Patrick Cheong-Iao Pang

Rongsheng Wang, Yaofei Duan, ChanTong Lam et al.

General large language models (LLMs) such as ChatGPT have shown remarkable success. However, such LLMs have not been widely adopted for medical purposes, due to poor accuracy and inability to provide medical advice. We propose IvyGPT, an LLM based on LLaMA that is trained and fine-tuned with high-quality medical question-answer (QA) instances and Reinforcement Learning from Human Feedback (RLHF). After supervised fine-tuning, IvyGPT has good multi-turn conversation capabilities, but it cannot perform like a doctor in other aspects, such as comprehensive diagnosis. Through RLHF, IvyGPT can output richer diagnosis and treatment answers that are closer to human. In the training, we used QLoRA to train 33 billion parameters on a small number of NVIDIA A100 (80GB) GPUs. Experimental results show that IvyGPT has outperformed other medical GPT models.

Yiming Luo, Patrick Cheong-Iao Pang, Shanton Chang

In the information era, how learners find, evaluate, and effectively use information has become a challenging issue, especially with the added complexity of large language models (LLMs) that have further confused learners in their information retrieval and search activities. This study attempts to unpack this complexity by combining exploratory search strategies with the theories of exploratory learning to form a new theoretical model of exploratory learning from the perspective of students' learning. Our work adapts Kolb's learning model by incorporating high-frequency exploration and feedback loops, aiming to promote deep cognitive and higher-order cognitive skill development in students. Additionally, this paper discusses and suggests how advanced LLMs integrated into information retrieval and information theory can support students in their exploratory searches, contributing theoretically to promoting student-computer interaction and supporting their learning journeys in the new era with LLMs.

Rongsheng Wang, Haoming Chen, Ruizhe Zhou et al.

Existing research has demonstrated that refining large language models (LLMs) through the utilization of machine-generated instruction-following data empowers these models to exhibit impressive zero-shot capabilities for novel tasks, without requiring human-authored instructions. In this paper, we systematically investigate, preprocess, and integrate three Chinese instruction-following datasets with the aim of enhancing the Chinese conversational capabilities of Mixtral-8x7B sparse Mixture-of-Experts model. Through instruction fine-tuning on this carefully processed dataset, we successfully construct the Mixtral-8x7B sparse Mixture-of-Experts model named "Aurora." To assess the performance of Aurora, we utilize three widely recognized benchmark tests: C-Eval, MMLU, and CMMLU. Empirical studies validate the effectiveness of instruction fine-tuning applied to Mixtral-8x7B sparse Mixture-of-Experts model. This work is pioneering in the execution of instruction fine-tuning on a sparse expert-mixed model, marking a significant breakthrough in enhancing the capabilities of this model architecture. Our code, data and model are publicly available at https://github.com/WangRongsheng/Aurora

Yaofei Duan, Tao Tan, Zhiyuan Zhu et al.

Fetal ultrasound (US) examinations require the acquisition of multiple planes, each providing unique diagnostic information to evaluate fetal development and screening for congenital anomalies. However, obtaining a comprehensive, multi-plane annotated fetal US dataset remains challenging, particularly for rare or complex anomalies owing to their low incidence and numerous subtypes. This poses difficulties in training novice radiologists and developing robust AI models, especially for detecting abnormal fetuses. In this study, we introduce a Flexible Fetal US image generation framework (FetalFlex) to address these challenges, which leverages anatomical structures and multimodal information to enable controllable synthesis of fetal US images across diverse planes. Specifically, FetalFlex incorporates a pre-alignment module to enhance controllability and introduces a repaint strategy to ensure consistent texture and appearance. Moreover, a two-stage adaptive sampling strategy is developed to progressively refine image quality from coarse to fine levels. We believe that FetalFlex is the first method capable of generating both in-distribution normal and out-of-distribution abnormal fetal US images, without requiring any abnormal data. Experiments on multi-center datasets demonstrate that FetalFlex achieved state-of-the-art performance across multiple image quality metrics. A reader study further confirms the close alignment of the generated results with expert visual assessments. Furthermore, synthetic images by FetalFlex significantly improve the performance of six typical deep models in downstream classification and anomaly detection tasks. Lastly, FetalFlex's anatomy-level controllable generation offers a unique advantage for anomaly simulation and creating paired or counterfactual data at the pixel level. The demo is available at: https://dyf1023.github.io/FetalFlex/.

Qi-Qiao He, Patrick Cheong-Iao Pang, Yain-Whar Si

Although transfer learning is proven to be effective in computer vision and natural language processing applications, it is rarely investigated in forecasting financial time series. Majority of existing works on transfer learning are based on single-source transfer learning due to the availability of open-access large-scale datasets. However, in financial domain, the lengths of individual time series are relatively short and single-source transfer learning models are less effective. Therefore, in this paper, we investigate multi-source deep transfer learning for financial time series. We propose two multi-source transfer learning methods namely Weighted Average Ensemble for Transfer Learning (WAETL) and Tree-structured Parzen Estimator Ensemble Selection (TPEES). The effectiveness of our approach is evaluated on financial time series extracted from stock markets. Experiment results reveal that TPEES outperforms other baseline methods on majority of multi-source transfer tasks.

Patrick Cheong-Iao Pang, Robert P. Biuk-Aghai, Simon Fong et al.

Treemaps have been used in information visualisation for over two decades. They make use of nested filled areas to represent information hierarchies such as file systems, library catalogues, etc. Recent years have witnessed the emergence of visualisations that resemble geographic maps. In this paper we present a study that compares the performance of one such map-like visualisation with the original two forms of the treemap, namely nested and non-nested treemaps. Our study employed a mixed-method evaluation of accuracy, speed and usability (such as the ease-of-use and helpfulness of understanding the information). We found that accuracy was highest for the map-like visualisations, followed by nested treemaps and lastly non-nested treemaps. Task performance was fastest for nested treemaps, followed by non-nested treemaps, and then map-like visualisations. For usability, nested treemaps was considered slightly more helpful than map-like visualisations while non-nested performed poorly. We conclude that the results regarding accuracy are promising for the use of map-like visualisations in tasks involving the visualisation of hierarchical information, while non-nested treemap are favoured in tasks requiring speed.