<ul><li>Researchers propose a transformer-based sign language production (SLP) framework.</li><li>A pose autoencoder encodes sign poses into a compact latent space using an articulator-based disentanglement strategy.</li><li>A non-autoregressive transformer decoder predicts latent representations from sentence-level text embeddings.</li><li>Channel-aware regularization aligns predicted latent distributions with ground-truth encodings using KL-divergence loss.</li></ul>

Disentangle and Regularize: Sign Language Production with Articulator-Based Disentanglement and Channel-Aware Regularization

Discover more