Zhanyu Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhanyu Wang has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Luping Zhou
University of Sydney, Sydney, Australia
18 shared publications - Lei Wang
University of Wollongong, Wollongong, Australia
12 shared publications - Lingqiao Liu
University of Adelaide, Adelaide, Australia
8 shared publications - Yunyi Liu
The University of Sydney
6 shared publications - Xiu Li
Tsinghua University
4 shared publications - Yingshu Li
School of Electrical and Computer Engineering The University of Sydney 2006 Sydney NSW Australia
4 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5582-5590
IF-Bench: Evaluating Instruction Following in Video Embedding Models via Controlled Preference Flips
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5582-5590
Open AccessIF-Bench: Evaluating Instruction Following in Video Embedding Models via Controlled Preference Flips
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5572-5581
Graph-Supervised Hierarchical Clinical Alignment for Radiology Report Generation with Large Language Models
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5572-5581
Open AccessGraph-Supervised Hierarchical Clinical Alignment for Radiology Report Generation with Large Language Models
- 1 October 2025
- Published by Zhejiang University Press in Frontiers of Information Technology & Electronic Engineering
- Vol. 26 (10) , 1832-1846
Can large language models effectively process and execute financial trading instructions?
The development of large language models (LLMs) has created transformative opportunities for the financial industry, especially in the area of financial tr
- 1 October 2025
- Published by Zhejiang University Press in Frontiers of Information Technology & Electronic Engineering
- Vol. 26 (10) , 1832-1846
Can large language models effectively process and execute financial trading instructions?
The development of large language models (LLMs) has created transformative opportunities for the financial industry, especially in the area of financial tr
- Open Access
S-RRG-Bench: Structured Radiology Report Generation with Fine-Grained Evaluation Framework
Radiology report generation (RRG) for diagnostic images, such as chest X-rays, plays a pivotal role in both clinical practice and AI. Traditional free-text reports suffer from redundancy and inconsistent language, complicating the extraction of critical clinical details. Structured radiology report generation (S-RRG) offers a promising solution by organizing information into standardized, concise formats. However, existing approaches often rely on classification or visual question answering (VQA) pipelines that require predefined label sets and produce only fragmented outputs. Template-based approaches, which generate reports by replacing keywords within fixed sentence patterns, further compromise expressiveness and often omit clinically important details. In this work, we present a novel approach to S-RRG that includes dataset construction, model training, and the introduction of a new evaluation framework. We first create a robust chest X-ray dataset (MIMIC-STRUC) that includes disease names, severity levels, probabilities, and anatomical locations, ensuring that the dataset is both clinically relevant and well-structured. We train an LLM-based model to generate standardized, high-quality reports. To assess the generated reports, we propose a specialized evaluation metric (S-Score) that not only measures disease prediction accuracy but also evaluates the precision of disease-specific details, thus offering a clinically meaningful metric for report quality that focuses on elements critical to clinical decision-making and demonstrates a stronger alignment with human assessments. Our approach highlights the effectiveness of structured reports and the importance of a tailored evaluation metric for S-RRG, providing a more clinically relevant measure of report quality.
Open AccessS-RRG-Bench: Structured Radiology Report Generation with Fine-Grained Evaluation Framework
Radiology report generation (RRG) for diagnostic images, such as chest X-rays, plays a pivotal role in both clinical practice and AI. Traditional free-text reports suffer from redundancy and inconsistent language, complicating the extraction of critical clinical details. Structured radiology report generation (S-RRG) offers a promising solution by organizing information into standardized, concise formats. However, existing approaches often rely on classification or visual question answering (VQA) pipelines that require predefined label sets and produce only fragmented outputs. Template-based approaches, which generate reports by replacing keywords within fixed sentence patterns, further compromise expressiveness and often omit clinically important details. In this work, we present a novel approach to S-RRG that includes dataset construction, model training, and the introduction of a new evaluation framework. We first create a robust chest X-ray dataset (MIMIC-STRUC) that includes disease names, severity levels, probabilities, and anatomical locations, ensuring that the dataset is both clinically relevant and well-structured. We train an LLM-based model to generate standardized, high-quality reports. To assess the generated reports, we propose a specialized evaluation metric (S-Score) that not only measures disease prediction accuracy but also evaluates the precision of disease-specific details, thus offering a clinically meaningful metric for report quality that focuses on elements critical to clinical decision-making and demonstrates a stronger alignment with human assessments. Our approach highlights the effectiveness of structured reports and the importance of a tailored evaluation metric for S-RRG, providing a more clinically relevant measure of report quality.
