Welcome to the TEA Lab

Welcome to the Thinking Embodied Agents (TEA) Lab at Virginia Tech! We build robots that operate in human environments rather than around them. We study how robots acquire and retain manipulation skills across their lifetime in unstructured settings, and how they model and adapt to the people working alongside them. We pair learned policies, such as language-conditioned, generative, and vision-language-driven approaches, with symbolic structure such as knowledge graphs, planners, and movement primitives, so that behavior generalizes from few demonstrations and stays inspectable enough to reason about safety and contact.

Hokies

News

Latest Updates

  • [September 2026] Two papers were accepted at NeurIPS 2026: “Learning When to Think: Adaptive Internal Computation for Reinforcement Learning” in the main conference, and our position paper “Neurosymbolic AI is a Strong Technical Foundation for Trustworthy, Deployable AI by Design”, with collaborators at Carnegie Mellon University, in the position paper track.
  • [September 2026] We are presenting three papers at IROS 2026: "From Local Corrections to Generalized Skills: Improving Neuro-Symbolic Policies with MEMO" in the main conference, “TRACT: Bimanual Cable Insertion via Tactile Tension Regulation” at the Touch-to-Action workshop, and “Learning Object-Centric Barrier Functions for Contact-Rich Interaction in Clutter” at the Learning and Formal Methods for Robotics workshop.
  • [August 2026] Hyeonbeen Lee, Sirui Zhan, and Haixin Jin join TEA Lab as PhD students this fall. Welcome!
  • [August 2026] Our work "Learning When to Stop: Prefix-Optimal Dynamic Diffusion Policies for Continuous Control" was presented at the “Reinforcement Learning Conference (RLC 2026)” in Montréal, where it learns a prefix value function at every denoising step to give diffusion policies a parameter-free stopping criterion at test time.
  • [August 2026] Our work "Influence-Guided Agent Adaptation for Dynamic Human–AI Collaboration" was presented at the “Continual Reinforcement Learning Workshop @ RLC 2026” in Montréal.
  • [June 2026] Our work "From Local Corrections to Generalized Skills: Improving Neuro-Symbolic Policies with MEMO", in collaboration with Collab at Virginia Tech, was accepted at “IROS 2026”. MEMO builds a retrieval-augmented skillbook from natural-language corrections, clustering feedback across users and tasks into generalized skill templates that a neuro-symbolic policy can retrieve at run time.
  • [August 2025] TEA Lab starts at Virginia Tech!
  • [June 2025] We received the best-paper award at the “Generative Models x HRI Workshop @ RSS 2025” for our work on “Modeling Latent Partner Strategies for Adaptive Zero-Shot Human-Agent Collaboration”
  • [June 2025] We received one of two best-paper awards at the “Workshop on Nonverbal Cues for Human-Robot Cooperative Intelligence at ICRA 2025” for our work on “Let Me Help You! Neuro-Symbolic Short-Context Action Anticipation”

Robots

People

Our lab brings together researchers from diverse backgrounds in robotics, machine learning, and formal methods. We are always looking for motivated students and researchers to join our team!

→ Meet our team