Ting-Ruen Wei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ting-Ruen Wei has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Yi Fang
Santa Clara University
4 shared publications - Hsin-Tai Wu
Docomo Innovations Santa Clara University Santa Clara University Santa Clara University Docomo Innovations
2 shared publications - Xuyang Wu
Santa Clara University Santa Clara CA
2 shared publications - Yuling Yan
Santa Clara University, 500 El Camino Real, Santa Clara, 95053, CA, USA
2 shared publications Aren Vierra
Santa Clara Valley Medical Center, San Jose, CA, USA
1 shared publicationHaowei Liu
Clara University Santa Clara University Santa Clara University Santa Clara University
1 shared publication
Latest Publications
- Open Access
- 15 August 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Recommender Systems
Diffusion Models in Recommendation Systems: A Survey
Recommender systems remain an essential topic due to its wide application and business potential. Given the great generation capability exhibited by diffusion models in computer vision recently, many recommender systems have adopted diffusion models and found improvements in performance for various tasks. Research in this domain has been growing rapidly and calling for a systematic survey. In this survey paper, we propose and present a taxonomy based on three complementary axes to categorize recommender systems that utilize diffusion models. Distinct from prior survey work that primarily categorizes based on the role of diffusion models, we organize the taxonomy primarily around the recommendation task. This choice is motivated by the observation that diffusion models are typically adopted to improve recommendation performance under different task settings. Our taxonomy provides a complementary perspective to existing surveys. We present the foundational algorithms in diffusion models and their applications in recommender systems to summarize recent progress in this field. Finally, we discuss open research directions to encourage further research. We compile the relevant papers in a public GitHub repository.
- 15 August 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Recommender Systems
Open AccessDiffusion Models in Recommendation Systems: A Survey
Recommender systems remain an essential topic due to its wide application and business potential. Given the great generation capability exhibited by diffusion models in computer vision recently, many recommender systems have adopted diffusion models and found improvements in performance for various tasks. Research in this domain has been growing rapidly and calling for a systematic survey. In this survey paper, we propose and present a taxonomy based on three complementary axes to categorize recommender systems that utilize diffusion models. Distinct from prior survey work that primarily categorizes based on the role of diffusion models, we organize the taxonomy primarily around the recommendation task. This choice is motivated by the observation that diffusion models are typically adopted to improve recommendation performance under different task settings. Our taxonomy provides a complementary perspective to existing surveys. We present the foundational algorithms in diffusion models and their applications in recommender systems to summarize recent progress in this field. Finally, we discuss open research directions to encourage further research. We compile the relevant papers in a public GitHub repository.
- Top Cited PapersOpen Access
- 1 January 2026
- Published by KEAI Publishing in Intelligent Oncology
- Vol. 2 (1) , 100037
Multimodal medical imaging AI for breast cancer diagnosis: A comprehensive review
- 1 January 2026
- Published by KEAI Publishing in Intelligent Oncology
- Vol. 2 (1) , 100037
Top Cited PapersOpen AccessMultimodal medical imaging AI for breast cancer diagnosis: A comprehensive review
- Open Access
A Survey on Feedback-based Multi-step Reasoning for Large Language Models on Mathematics
Recent progress in large language models (LLM) found chain-of-thought prompting strategies to improve the reasoning ability of LLMs by encouraging problem solving through multiple steps. Therefore, subsequent research aimed to integrate the multi-step reasoning process into the LLM itself through process rewards as feedback and achieved improvements over prompting strategies. Due to the cost of step-level annotation, some turn to outcome rewards as feedback. Aside from these training-based approaches, training-free techniques leverage frozen LLMs or external tools for feedback at each step to enhance the reasoning process. With the abundance of work in mathematics due to its logical nature, we present a survey of strategies utilizing feedback at the step and outcome levels to enhance multi-step math reasoning for LLMs. As multi-step reasoning emerges a crucial component in scaling LLMs, we hope to establish its foundation for easier understanding and empower further research.