- 25 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 44 (11) , 4666-4677
Enhancing Radiology Report Generation via Multi-Phased Supervision
Radiology report generation using large language models has recently produced reports with more realistic styles and better language fluency. However, their clinical accuracy remains inadequate. Considering the significant imbalance between clinical phrases and general descriptions in a report, we argue that using an entire report for supervision is problematic as it fails to emphasize the crucial clinical phrases, which require focused learning. To address this issue, we propose a multi-phased supervision method, inspired by the spirit of curriculum learning where models are trained by gradually increasing task complexity. Our approach organizes the learning process into structured phases at different levels of semantical granularity, each building on the previous one to enhance the model. During the first phase, disease labels are used to supervise the model, equipping it with the ability to identify underlying diseases. The second phase progresses to use entity-relation triples to guide the model to describe associated clinical findings. Finally, in the third phase, we introduce conventional whole-report-based supervision to quickly adapt the model for report generation. Throughout the phased training, the model remains the same and consistently operates in the generation mode. As experimentally demonstrated, this proposed change in the way of supervision enhances report generation, achieving state-of-the-art performance in both language fluency and clinical accuracy. Our work underscores the importance of training process design in radiology report generation. Our code is available on https://github.com/zailongchen/MultiP-R2Gen.
- 25 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 44 (11) , 4666-4677
Enhancing Radiology Report Generation via Multi-Phased Supervision
Radiology report generation using large language models has recently produced reports with more realistic styles and better language fluency. However, their clinical accuracy remains inadequate. Considering the significant imbalance between clinical phrases and general descriptions in a report, we argue that using an entire report for supervision is problematic as it fails to emphasize the crucial clinical phrases, which require focused learning. To address this issue, we propose a multi-phased supervision method, inspired by the spirit of curriculum learning where models are trained by gradually increasing task complexity. Our approach organizes the learning process into structured phases at different levels of semantical granularity, each building on the previous one to enhance the model. During the first phase, disease labels are used to supervise the model, equipping it with the ability to identify underlying diseases. The second phase progresses to use entity-relation triples to guide the model to describe associated clinical findings. Finally, in the third phase, we introduce conventional whole-report-based supervision to quickly adapt the model for report generation. Throughout the phased training, the model remains the same and consistently operates in the generation mode. As experimentally demonstrated, this proposed change in the way of supervision enhances report generation, achieving state-of-the-art performance in both language fluency and clinical accuracy. Our work underscores the importance of training process design in radiology report generation. Our code is available on https://github.com/zailongchen/MultiP-R2Gen.
- 22 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (8) , 6585-6598
Diagnostic Captioning by Cooperative Task Interactions and Sample-Graph Consistency
Radiographic images are similar to each other, making it challenging for diagnostic captioning to narrate fine-grained visual differences of clinical importance. In this paper, we propose a self-boosting framework integrating two novel strategies to learn tightly correlated image and text features for diagnostic captioning. The first strategy explicitly aligns image and text features through training an auxiliary task of image-text matching (ITM) jointly with the main task of report generation (RG) as two branches of a network model. The ITM branch explicitly learns image-text alignment and provides highly correlated visual and textual features for the RG branch to generate high-quality reports. The high-quality reports generated by RG branch, in turn, are utilized as additional harder negative samples to push the ITM branch to evolve towards better image-text alignment. These two branches help improve each other progressively, so that the whole model is self-boosted without requiring external resources. The second strategy aligns image-sample space and report-sample space to achieve consistent image and text feature embeddings. To achieve this, the sample graph of the embedded ground-truth reports is built and used as the target to train the sample graph of the embedded images so that the fine discrepancy in the ground-truth reports could be captured by the learned visual feature embeddings. Our proposed framework demonstrates its superiority on two medical report generation benchmarks, including the largest dataset MIMIC-CXR.
