and independently validated, such improvements could offer a pathway toward superintelligence. By connecting research autonomy with the conditions for reliable and cumulative progress, this survey provides a unified foundation for understanding the evolution and long-term potential of AI4AI.
- 25 September 2026
- Published by Springer Nature
- p. 279-289
Really Need Recursion? Revisiting One-Pass Registration with Multi-Level Multi-Space Contextual Guidance
- 25 September 2026
- Published by Springer Nature
- p. 279-289
Really Need Recursion? Revisiting One-Pass Registration with Multi-Level Multi-Space Contextual Guidance
- 24 September 2026
- Published by Springer Nature
- p. 108-118
Case-Specific Priors-Guided Multimodal Fusion for Prognosis Prediction in Head and Neck Cancer
- 24 September 2026
- Published by Springer Nature
- p. 108-118
Case-Specific Priors-Guided Multimodal Fusion for Prognosis Prediction in Head and Neck Cancer
- Open Access
- 3 July 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 332
Language-guided medical image segmentation with target-informed multi-level contrastive alignments
- 3 July 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 332
Open AccessLanguage-guided medical image segmentation with target-informed multi-level contrastive alignments
- 9 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. PP (21682194) , 1-12
Hybrid-CMLP: Hybrid CNN-MLP Networks for Low-to-standard-dose PET Synthesis
Positron Emission Tomography (PET) is a critical modality in medical imaging for detecting abnormalities and diagnosing diseases. However, the radiation exposure from the radiotracer remains a significant concern. Synthesizing standard-dose PET (sPET) images from low-dose PET (lPET) offers a compelling solution, enabling high-quality imaging while substantially reducing radiation risks to patients. Existing PET synthesis methods predominantly rely on convolutional neural networks (CNNs), which are inherently limited by their local receptive fields. Transformer-based architectures have been explored to address this limitation by modeling long-range dependencies through self-attention. However, the high computational and memory costs of self-attention restrict Transformers to downsampled feature maps, limiting their ability to model global anatomical and functional correlations at full resolution. Multilayer Perceptrons (MLPs), in contrast, offer a computationally efficient way to capture long-range dependencies at full resolution. Yet, existing MLP-based methods for PET synthesis lack mechanisms to capture localized features such as subtle tissue textures that are critical for PET functionality. In this study, we propose a hybrid CNN-MLP network (Hybrid-CMLP) architecture for PET synthesis. Central to this architecture is a novel Hybrid-Syn block, which integrates axis-wise MLP branches for capturing global dependencies along spatial dimensions, and dual CNN branches for extracting both fine-grained and broad contextual features. To further enhance fine-grained reasoning, we introduce an Adaptive Fusion Mechanism (AFM) that dynamically integrates global and local features based on spatial context. Extensive experiments on two benchmark datasets demonstrate that Hybrid-CMLP consistently outperforms state-of-the-art methods in both qualitative and quantitative evaluations.
- 9 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. PP (21682194) , 1-12
Hybrid-CMLP: Hybrid CNN-MLP Networks for Low-to-standard-dose PET Synthesis
Positron Emission Tomography (PET) is a critical modality in medical imaging for detecting abnormalities and diagnosing diseases. However, the radiation exposure from the radiotracer remains a significant concern. Synthesizing standard-dose PET (sPET) images from low-dose PET (lPET) offers a compelling solution, enabling high-quality imaging while substantially reducing radiation risks to patients. Existing PET synthesis methods predominantly rely on convolutional neural networks (CNNs), which are inherently limited by their local receptive fields. Transformer-based architectures have been explored to address this limitation by modeling long-range dependencies through self-attention. However, the high computational and memory costs of self-attention restrict Transformers to downsampled feature maps, limiting their ability to model global anatomical and functional correlations at full resolution. Multilayer Perceptrons (MLPs), in contrast, offer a computationally efficient way to capture long-range dependencies at full resolution. Yet, existing MLP-based methods for PET synthesis lack mechanisms to capture localized features such as subtle tissue textures that are critical for PET functionality. In this study, we propose a hybrid CNN-MLP network (Hybrid-CMLP) architecture for PET synthesis. Central to this architecture is a novel Hybrid-Syn block, which integrates axis-wise MLP branches for capturing global dependencies along spatial dimensions, and dual CNN branches for extracting both fine-grained and broad contextual features. To further enhance fine-grained reasoning, we introduce an Adaptive Fusion Mechanism (AFM) that dynamically integrates global and local features based on spatial context. Extensive experiments on two benchmark datasets demonstrate that Hybrid-CMLP consistently outperforms state-of-the-art methods in both qualitative and quantitative evaluations.
