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

TL;DR

LangForce introduces a Bayesian framework with latent action queries to improve language grounding and out-of-distribution generalization in vision-language-action models for robot manipulation.

Contribution

It proposes a novel Bayesian decomposition approach with learnable latent queries to enhance instruction following and mitigate dataset bias.

Findings

Achieves 11.3% improvement on OOD benchmarks

Effectively penalizes vision-only shortcuts in policies

Significantly enhances generalization in complex tasks

Abstract

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. To address this, we propose LangForce, a novel framework that enforces instruction following via Bayesian decomposition. By introducing learnable Latent Action Queries, we construct a dual-branch architecture to estimate both a vision-only prior $p(a \mid v)$ and a language-conditioned posterior $\pi(a \mid v, \ell)$. We then optimize the policy to maximize the conditional Pointwise Mutual Information (PMI) between actions and instructions. This objective effectively penalizes the vision shortcut and rewards actions that explicitly explain the language command. Without requiring new data, LangForce significantly improves generalization. Extensive experiments across on SimplerEnv and RoboCasa demonstrate substantial gains, including an 11.3% improvement on the challenging OOD SimplerEnv benchmark, validating the ability of our approach to robustly ground language in action.