- 22 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (8) , 6585-6598
Diagnostic Captioning by Cooperative Task Interactions and Sample-Graph Consistency
Radiographic images are similar to each other, making it challenging for diagnostic captioning to narrate fine-grained visual differences of clinical importance. In this paper, we propose a self-boosting framework integrating two novel strategies to learn tightly correlated image and text features for diagnostic captioning. The first strategy explicitly aligns image and text features through training an auxiliary task of image-text matching (ITM) jointly with the main task of report generation (RG) as two branches of a network model. The ITM branch explicitly learns image-text alignment and provides highly correlated visual and textual features for the RG branch to generate high-quality reports. The high-quality reports generated by RG branch, in turn, are utilized as additional harder negative samples to push the ITM branch to evolve towards better image-text alignment. These two branches help improve each other progressively, so that the whole model is self-boosted without requiring external resources. The second strategy aligns image-sample space and report-sample space to achieve consistent image and text feature embeddings. To achieve this, the sample graph of the embedded ground-truth reports is built and used as the target to train the sample graph of the embedded images so that the fine discrepancy in the ground-truth reports could be captured by the learned visual feature embeddings. Our proposed framework demonstrates its superiority on two medical report generation benchmarks, including the largest dataset MIMIC-CXR.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3907-3916
GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation
Recent advances in Multimodal Large Language Models (MLLMs) have constituted a significant leap forward in the field, particularly in the processing of videos, which encompasses inherent challenges such as spatiotemporal relationships. However, existing MLLMs are predominantly focused on the comprehension of video inputs, with limited capabilities in generating video content. In this paper, we present GPT4Video, a unified framework that seamlessly and lightly integrates with LLMs, visual feature extractors, and stable diffusion generative models for cohesive video understanding and generation. Moreover, we explore a text-only finetuning approach to equip models for instruction-following and safeguarding in multimodal conversations, enhancing training efficiency and generalization capabilities. Additionally, we construct multi-turn and caption-interleaved datasets for finetuning and benchmarking MLLMs, which serve as solid resources for advancing this field. Through quantitative and qualitative assessments, GPT4Video demonstrates the following advantages: 1) The framework incorporates video generation ability without adding extra training parameters, ensuring seamless compatibility with various video generators. 2) The model achieves superior performances across a variety of benchmarks. For instance, it outperforms Valley by 11.8% on video question answering, and surpasses NExt-GPT by 2.3% on text-to-video generation. 3) As safety pioneers in open-source MLLMs, we developed finetuning and evaluation datasets, securing an F1 score exceeding 80% in blocking harmful content during understanding and generating videos. In general, GPT4Video shows potential to function as a real-life assistant, marked by its effectiveness, adaptability, and safety.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3907-3916
Open AccessGPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation
Recent advances in Multimodal Large Language Models (MLLMs) have constituted a significant leap forward in the field, particularly in the processing of videos, which encompasses inherent challenges such as spatiotemporal relationships. However, existing MLLMs are predominantly focused on the comprehension of video inputs, with limited capabilities in generating video content. In this paper, we present GPT4Video, a unified framework that seamlessly and lightly integrates with LLMs, visual feature extractors, and stable diffusion generative models for cohesive video understanding and generation. Moreover, we explore a text-only finetuning approach to equip models for instruction-following and safeguarding in multimodal conversations, enhancing training efficiency and generalization capabilities. Additionally, we construct multi-turn and caption-interleaved datasets for finetuning and benchmarking MLLMs, which serve as solid resources for advancing this field. Through quantitative and qualitative assessments, GPT4Video demonstrates the following advantages: 1) The framework incorporates video generation ability without adding extra training parameters, ensuring seamless compatibility with various video generators. 2) The model achieves superior performances across a variety of benchmarks. For instance, it outperforms Valley by 11.8% on video question answering, and surpasses NExt-GPT by 2.3% on text-to-video generation. 3) As safety pioneers in open-source MLLMs, we developed finetuning and evaluation datasets, securing an F1 score exceeding 80% in blocking harmful content during understanding and generating videos. In general, GPT4Video shows potential to function as a real-life assistant, marked by its effectiveness, adaptability, and safety.
