SOURCE-LINKED INTELLIGENCE

Temporal Forcing: 4D Representation Alignment for Vision-Language-Action Models

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Recent vision-language-action (VLA) methods improve manipulation performance by aligning their representations with 3D scene geometry. However, these methods often struggle with long-horizon manipulation and observation aliasing between visually similar states due to a lack of temporal information: the 3D scene geometry captures only the current state, rather than how it has evolved over time. To resolve this, we present Temporal Forcing, a 4D representation alignment method for VLA models. Specifically, we first introduce a history pathway that enables a vanilla VLA model to summarize observa

Read original source ↗ Open in workspace

recordType

paper

region

Global