- 27 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-11
Dynamic Traceback Learning for Medical Report Generation
Automated medical report generation has demonstrated the potential to significantly reduce the workload associated with time-consuming medical reporting. Recent generative representation learning methods have shown promise in integrating vision and language modalities for medical report generation. However, when trained end-to-end and applied directly to medical image-to-text generation, they face two significant challenges: i) difficulty in accurately capturing subtle yet crucial pathological details, and ii) reliance on both visual and textual inputs during inference, leading to performance degradation in zero-shot inference when only images are available. To address these challenges, this study proposes a novel multimodal dynamic traceback learning framework (DTrace)1. Specifically, we introduce a traceback mechanism to supervise the semantic validity of generated content and a dynamic learning strategy to adapt to various proportions of image and text input, enabling text generation without strong reliance on the input from both modalities during inference. The learning of cross-modal knowledge is enhanced by supervising the model to recover masked semantic information from a complementary counterpart. Extensive experiments conducted on two benchmark datasets, IU-Xray and MIMIC-CXR, demonstrate that the proposed DTrace framework outperforms state-of-the-art methods for medical report generation.
- 27 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-11
Dynamic Traceback Learning for Medical Report Generation
Automated medical report generation has demonstrated the potential to significantly reduce the workload associated with time-consuming medical reporting. Recent generative representation learning methods have shown promise in integrating vision and language modalities for medical report generation. However, when trained end-to-end and applied directly to medical image-to-text generation, they face two significant challenges: i) difficulty in accurately capturing subtle yet crucial pathological details, and ii) reliance on both visual and textual inputs during inference, leading to performance degradation in zero-shot inference when only images are available. To address these challenges, this study proposes a novel multimodal dynamic traceback learning framework (DTrace)1. Specifically, we introduce a traceback mechanism to supervise the semantic validity of generated content and a dynamic learning strategy to adapt to various proportions of image and text input, enabling text generation without strong reliance on the input from both modalities during inference. The learning of cross-modal knowledge is enhanced by supervising the model to recover masked semantic information from a complementary counterpart. Extensive experiments conducted on two benchmark datasets, IU-Xray and MIMIC-CXR, demonstrate that the proposed DTrace framework outperforms state-of-the-art methods for medical report generation.
- Open Access
Toward Next-generation Medical Vision Backbones: Modeling Finer-grained Long-range Visual Dependency
Medical Image Computing (MIC) is a broad research topic covering both pixel-wise (e.g., segmentation, registration) and image-wise (e.g., classification, regression) vision tasks. Effective analysis demands models that capture both global long-range context and local subtle visual characteristics, necessitating fine-grained long-range visual dependency modeling. Compared to Convolutional Neural Networks (CNNs) that are limited by intrinsic locality, transformers excel at long-range modeling; however, due to the high computational loads of self-attention, transformers typically cannot process high-resolution features (e.g., full-scale image features before downsampling or patch embedding) and thus face difficulties in modeling fine-grained dependency among subtle medical image details. Concurrently, Multi-layer Perceptron (MLP)-based visual models are recognized as computation/memory-efficient alternatives in modeling long-range visual dependency but have yet to be widely investigated in the MIC community. This doctoral research advances deep learning-based MIC by investigating effective long-range visual dependency modeling. It first presents innovative use of transformers for both pixel- and image-wise medical vision tasks. The focus then shifts to MLPs, pioneeringly developing MLP-based visual models to capture fine-grained long-range visual dependency in medical images. Extensive experiments confirm the critical role of long-range dependency modeling in MIC and reveal a key finding: MLPs provide feasibility in modeling finer-grained long-range dependency among higher-resolution medical features containing enriched anatomical/pathological details. This finding establishes MLPs as a superior paradigm over transformers/CNNs, consistently enhancing performance across various medical vision tasks and paving the way for next-generation medical vision backbones.
