Video-based Clinical Gait Analysis often suffers from poor generalization as models overfit environmental biases instead of capturing pathological motion. To address this, we propose BioGait-VLM, a tri-modal Vision-Language-Biomechanics framework for interpretable clinical gait assessment. Unlike standard video encoders, our architecture incorporates a Temporal Evidence Distillation branch to capture rhythmic dynamics and a Biomechanical Tokenization branch that projects 3D skeleton sequences into language-aligned semantic tokens. This enables the model to explicitly reason about joint mechanics independent of visual shortcuts. To ensure rigorous benchmarking, we augment the public GAVD dataset with a high-fidelity Degenerative Cervical Myelopathy (DCM) cohort to form a unified 8-class taxonomy, establishing a strict subject-disjoint protocol to prevent data leakage. Under this setting, BioGait-VLM achieves state-of-the-art recognition accuracy. Furthermore, a blinded expert study confirms that biomechanical tokens significantly improve clinical plausibility and evidence grounding, offering a path toward transparent, privacy-enhanced gait assessment.
@article{arxiv.2603.08564,
title = {BioGait-VLM: A Tri-Modal Vision-Language-Biomechanics Framework for Interpretable Clinical Gait Assessment},
author = {Erdong Chen and Yuyang Ji and Jacob K. Greenberg and Benjamin Steel and Faraz Arkam and Abigail Lewis and Pranay Singh and Feng Liu},
journal= {arXiv preprint arXiv:2603.08564},
year = {2026}
}