Zexin (Jason) Xu

👨‍💻 About Me: I am an alumnus of The Ohio State University, where I earned my M.S. in Computer Science and Engineering under the expert guidance of Dr. Yu Su. Driven by a vision to leverage AI for the betterment of humanity, my academic interests has spanned across NLP, Vision & Language, Embodied AI, and Large Language Models. During my master’s program, I led the software engineering team for SalsaBot, contributing significantly to the first Amazon Alexa Prize Simbot Challenge. Prior to pursuing my master’s degree, I obtained my B.S. degree in Computer Science and Engineering from The Ohio State University.

📚 Beyond Computer Science: I am also deeply interested in Educational Technology. I have collaborated with educational researchers, focusing on the application of AI, including GPT models, in educational contexts. Currently, I’m part of an exciting venture with UC Irvine on a project named TimeWise. Our team has successfully advanced to phase two of the Tools Competition, a significant achievement considering the selection rate of 800 out of 2000 submissions!

🎮 Gamer at Heart: Outside of my professional pursuits, I am deeply passionate about gaming. As a hard-core World of Warcraft player, I’ve achieved the rank of a Rank 1 Restoration Shaman! My love for gaming also extends to Genshin Impact, where I’m captivated by its storytelling and artistry. Board games are another avenue of enjoyment; I frequently host game nights featuring favorites like Everdell, Root, Brass: Birmingham, and etc. In addition to these digital and tabletop adventures, I enjoy playing basketball, badminton, and swimming.

🤝 If you’re on a mission to blend AI with real-world solutions, and you value a team member who can bring both technical expertise and a dash of fun to the table, let’s connect! I’m all set to embark on the next phase of my professional journey, and I’d love to explore how we can create something awesome together.

NEWS

Dec 08, 2023	Project `TimeWise` selected into Phase 2 of the Tools Competition! 🥳
Jul 01, 2023	Completed the AWS Cloud Technical Essentials course. 🎉
May 15, 2023	Graduated from The Ohio State University with a M.S.! Go Buckeyes!

SELECTED PUBLICATIONS

CVPR

Towards a robust and generalizable embodied agent

Chan Hee Song , Jiaman Wu , Ju-Seung Byun , Zexin Xu , Vardaan Pahuja , Goonmeet Bajaj , Samuel Stevens , Ziru Chen , and Yu Su

In Embodied AI Workshop at CVPR , 2023

PDF
Languages
Exploring the Role of Artificial Intelligence in Facilitating Assessment of Writing Performance in Second Language Learning

Zilu Jiang , Zexin Xu , Zilong Pan , Jingwen He , and Kui Xie

Languages, 2023

Abs Bib PDF

This study examined the robustness and efficiency of four large language models (LLMs), GPT-4, GPT-3.5, iFLYTEK and Baidu Cloud, in assessing the writing accuracy of the Chinese language. Writing samples were collected from students in an online high school Chinese language learning program in the US. The official APIs of the LLMs were utilized to conduct analyses at both the T-unit and sentence levels. Performance metrics were employed to evaluate the LLMs’ performance. The LLM results were compared to human rating results. Content analysis was conducted to categorize error types and highlight the discrepancies between human and LLM ratings. Additionally, the efficiency of each model was evaluated. The results indicate that GPT models and iFLYTEK achieved similar accuracy scores, with GPT-4 excelling in precision. These findings provide insights into the potential of LLMs in supporting the assessment of writing accuracy for language learners.
@article{languages8040247, author = {Jiang, Zilu and Xu, Zexin and Pan, Zilong and He, Jingwen and Xie, Kui}, title = {Exploring the Role of Artificial Intelligence in Facilitating Assessment of Writing Performance in Second Language Learning}, journal = {Languages}, volume = {8}, year = {2023}, number = {4}, article-number = {247}, url = {https://www.mdpi.com/2226-471X/8/4/247}, issn = {2226-471X}, doi = {10.3390/languages8040247}, }