Open AccessToward Next-generation Medical Vision Backbones: Modeling Finer-grained Long-range Visual Dependency
Medical Image Computing (MIC) is a broad research topic covering both pixel-wise (e.g., segmentation, registration) and image-wise (e.g., classification, regression) vision tasks. Effective analysis demands models that capture both global long-range context and local subtle visual characteristics, necessitating fine-grained long-range visual dependency modeling. Compared to Convolutional Neural Networks (CNNs) that are limited by intrinsic locality, transformers excel at long-range modeling; however, due to the high computational loads of self-attention, transformers typically cannot process high-resolution features (e.g., full-scale image features before downsampling or patch embedding) and thus face difficulties in modeling fine-grained dependency among subtle medical image details. Concurrently, Multi-layer Perceptron (MLP)-based visual models are recognized as computation/memory-efficient alternatives in modeling long-range visual dependency but have yet to be widely investigated in the MIC community. This doctoral research advances deep learning-based MIC by investigating effective long-range visual dependency modeling. It first presents innovative use of transformers for both pixel- and image-wise medical vision tasks. The focus then shifts to MLPs, pioneeringly developing MLP-based visual models to capture fine-grained long-range visual dependency in medical images. Extensive experiments confirm the critical role of long-range dependency modeling in MIC and reveal a key finding: MLPs provide feasibility in modeling finer-grained long-range dependency among higher-resolution medical features containing enriched anatomical/pathological details. This finding establishes MLPs as a superior paradigm over transformers/CNNs, consistently enhancing performance across various medical vision tasks and paving the way for next-generation medical vision backbones.
- 29 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 44 (6) , 2463-2476
Enhancing Medical Vision-Language Contrastive Learning via Inter-Matching Relation Modeling
Medical image representations can be learned through medical vision-language contrastive learning (mVLCL) where medical imaging reports are used as weak supervision through image-text alignment. These learned image representations can be transferred to and benefit various downstream medical vision tasks such as disease classification and segmentation. Recent mVLCL methods attempt to align image sub-regions and the report keywords as local-matchings. However, these methods aggregate all local-matchings via simple pooling operations while ignoring the inherent relations between them. These methods therefore fail to reason between local-matchings that are semantically related, e.g., local-matchings that correspond to the disease word and the location word (semantic-relations), and also fail to differentiate such clinically important local-matchings from others that correspond to less meaningful words, e.g., conjunction words (importance-relations). Hence, we propose a mVLCL method that models the inter-matching relations between local-matchings via a relation-enhanced contrastive learning framework (RECLF). In RECLF, we introduce a semantic-relation reasoning module (SRM) and an importance-relation reasoning module (IRM) to enable more fine-grained report supervision for image representation learning. We evaluated our method using six public benchmark datasets on four downstream tasks, including segmentation, zero-shot classification, linear classification, and cross-modal retrieval. Our results demonstrated the superiority of our RECLF over the state-of-the-art mVLCL methods with consistent improvements across single-modal and cross-modal tasks. These results suggest that our RECLF, by modelling the inter-matching relations, can learn improved medical image representations with better generalization capabilities.
- 29 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 44 (6) , 2463-2476
Enhancing Medical Vision-Language Contrastive Learning via Inter-Matching Relation Modeling
Medical image representations can be learned through medical vision-language contrastive learning (mVLCL) where medical imaging reports are used as weak supervision through image-text alignment. These learned image representations can be transferred to and benefit various downstream medical vision tasks such as disease classification and segmentation. Recent mVLCL methods attempt to align image sub-regions and the report keywords as local-matchings. However, these methods aggregate all local-matchings via simple pooling operations while ignoring the inherent relations between them. These methods therefore fail to reason between local-matchings that are semantically related, e.g., local-matchings that correspond to the disease word and the location word (semantic-relations), and also fail to differentiate such clinically important local-matchings from others that correspond to less meaningful words, e.g., conjunction words (importance-relations). Hence, we propose a mVLCL method that models the inter-matching relations between local-matchings via a relation-enhanced contrastive learning framework (RECLF). In RECLF, we introduce a semantic-relation reasoning module (SRM) and an importance-relation reasoning module (IRM) to enable more fine-grained report supervision for image representation learning. We evaluated our method using six public benchmark datasets on four downstream tasks, including segmentation, zero-shot classification, linear classification, and cross-modal retrieval. Our results demonstrated the superiority of our RECLF over the state-of-the-art mVLCL methods with consistent improvements across single-modal and cross-modal tasks. These results suggest that our RECLF, by modelling the inter-matching relations, can learn improved medical image representations with better generalization capabilities.
- Top Cited PapersOpen Access
- 1 January 2025
- Published by Elsevier in Pattern Recognition
- Vol. 161
AutoFuse: Automatic fusion networks for deformable medical image registration
- 1 January 2025
- Published by Elsevier in Pattern Recognition
- Vol. 161
Top Cited PapersOpen AccessAutoFuse: Automatic fusion networks for deformable medical image registration