Hi 👋, I am Yuan Tian. I'm a Ph.D. candidate in the Department of Computer Science at Purdue University, advised by Professor Tianyi Zhang.
My research spans machine learning, natural language processing, and human-computer interaction.
During my PhD, I'm applying grounding
theory and anchoring
effect to make generative AI more controllable and accurate. I'm particularly interested in building AI agents for
database and coding __Example Scenario
An agent iteratively generates executable code (e.g., Python, SQL), interacts with environments (e.g., databases, test cases, humans) to gather verification signals, and adapt to environments.
I believe inference-time verification and large-scale memory are key to advancing AI intelligence to the next level. Beyond that, I am broadly interested in pushing AI intelligence forward across multiple dimensions, including model architecture, reasoning pipelines, synthetic data, and interactive designs.
In addition to my individual research, I am working on an
NSF-funded project
, where I am building a large-scale knowledge
graph for AI security.
I interned twice at
Adobe
as an applied scientist, where I mainly worked on building the
AI
assistant for Adobe
Experience Platform.
📢 I am seeking full-time AI research positions. Feel free to contact me at tian211@purdue.edu. Thank you!
HuggingFace
