I am first-year PhD student @ SJTU, supervised by Siheng Chen. My general research interest lies in LLM Agents and Embodied Agents. Currently, I focus on Tool-Augmented LLM Agents and Humanoid Robot Control. If you are interested in me and seek for cooperation, feel free to email me at youngsoul0731@gmail.com.
🔥 News
- 2024.07: 🎉🎉 The paper entitled “ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerance” has been accepted by CIKM ‘24: 33rd International Conference on Information and Knowledge Management. I serve as a co-first author.
📝 Publications
CIKM 2024
ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerance
Ling-Hao Chen, Yuanshuo Zhang, et al.
- We fist introduce error-resilient mechanism to graph representation learning.
📝 Preprints
Preprint
GNNs as Predictors of Agentic Workflow Performances
Yuanshuo Zhang, Yuchen Hou, Bohan Tang, Shuo Chen, Muhan Zhang, Xiaowen Dong, Siheng Chen
- We propose FLORA to use GNNs as predictors of agentic workflow performance thus avoiding repeated LLM invocations for evaluation.
📖 Educations
- 2021.09 - 2025.06, School of Electronic Engineering, Xidian University.
💻 Internships
- 2024.08 - 2025.07, BIGAI, Beijing, China.