Previously, my research was focused on:
(1) Language Model: Human-AI Interaction (UCFE-Benchmark), Agent System (TwinMarket), AI for Scientific Applications (Open-FinLLMs), Trustworthy NLP (SAE-free)
(2) Data Mining: Spatial-Temporal Modeling (FAST-CA), Social Computing

My vision is to build reliable and trustworthy AI systems that bridge the gap between machines and the real world. My focus is on enabling (vision) language model to interact more reliable with humans and their environments, empowering them to understand and simulate the underlying principles of the world. Additionally, I strive to uncover the internal mechanisms of language model to demystify their "black-box" nature, making AI system more interpretable, transparent, and aligned with human values. Through my research, I hope to contribute to the development of AI systems that are not only intelligent but also responsible, ethical, and deeply integrated into our daily lives.

Discover more on Publications page or Google Scholar. (* indicates equal contribution)

Yuzhe Yang*, Yifei Zhang*, Minghao Wu*, et al.

Best Paper Award, ICLR 2025 Workshop on Advances in Financial AI

A multi-agent framework that leverages LLMs to simulate socio-economic systems

Paper / Code / Project Page

Yuzhe Yang*, Yifei Zhang*, Yan Hu*, et al.

Findings of NAACL 2025

A User-Centric framework designed to evaluate LLMs' ability to handle complex financial tasks

Paper / Code / Dataset

Jiaqi Wu, Simin Chen, Jing Tang, Yuzhe Yang, et al.

ICCV 2025

Federated prompt tuning approach for black-box visual-language models

Paper

📸 I am an amateur photographer with an interest in digital, film, and aerial photography, with a special passion for landscape photography 🏔️. You can find my photos on Unsplash 🎞️. Also, you can visit my HDR photo gallery.