GaitDynamics: A Foundation Model for Predicting Human Gait Dynamics Data driven-models are a promising solution to quantify gait dynamics with less cost and time compared with traditional lab-based experiments. Typical data-driven models are limited to a specific downstream task with fixed inputs and outputs. GaitDynamics is the first generative foundation model to quantify gait dynamics for different gait patterns. It is a flexible, scalable solution that is able to predict both motions and forces for human walking and running with partial or no input data. Postdoctoral fellow Tian Tan and colleagues from the NIH-funded Restore<http://restore.stanford.edu> and Mobilize<http://mobilize.stanford.edu> Centers and the Wu Tsai Human Performance Alliance<https://humanperformancealliance.org/> developed the model and have made it open-source. Access GaitDynamics code<https://github.com/stanfordnmbl/GaitDynamics> | Read preprint<https://pmc.ncbi.nlm.nih.gov/articles/PMC11957236/> Join a Workshop on Large-Scale Biomechanics at RehabWeek 2025 May 12-16, 2025, Chicago, IL, USA The Restore<http://restore.stanford.edu> and Mobilize<http://mobilize.stanford.edu> Centers are running a workshop at RehabWeek, "OpenCap and AddBiomechanics: Tools for Large-Scale Biomechanics Studies.” Join the workshop to learn how these tools enable rapid, accessible movement analysis—from measuring 3D human motion using smartphone videos with OpenCap<http://opencap.ai> to automating motion capture data processing with AddBiomechanics<http://addbiomechanics.org>. Through demos and hands-on tutorials, our team will demonstrate how these tools accelerate both lab-based and out-of-lab studies of hundreds of participants for movement screening, injury prevention, and monitoring rehabilitation. Learn more<https://rehabweek.org/wp-content/uploads/2025/01/OpenCap-and-AddBiomechanics-Tools-for-Large-Scale-Biomechanics-Studies.pdf> | Register for the conference<https://rehabweek.org/registration/> Apply to be a Reproducible Rehabilitation (ReproRehab) Program Fellow Submission Deadline: May 2, 2025 The Reproducible Rehabilitation (ReproRehab) program<https://www.reprorehab.usc.edu/> is an NIH-funded R25 research educational program designed to build a sustainable national workforce of rehabilitation researchers equipped with basic data science skills to improve reproducibility in research. Applications to become a ReproRehab fellow are now open. ReproRehab fellows participate in: (1) the in-person Reproducible Rehabilitation Research Summit<https://www.reprorehab.usc.edu/conference>, (2) a hands-on virtual bootcamp where rehabilitation researchers learn data science and open science skills to integrate into their own research in small pods of 8-10 learners with 2 teaching assistants, (3) self-guided learning, using resources on ReproRehabDB<https://reprorehabdb.usc.edu/>, a curated, searchable, rateable database of online courses and open-source datasets specifically for rehabilitation researchers. Apply<https://www.reprorehab.usc.edu/apply> to be either a learner (free to attend) or a teaching assistant (receive a $5,000 stipend). — OpenSim is supported by the Mobilize Center<https://mobilize.stanford.edu/>, an NIH Biomedical Technology Resource Center (grant P41 EB027060); the Restore Center<https://restore.stanford.edu/>, an NIH-funded Medical Rehabilitation Research Resource Network Center (grant P2C HD101913); and the Wu Tsai Human Performance Alliance <https://humanperformancealliance.org/> through the Joe and Clara Tsai Foundation. No longer want to receive these emails? Unsubscribe<https://lists.simtk.org/mailman/listinfo/opensim-announcement>