About me

Hi! I’m Yezeng Chen, a second year graduate student majored in computer science at School of Information Science and Technology, Shanghaitech University.

My research interests are about natural language processing and large language model. Currently, I am actively involved in an exciting project, with a special focus on AI for Chemistry (AI4Chem) and AI for Mathematics (AI4Math). I firmly believe that AI for Science/Math will change the future of scientific research. For more information, please refer to my resume. Should you have any questions, collaboration inquiries, or opportunities, please do not hesitate to contact me via email.

Education

Internship at XiaoYi, Huawei 2024.06-2025.12
M.E. in Computer Science and Technology, ShanghaiTech University, 2022.09-2025.06(estimated)
B.E. in Computer Science and Technology, ShanghaiTech University, 2018.09-2022.06

Publications

Y. Yangming, L. Chunxiao, C. YeZeng, D. Zijie and Z. Yi, Knowledge Discovery from Natural Languages: a Linguistic Dataset of 10K Kinship Relations, 2023 IEEE 6th International Conference on Big Data and Artificial Intelligence (BDAI), 2023
Haoyi Wu, Wenyang Hui, Yezeng Chen, Weiqi Wu, Kewei Tu, and Yi Zhou. 2023. Conic10K: A Challenging Math Problem Understanding and Reasoning Dataset. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 6444–6458, Singapore. Association for Computational Linguistics.
Chen, Z., Chen, Y., Han, J., Huang, Z., Qi, J., & Zhou, Y. (2024). An Empirical Study of Data Ability Boundary in LLMs’ Math Reasoning. arXiv preprint arXiv:2403.00799.
Chen, Y., Chen, Z., & Zhou, Y. (2024). Brain-Inspired Two-Stage Approach: Enhancing Mathematical Reasoning by Imitating Human Thought Processes. arXiv preprint arXiv:2403.00800.
X Li, Z Feng, Y Chen, W Dai, Z He, Y Zhou, S Jiao. Coeff-kans: A paradigm to address the electrolyte field with kans arXiv preprint arXiv:2407.20265, 2024
W Dai, Y Chen, Z Dai, Z Huang, Y Liu, Y Pan, B Song &… KALE-LM: Unleash The Power Of AI For Science Via Knowledge And Logic Enhanced Large Model arXiv preprint arXiv:2409.18695, 2024