Assistant Professor, Brown University
4 papers at NeurIPS 2025
A novel intrinsic motivation method based on world-model memory mismatch enables embodied agents to exhibit robust autonomous behaviors that closely match whole-brain neural data from zebrafish.
A data-driven nonlinear control-theoretic framework to characterize subsystem interactions, leveraging a deep-learning method to learn dynamical system Jacobians.
We parallelize MCMC over the sequence, yielding more than order of magnitude wall-clock speedup on sampling.
Nonlinear systems whose future behavior is not overly sensitive to small perturbations can be efficiently parallelized; whereas unpredictable dynamical systems cannot be efficiently parallelized.
