LangForce: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries

Understand

Vision-Language-Action (VLA) models have shown promise in robot manipulation but often struggle to generalize to new instructions or complex multi-task scenarios.

• We identify a critical pathology in current training paradigms where goal-driven data collection creates a dataset bias.
• In such datasets, language instructions are highly predictable from visual observations alone, causing the conditional mutual information between instructions and actions to vanish, a phenomenon we term Information Collapse.
• Consequently, models degenerate into vision-only policies that ignore language constraints and fail in out-of-distribution (OOD) settings.