Applied thought partnership

Schematic of representational-alignment-aware machine teaching: a teacher and a learner with internal representations, with the teacher selecting hints conditioned on the learner's representations so that the learner improves. — The GRADE system: machine teachers aligned to a learner's representations produce better hints. From *Representational Alignment Supports Effective Teaching* (Sucholutsky et al. 2025).

The applied face of the program. We translate AITP science into systems that work alongside people in specific domains, with each project chosen so the application also feeds back into the core science.

Education. Representational Alignment Supports Effective Teaching (Sucholutsky et al. 2025; the GRADE paper) shows that aligning machine teachers to learner representations improves hint quality. Adjacent work spans K-12 collaborations with the Children Helping Science network and graduate-level mathematics tutoring through the MATH-AI workshop community.

Music. Collaborative interactive editing tools for music, in development with collaborators across NYU, Cornell, and the music-cognition community.

Math. AI partners for graduate-level mathematical research.

Robotics. The LGA series on language-guided abstraction for robot learners, published at ICLR, HRI, and CoRL 2024.