Huitong(Jo) Pan
PhD Student, Temple University
Philadelphia, Pennsylvania
huitong.pan [AT] temple.edu
Bio
I am a final-year Ph.D. student in the Department of Computer and Information Science at Temple University, focusing on Natural Language Processing and Computer Vision. My research combines large-scale dataset development, entity recognition, and knowledge graph construction. I aim to bridge the gap between academic innovation and practical AI applications.
Full Resume in PDF.
Research Interests
My research focuses on creating innovative tools and methods in:1) Entity recognition and relation extraction in scientific texts.
2) Large-scale dataset development for specialized domains such as climate science.
3) Multimodal model evaluation with a focus on Vision-Language models.
4) Knowledge graph construction and integration using LLM techniques.
News
October 2024: Presented research on Climate Knowledge Graphs at a NASA workshop.
October 2024: Paper accepted at EMNLP 2024.
October 2024: Joined ARR-Oct 2024 as a reviewer.
September 2024: Joined EMNLP 2024 as a reviewer.
July 2024: Paper accepted in ECAI 2024. Released FlowLearn dataset for multimodal VQA tasks.
Publications
Most recent publications on Google Scholar.
‡ indicates equal contribution.
Climate Entity Recognition in Scientific Publications: Resource Development and LLM Performance Evaluation
Pan, Huitong, Qi Zhang, Eduard Dragut, Cornelia Caragea, and Longin Jan Latecki
Under Review, 2024
SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents
Zhang, Qi, et al.
Empirical Methods in Natural Language Processing (EMNLP), 2024
FlowLearn: Evaluating Large Vision-Language Models on Flowchart Understanding
Pan, Huitong, Qi Zhang, Eduard Dragut, Cornelia Caragea, and Longin Jan Latecki
27th European Conference on Artificial Intelligence (ECAI), 2024
SciDMT: A Large-Scale Corpus for Detecting Scientific Mentions
Pan, Huitong, Qi Zhang, Cornelia Caragea, Eduard Dragut, and Longin Jan Latecki
The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING), 2024, pp. 14407–14417
DMDD: A Large-Scale Dataset for Dataset Mentions Detection
Pan, Huitong, Qi Zhang, Eduard Dragut, Cornelia Caragea, and Longin Jan Latecki
Transactions of the Association for Computational Linguistics (TACL), vol. 11, 2023, pp. 1132–1146
SGUNET: Semantic Guided UNET For Thyroid Nodule Segmentation
Pan, Huitong, Quan Zhou, and Longin Jan Latecki
2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), 2021, pp. 630–634
Prostate Segmentation From 3D MRI Using A Two-Stage Model and Variable-Input Based Uncertainty Measure
Pan, Huitong, Brandon Yushan Feng, Quan Chen, Craig H. Meyer, and Xue Feng
IEEE 16th International Symposium on Biomedical Imaging (ISBI), 2019, pp. 468–471
A Self-Adaptive Network for Multiple Sclerosis Lesion Segmentation From Multi-Contrast MRI With Various Imaging Sequences
Feng, Yushan, Huitong Pan, Craig H. Meyer, and Xue Feng
IEEE 16th International Symposium on Biomedical Imaging (ISBI), 2019, pp. 472–475
Analyzing National and State Opioid Abuse Treatment Completion with Multilevel Modeling
Pan, Huitong, Sally Gao, K. Grant, Wendy M. Novicoff, and Hyojung Kang
Systems and Information Engineering Design Symposium (SIEDS), 2018, pp. 123–128
Climate Entity Recognition in Scientific Publications: Resource Development and LLM Performance Evaluation
Pan, Huitong, Qi Zhang, Eduard Dragut, Cornelia Caragea, and Longin Jan Latecki
Under Review, 2024
SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents
Zhang, Qi, et al.
Empirical Methods in Natural Language Processing (EMNLP), 2024
FlowLearn: Evaluating Large Vision-Language Models on Flowchart Understanding
Pan, Huitong, Qi Zhang, Eduard Dragut, Cornelia Caragea, and Longin Jan Latecki
27th European Conference on Artificial Intelligence (ECAI), 2024
SciDMT: A Large-Scale Corpus for Detecting Scientific Mentions
Pan, Huitong, Qi Zhang, Cornelia Caragea, Eduard Dragut, and Longin Jan Latecki
The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING), 2024, pp. 14407–14417
DMDD: A Large-Scale Dataset for Dataset Mentions Detection
Pan, Huitong, Qi Zhang, Eduard Dragut, Cornelia Caragea, and Longin Jan Latecki
Transactions of the Association for Computational Linguistics (TACL), vol. 11, 2023, pp. 1132–1146
SGUNET: Semantic Guided UNET For Thyroid Nodule Segmentation
Pan, Huitong, Quan Zhou, and Longin Jan Latecki
2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), 2021, pp. 630–634
Prostate Segmentation From 3D MRI Using A Two-Stage Model and Variable-Input Based Uncertainty Measure
Pan, Huitong, Brandon Yushan Feng, Quan Chen, Craig H. Meyer, and Xue Feng
IEEE 16th International Symposium on Biomedical Imaging (ISBI), 2019, pp. 468–471
A Self-Adaptive Network for Multiple Sclerosis Lesion Segmentation From Multi-Contrast MRI With Various Imaging Sequences
Feng, Yushan, Huitong Pan, Craig H. Meyer, and Xue Feng
IEEE 16th International Symposium on Biomedical Imaging (ISBI), 2019, pp. 472–475
Analyzing National and State Opioid Abuse Treatment Completion with Multilevel Modeling
Pan, Huitong, Sally Gao, K. Grant, Wendy M. Novicoff, and Hyojung Kang
Systems and Information Engineering Design Symposium (SIEDS), 2018, pp. 123–128
Vitæ
Full Resume in PDF.
-
Temple University 08/2019 - PresentResearch Assistant and Teaching Assistant
Department of Computer Science -
Temple University 2019 - PresentPh.D. Student
Focus: Natural Language Processing and Computer Vision -
Bosch 06/2021 - 08/2021Computer Vision Intern
Security Camera Team -
Springbok Analytics 06/2020 - 08/2020Research Scientist Intern
Medical Imaging Projects -
Springbok Analytics 07/2018 - 07/2019Data Scientist
Medical Image Analysis -
University of Virginia 2017 - 2018M.S. in Data Science
Graduate School of Arts & Sciences -
University of Virginia 2015 - 2017B.S. in Finance and Business Analytics
McIntire School of Commerce
Skills
Programming Languages: Python(Expert), Java, R, SQL, NOSQL, Spark SQL, MATLAB, Linux, HTML
Softwares: PyTorch, TensorFlow, CUDA, Pyspark, Scikit-Learn, NLTK, AWS, Docker, Git, Tableau