Open AccessA Survey on Feedback-based Multi-step Reasoning for Large Language Models on Mathematics
Recent progress in large language models (LLM) found chain-of-thought prompting strategies to improve the reasoning ability of LLMs by encouraging problem solving through multiple steps. Therefore, subsequent research aimed to integrate the multi-step reasoning process into the LLM itself through process rewards as feedback and achieved improvements over prompting strategies. Due to the cost of step-level annotation, some turn to outcome rewards as feedback. Aside from these training-based approaches, training-free techniques leverage frozen LLMs or external tools for feedback at each step to enhance the reasoning process. With the abundance of work in mathematics due to its logical nature, we present a survey of strategies utilizing feedback at the step and outcome levels to enhance multi-step math reasoning for LLMs. As multi-step reasoning emerges a crucial component in scaling LLMs, we hope to establish its foundation for easier understanding and empower further research.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 18534-18555
Does Reasoning Introduce Bias? A Study of Social Bias Evaluation and Mitigation in LLM Reasoning
Xuyang Wu, Jinming Nian, Ting-Ruen Wei, Zhiqiang Tao, Hsin-Tai Wu, Yi Fang. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 18534-18555
Open AccessDoes Reasoning Introduce Bias? A Study of Social Bias Evaluation and Mitigation in LLM Reasoning
Xuyang Wu, Jinming Nian, Ting-Ruen Wei, Zhiqiang Tao, Hsin-Tai Wu, Yi Fang. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- Open Access
- 22 October 2024
- Published by Elsevier in Pattern Recognition Letters
- Vol. 186, 258-264
Table Transformers for imputing textual attributes
- 22 October 2024
- Published by Elsevier in Pattern Recognition Letters
- Vol. 186, 258-264
Open AccessTable Transformers for imputing textual attributes
- Open Access
- 5 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Engineering in Medicine and Biology
- Vol. 6, 100-106
Breast Cancer Detection on Dual-View Sonography via Data-Centric Deep Learning
Goal: This study aims to enhance AI-assisted breast cancer diagnosis through dual-view sonography using a data-centric approach. Methods: We customize a DenseNet-based model on our exclusive dual-view breast ultrasound dataset to enhance the model's ability to differentiate between malignant and benign masses. Various assembly strategies are designed to integrate the dual views into the model input, contrasting with the use of single views alone, with a goal to maximize performance. Subsequently, we compare the model against the radiologist and quantify the improvement in key performance metrics. We further assess how the radiologist's diagnostic accuracy is enhanced with the assistance of the model. Results: Our experiments consistently found that optimal outcomes were achieved by using a channel-wise stacking approach incorporating both views, with one duplicated as the third channel. This configuration resulted in remarkable model performance with an area underthe receiver operating characteristic curve (AUC) of 0.9754, specificity of 0.96, and sensitivity of 0.9263, outperforming the radiologist by 50% in specificity. With the model's guidance, the radiologist's performance improved across key metrics: accuracy by 17%, precision by 26%, and specificity by 29%. Conclusions: Our customized model, withan optimal configuration for dual-view image input, surpassed both radiologists and existing model results in the literature. Integrating the model as a standalone tool or assistive aid for radiologists can greatly enhance specificity, reduce false positives, thereby minimizing unnecessary biopsies and alleviating radiologists' workload.
- 5 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Engineering in Medicine and Biology
- Vol. 6, 100-106
Open AccessBreast Cancer Detection on Dual-View Sonography via Data-Centric Deep Learning
Goal: This study aims to enhance AI-assisted breast cancer diagnosis through dual-view sonography using a data-centric approach. Methods: We customize a DenseNet-based model on our exclusive dual-view breast ultrasound dataset to enhance the model's ability to differentiate between malignant and benign masses. Various assembly strategies are designed to integrate the dual views into the model input, contrasting with the use of single views alone, with a goal to maximize performance. Subsequently, we compare the model against the radiologist and quantify the improvement in key performance metrics. We further assess how the radiologist's diagnostic accuracy is enhanced with the assistance of the model. Results: Our experiments consistently found that optimal outcomes were achieved by using a channel-wise stacking approach incorporating both views, with one duplicated as the third channel. This configuration resulted in remarkable model performance with an area underthe receiver operating characteristic curve (AUC) of 0.9754, specificity of 0.96, and sensitivity of 0.9263, outperforming the radiologist by 50% in specificity. With the model's guidance, the radiologist's performance improved across key metrics: accuracy by 17%, precision by 26%, and specificity by 29%. Conclusions: Our customized model, withan optimal configuration for dual-view image input, surpassed both radiologists and existing model results in the literature. Integrating the model as a standalone tool or assistive aid for radiologists can greatly enhance specificity, reduce false positives, thereby minimizing unnecessary biopsies and alleviating radiologists' workload.
