Yiqi Zhu

Yiqi Zhu 朱奕祺

Ph.D. Student

Department of Computer Science and Technology

Institute for AI Industry Research

Tsinghua University

Twitter Google Scholar CV

About Me

Hi there! I am a first-year Computer Science Ph.D. Student at Tsinghua University, advised by Yang Liu and Peng Li and working on language agents. I obtained my bachelar's degree of Computer Science and Technology from Tsinghua University. I'm also a research intern at Tongyi Lab, Alibaba Group. I was once a visiting student at Carnegie Mellon University, where I had the opportunity to work with Graham Neubig.

My research interests broadly lie in large language models and agents. Currently, I am most interested in the following topics:
1) How to build robust language agents to complete challenging tasks (e.g. solve complicated coding tasks; facilitate scientific discovery)?
2) How to construct realistic environments for evaluating and training agents on real-world tasks?
3) How to utilize the generalization ability of (visual) foundation models in embodied scenarios and tasks?
If you are interested in my research or would like to collaborate, feel free to reach out!

Publications

Benchmarking General Mobile Assistants in Challenging Real-World Scenarios
Yiqi Zhu, Feiyu Gao, Jiaxing Fan, Jiahui Zeng, Minggang Wu, Chenliang Li, Haiyang Xu, Peng Li, Ming Yan, Yang Liu
Preprint Homepage Code Paper
Training Versatile Coding Agents in Synthetic Environments
Yiqi Zhu, Apurva Gandhi, Graham Neubig
Preprint Homepage Code Paper
CoSpace: Benchmarking Continuous Space Perception Ability for Vision-Language Models
Yiqi Zhu*, Ziyue Wang*, Can Zhang, Peng Li, Yang Liu
CVPR 2025 Homepage Code Paper
AIGS: Generating Science from AI-Powered Automated Falsification
Zijun Liu*, Kaiming Liu*, Yiqi Zhu*, Xuanyu Lei*, Zonghan Yang*, Zhenhe Zhang, Peng Li, Yang Liu
Tech Report Homepage Code Paper
State2State: Environment-Derived Mid-Training for LLM Agents
Xuanyu Lei, Yiqi Zhu, Chenliang Li, Kaiming Liu, Peng Li, Ming Yan, Jieping Ye, Ya-Qin Zhang, Yang Liu
Preprint Homepage Code Paper
Browse and Concentrate: Comprehending Multimodal Content via prior-LLM Context Fusion
Ziyue Wang*, Chi Chen*, Yiqi Zhu, Fuwen Luo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Maosong Sun, Yang Liu
ACL 2024 Oral Homepage Code Paper