AI for Science
Using LLMs and Agentic AI for scientific literature mining, time-series and tabular data modeling, and autonomous research agents for scientific task solving and discovery.
My research develops cognitive intelligence methods for complex data mining, centered on LLMs and Agentic AI, and driven by the dual foundations of time-series observations and scientific knowledge. My methodological focus lies in context representation and reasoning, aiming to build predictive intelligence for complex systems through multimodal semantic understanding, slow-thinking temporal reasoning, and autonomous agentic interaction.
Developing autonomous interactive learning for large language models, including environment-interactive Agentic RL, tool-augmented reasoning, multi-agent orchestration, and continual capability evolution through context, knowledge, and memory.
Developing context-aware predictive intelligence, with a focus on multimodal context representation, slow-thinking reasoning, uncertainty-aware forecasting, and autonomous agentic interaction.
Building context-aware predictive intelligence for complex systems through multimodal context representation, slow-thinking temporal reasoning, uncertainty-aware forecasting, and autonomous agentic interaction.
This direction develops agent-ready scientific knowledge intelligence through LLM-driven literature mining, multimodal scientific document understanding, evidence-grounded reasoning, and scientific knowledge integration for predictive modeling and decision support.
Using LLMs and Agentic AI for scientific literature mining, time-series and tabular data modeling, and autonomous research agents for scientific task solving and discovery.
Studying online user modeling and personalized recommender systems for Internet applications, with a focus on user behavior understanding, preference learning, and context-aware recommendation.