MIMIC-MJX: Neuromechanical Emulation of Animal Behavior.

The primary output of the nervous system is movement and behavior. While recent advances have democratized pose tracking during complex behavior, kinematic trajectories alone provide only indirect access to the underlying control processes. Here we present MIMIC-MJX, a framework for learning biologically-plausible neural control policies from kinematics. MIMIC-MJX models the generative process of motor control by training neural controllers that learn to actuate biomechanically-realistic body models in physics simulation to reproduce real kinematic trajectories. We demonstrate that our implementation is accurate, fast, data-efficient, and generalizable to diverse animal body models. Policies trained with MIMIC-MJX can be utilized to both analyze neural control strategies and simulate behavioral experiments, illustrating its potential as an integrative modeling framework for neuroscience.

Authors

Institutions

Publication Details

Journal
PubMed
Published
2025-12-02
Primary Topic
Zebrafish Biomedical Research Applications
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

MIMIC-MJX: Neuromechanical Emulation of Animal Behavior.

David Labonte, Blake A. Richards, Steven W. Flavell, Talmo Pereira et al.
PubMed
Zebrafish Biomedical Research Applications
article

MIMIC-MJX: Neuromechanical Emulation of Animal Behavior.

David Labonte, Blake A. Richards, Steven W. Flavell, Talmo Pereira, Joshua Park, C. Y. Zhang, Bingni W. Brunton, Adam J. Lee, Ayesha Thanawalla, Richa Bhatt, Hendrik Beck, Kee Wui Huang, Aaditya Prasad, Bence P. Ölveczky, Akira Nagamori, Fabian Plum, Diego Aldarondo, Elliott T. T. Abe, Eiman Azim, Eric Leonardis, Yuanjia Yang, Jason Foat, Kaiwen Bian, Hutton Saunders, Aidan Sirbu, Emil Wärnberg
article en

Abstract

The primary output of the nervous system is movement and behavior. While recent advances have democratized pose tracking during complex behavior, kinematic trajectories alone provide only indirect access to the underlying control processes. Here we present MIMIC-MJX, a framework for learning biologically-plausible neural control policies from kinematics. MIMIC-MJX models the generative process of motor control by training neural controllers that learn to actuate biomechanically-realistic body models in physics simulation to reproduce real kinematic trajectories. We demonstrate that our implementation is accurate, fast, data-efficient, and generalizable to diverse animal body models. Policies trained with MIMIC-MJX can be utilized to both analyze neural control strategies and simulate behavioral experiments, illustrating its potential as an integrative modeling framework for neuroscience.

PubMed
Canadian Institute for Advanced Research (CA), Montreal Neurological Institute and Hospital (CA), Salk Institute for Biological Studies (US), Howard Hughes Medical Institute (US), Harvard University (US), University of Washington (US), Harvard University Press (US), University of California San Diego (US), Mila - Quebec Artificial Intelligence Institute (CA), Imperial College London (GB), McGill University (CA), Massachusetts Institute of Technology (US)
Openalex Percentile: Top 59%
Zebrafish Biomedical Research Applications
OpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.