|
Learning to Learn
Hi, I am Toby Yang, also go by the name Yuzhe Yang (阳雨哲). I am currently a final-year CS undergrad at the Chinese University of Hong Kong, Shenzhen, and a visiting student at the University of California, Santa Barbara, where I work with Prof. Xin Eric Wang. Throughout my undergrad studies at CUHK-Shenzhen, I have been fortunate to be advised by Prof. Benyou Wang and to collaborate closely with Prof. Honghai Yu’s team at Nanjing University. I was also a researcher of TheFinAI, led by Jimin Huang. Prior to that, I had the opportunity to work with Prof. Jianfeng Mao. I have published several papers at top-tier conferences including NeurIPS, EMNLP, NAACL, ICCV, and received the Best Paper Award at ICLR workshop. My research spans multiple areas with a focus on: Human-AI Interaction (UCFE-Benchmark), Multi-Agent System (TwinMarket), AI for Scientific Applications (Open-FinLLMs), Trustworthy NLP (SAE-free), and Socially Aware NLP. Currently, I am seeking a PhD position (2026 Fall). I am also open to research collaborations. If you are interested in my work or would like to discuss potential collaboration opportunities, please feel free to reach out and schedule time with me. Email: |
Learning to Learn
|
|
09/2025: One paper (TwinMarket) was accepted to NeurIPS 2025. See you in San Diego! 🌊 08/2025: One paper (SAE-free) was accepted to EMNLP 2025. 06/2025: One paper (FDPT) was accepted to ICCV 2025. See you in Hawaii! 🌴 05/2025: Invited talk at Wisemodel.cn (Special Session by FreedomAI Team in CUHK-Shenzhen). 04/2025: TwinMarket won the Best Paper Award 🏆 at the Advances in Financial AI Workshop @ ICLR 2025. •••
|
|
My vision is to build reliable and trustworthy AI systems that serve as a bridge between machine intelligence and human society. I am dedicated to enhancing the social intelligence of (vision) language models, empowering them to not only understand the principles of the physical world but also to gain insight into complex social environments, enabling reliable and meaningful interactions with humans. |
|
Discover more on Publications page or Google Scholar. (* indicates equal contribution) TwinMarket: A Scalable Behavioral and Social Simulation for Financial MarketsProceedings of NeurIPS 2025 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 UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models Findings of NAACL 2025 A User-Centric framework designed to evaluate LLMs' ability to handle complex financial tasks Paper / Code / Dataset Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models Proceedings of EMNLP 2025 Enhance LLM reasoning by steering activations via a novel SAE-free method using Chain-of-Thought features, without external data Paper FDPT: Federated Discrete Prompt Tuning for Black-Box Visual-Language Models Proceedings of ICCV 2025 Federated prompt tuning approach for black-box visual-language models Paper |
|
CUHK-Shenzhen NLP Group
2024.06 – Present
Undergraduate Research Assistant Advised by Prof. Benyou Wang and Dr. Yan Hu Best Paper Award & Travel Grant Award (ICLR 2025 Workshop) 
School of Management & Engineering, Nanjing University
2024.08 – 2025.01
Undergraduate Research Assistant Advised by Prof. Honghai Yu 
School of Data Science, CUHK-Shenzhen
2023.08 – 2024.06
Undergraduate Research Assistant Advised by Prof. Jianfeng Mao Undergraduate Research Award (2024, 2025) |
|
📸 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. 
|
|
|