FlowVLA: Visual Chain of Thought-based Motion Reasoning for Vision-Language-Action Models

TL;DR

FlowVLA introduces a motion reasoning paradigm for vision-language-action models, explicitly modeling dynamics via optical flow to improve visual prediction coherence and policy efficiency in robotics tasks.

Contribution

The paper proposes Visual CoT and FlowVLA, a novel autoregressive Transformer that explicitly reasons about motion dynamics before frame prediction, enhancing physical plausibility and policy performance.

Findings

Produces more coherent, physically plausible visual forecasts.

Achieves state-of-the-art policy performance on robotics benchmarks.

Improves sample efficiency in policy learning.

Abstract

Many Vision-Language-Action (VLA) models are built upon an internal world model trained via next-frame prediction ``$v_t \rightarrow v_{t+1}$''. However, this paradigm attempts to predict the future frame's appearance directly, without explicitly reasoning about the underlying dynamics. \textbf{This lack of an explicit motion reasoning step} often leads to physically implausible visual forecasts and inefficient policy learning. To address this limitation, we introduce the \textbf{Visual Chain of Thought (Visual CoT)}, a paradigm that compels the model to first reason about \textbf{motion dynamics} before generating the future frame. We instantiate this paradigm by proposing \textbf{FlowVLA}, an autoregressive Transformer that explicitly materializes this reasoning process as ``$v_t \rightarrow f_t \rightarrow v_{t+1}$'', where $f_t$ is an intermediate optical flow prediction that inherently encodes motion. By forcing the model to first follow the motion plan encoded by $f_t$, this process inherently \textbf{aligns the pre-training objective of dynamics prediction with the downstream task of action generation.} We conduct experiments on challenging robotics manipulation benchmarks, as well as real-robot evaluations. Our FlowVLA not only generates \textbf{more coherent and physically plausible visual predictions}, but also achieves state-of-the-art policy performance with \textbf{substantially improved sample efficiency}, pointing toward a more principled foundation for world modeling in VLAs. Project page: https://irpn-lab.github.io/FlowVLA/