- Open Access
Full-range Head Pose Geometric Data Augmentations
Many head pose estimation (HPE) methods promise the ability to create full-range datasets, theoretically allowing the estimation of the rotation and positioning of the head from various angles. However, these methods are only accurate within a range of head angles; exceeding this specific range led to significant inaccuracies. This is dominantly explained by unclear specificity of the coordinate systems and Euler Angles used in the foundational rotation matrix calculations. Here, we addressed these limitations by presenting (1) methods that accurately infer the correct coordinate system and Euler angles in the correct axis-sequence, (2) novel formulae for 2D geometric augmentations of the rotation matrices under the (SPECIFIC) coordinate system, (3) derivations for the correct drawing routines for rotation matrices and poses, and (4) mathematical experimentation and verification that allow proper pitch-yaw coverage for full-range head pose dataset generation. Performing our augmentation techniques to existing head pose estimation methods demonstrated a significant improvement to the model performance. Code will be released upon paper acceptance.
Open AccessFull-range Head Pose Geometric Data Augmentations
Many head pose estimation (HPE) methods promise the ability to create full-range datasets, theoretically allowing the estimation of the rotation and positioning of the head from various angles. However, these methods are only accurate within a range of head angles; exceeding this specific range led to significant inaccuracies. This is dominantly explained by unclear specificity of the coordinate systems and Euler Angles used in the foundational rotation matrix calculations. Here, we addressed these limitations by presenting (1) methods that accurately infer the correct coordinate system and Euler angles in the correct axis-sequence, (2) novel formulae for 2D geometric augmentations of the rotation matrices under the (SPECIFIC) coordinate system, (3) derivations for the correct drawing routines for rotation matrices and poses, and (4) mathematical experimentation and verification that allow proper pitch-yaw coverage for full-range head pose dataset generation. Performing our augmentation techniques to existing head pose estimation methods demonstrated a significant improvement to the model performance. Code will be released upon paper acceptance.
- Open Access
- 5 October 2022
- Published by MDPI AG in Bioengineering
- Vol. 9 (10) , 523
Automated Atrial Fibrillation Detection with ECG
An electrocardiography system records electrical activities of the heart, and it is used to assist doctors in the diagnosis of cardiac arrhythmia such as atrial fibrillation. This study presents a fast, automated deep-learning algorithm that predicts atrial fibrillation with excellent performance (F-1 score 88.2% and accuracy 97.3%). Our approach involves the pre-processing of ECG signals, followed by an alternative representation of the signals using a spectrogram, which is then fed to a fine-tuned EfficientNet B0, a pre-trained convolution neural network model, for the classification task. Using the transfer learning approach and with fine-tuning of the EfficientNet, we optimize the model to achieve highly efficient and effective classification of the atrial fibrillation.
- 5 October 2022
- Published by MDPI AG in Bioengineering
- Vol. 9 (10) , 523
Open AccessAutomated Atrial Fibrillation Detection with ECG
An electrocardiography system records electrical activities of the heart, and it is used to assist doctors in the diagnosis of cardiac arrhythmia such as atrial fibrillation. This study presents a fast, automated deep-learning algorithm that predicts atrial fibrillation with excellent performance (F-1 score 88.2% and accuracy 97.3%). Our approach involves the pre-processing of ECG signals, followed by an alternative representation of the signals using a spectrogram, which is then fed to a fine-tuned EfficientNet B0, a pre-trained convolution neural network model, for the classification task. Using the transfer learning approach and with fine-tuning of the EfficientNet, we optimize the model to achieve highly efficient and effective classification of the atrial fibrillation.