- 4 October 2024
- Published by Springer Nature
- p. 382-392
KARGEN: Knowledge-Enhanced Automated Radiology Report Generation Using Large Language Models
- 4 October 2024
- Published by Springer Nature
- p. 382-392
KARGEN: Knowledge-Enhanced Automated Radiology Report Generation Using Large Language Models
- 3 October 2024
- Published by Springer Nature
- p. 283-292
MRScore: Evaluating Medical Report with LLM-Based Reward System
- 3 October 2024
- Published by Springer Nature
- p. 283-292
MRScore: Evaluating Medical Report with LLM-Based Reward System
- Open Access
KARGEN: Knowledge-enhanced Automated Radiology Report Generation Using Large Language Models
Harnessing the robust capabilities of Large Language Models (LLMs) for narrative generation, logical reasoning, and common-sense knowledge integration, this study delves into utilizing LLMs to enhance automated radiology report generation (R2Gen). Despite the wealth of knowledge within LLMs, efficiently triggering relevant knowledge within these large models for specific tasks like R2Gen poses a critical research challenge. This paper presents KARGEN, a Knowledge-enhanced Automated radiology Report GENeration framework based on LLMs. Utilizing a frozen LLM to generate reports, the framework integrates a knowledge graph to unlock chest disease-related knowledge within the LLM to enhance the clinical utility of generated reports. This is achieved by leveraging the knowledge graph to distill disease-related features in a designed way. Since a radiology report encompasses both normal and disease-related findings, the extracted graph-enhanced disease-related features are integrated with regional image features, attending to both aspects. We explore two fusion methods to automatically prioritize and select the most relevant features. The fused features are employed by LLM to generate reports that are more sensitive to diseases and of improved quality. Our approach demonstrates promising results on the MIMIC-CXR and IU-Xray datasets.
Open AccessKARGEN: Knowledge-enhanced Automated Radiology Report Generation Using Large Language Models
Harnessing the robust capabilities of Large Language Models (LLMs) for narrative generation, logical reasoning, and common-sense knowledge integration, this study delves into utilizing LLMs to enhance automated radiology report generation (R2Gen). Despite the wealth of knowledge within LLMs, efficiently triggering relevant knowledge within these large models for specific tasks like R2Gen poses a critical research challenge. This paper presents KARGEN, a Knowledge-enhanced Automated radiology Report GENeration framework based on LLMs. Utilizing a frozen LLM to generate reports, the framework integrates a knowledge graph to unlock chest disease-related knowledge within the LLM to enhance the clinical utility of generated reports. This is achieved by leveraging the knowledge graph to distill disease-related features in a designed way. Since a radiology report encompasses both normal and disease-related findings, the extracted graph-enhanced disease-related features are integrated with regional image features, attending to both aspects. We explore two fusion methods to automatically prioritize and select the most relevant features. The fused features are employed by LLM to generate reports that are more sensitive to diseases and of improved quality. Our approach demonstrates promising results on the MIMIC-CXR and IU-Xray datasets.