NeurIPS 2026
MCD
Reusable motor skills
Learning Reusable Motor Motifs for Continuous Animal Behavior Modeling
Discovering reusable motor motifs from offline behavior data and composing them into continuous, interpretable policies.
Research output
Publications
Robot learning, reusable motor skills, and brain-inspired learning. My name is highlighted in the author lists.
NeurIPS 2026
EISep
Stable learning & control
Leveraging Dale’s Principle as an Inductive Bias in Recurrent Neural Networks
Learnable excitatory–inhibitory separation improves recurrent learning stability, continual learning, and reinforcement learning control.
ICML 2025
SWIRL
Learning behavioral intentions
Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal Behaviors
Recovering time-varying, history-dependent rewards from long behavioral trajectories with switching inverse reinforcement learning.