I am interested in AI systems that can keep improving after their initial training: systems that accumulate experience, decide when to look something up and when to internalize it, and explore productively when existing strategies fall short. The themes below are some of my current interests rather than a fixed research agenda.
Learning is, at its core, fitting data, so the data often matters most. I am interested in which data should be used for which tasks, how to organize it into curricula, and how to construct effective data for knowledge distillation.
What should a model absorb into its parameters, retain in external memory, or receive through context? I am interested in how stability, reuse, and forgetting should affect that choice.
A system can only learn from the experiences it produces. I am curious about agents that guide their own exploration and about whether useful exploration should happen in text, latent, or task-specific spaces.
Working on something in this space? I am always open to collaborations, so get in touch.