Presented Beyond Task and Motion Planning: Hierarchical Planning for General-Purpose Robot Skills at ICRA 2026.

Released TAM: Torque Adaptation Module for Robust Motion Transfer in Manipulation, a torque-level adaptation module for transferring manipulation policies across robots.

Context-Sensitive Abstractions for Reinforcement Learning with Parameterized Actions was accepted at AAAI 2026.

Co-chaired the 3rd Workshop on Learning Efficient Abstractions for Planning (LEAP) at CoRL 2025.

From the Real World to Logic and Back: Learning Symbolic World Models for Long Horizon Planning appeared at CoRL 2025.

Joined the Allen Institute for AI (Ai2) as a Research Scientist, working with Dieter Fox on scaling robot data generation and hierarchical vision-language-action models.

SkillWrapper received the Best Paper Award at the ICRA 2025 Workshop on Language and Semantics of Task and Motion Planning.

Started as a Postdoctoral Researcher at Brown University with George Konidaris.

Defended my Ph.D. thesis, Autonomously Learning World-Model Representations for Efficient Robot Planning, at Arizona State University.