0%
Schedule February
👋 Welcome to my Blog.

Hi, I'm Yanqiao Chen

|

This is my blog for my technical notes, project updates and publications.

🎯

Research Focus

Context Engineering and Reinforcement Learning. Apart from that, I am also interested in the scaling optimization method design and the theoretical aspects of deep learning and the interpretability of large language models.

🎓
Final Review
期末复习专栏
📂
Browse Columns
按专栏浏览笔记

📝 What's New?

View All →

🎓 Final Reviews

View All →

💼 My Work in Research

View All →
Jul2026 - Sep2026 ICLR 2027 Under Preparation

Individual Researcher

First Author

Working on a regularization-based study of Vision-Language-Action (VLA) models, targeting ICLR 2027. The project introduces a regularization term into VLA training to improve the behavior and robustness of learned policies, with both a principled motivation and empirical evaluation.

My contribution covers the method design, the theoretical motivation, and the experimental evaluation. Specifics are kept anonymous while the paper is under review.

Keywords / skills involved: vision-language-action models, robot learning, regularization, imitation learning, policy training.

Mar2026 - Present AAAI 2027 Under Preparation

SUSTech Theory of AI Lab

Undergraduate Researcher

I work on the theoretical analysis of randomised search heuristics and genetic programming, under the supervision of Prof. Pietro Simone Oliveto and in collaboration with Mingxuan Yin. The current direction focuses on runtime analysis and generalisation bounds, with a full paper targeting AAAI 2027; an extended journal version is planned for submission to a venue such as IEEE Transactions on Evolutionary Computation (TEVC).

My contribution includes deriving runtime bounds, formalising proof arguments, and exploring how algorithmic parameters affect generalisation in evolutionary search.

Keywords / skills involved: probabilistic methods, drift theorems, runtime analysis, evolutionary algorithms, mathematical proofs.

🚀 Recently, I am working on...

View All →

🤝 Keep in Touch...