Robust robotic manipulation requires not only predicting how the scene evolves over time, but also recognizing task-relevant objects in complex scenes. However, existing VLA models face two limitations. They typically act only on the current frame, while future prediction and object-aware reasoning are often learned in separate latent spaces. We propose OFlow (injecting Object-Aware Temporal Flow Matching into VLAs), a framework that addresses both limitations by unifying temporal foresight and object-aware reasoning in a shared semantic latent space. Our method forecasts future latents with temporal flow matching, factorizes them into object-aware representations that emphasize physically relevant cues while filtering task-irrelevant variation, and conditions continuous action generation on these predictions. By integrating OFlow into VLA pipelines, our method enables more reliable control under distribution shifts. Extensive experiments across LIBERO, LIBERO-Plus, MetaWorld, and SimplerEnv benchmarks and real-world tasks demonstrate that object-aware foresight consistently enhances robustness and success.
@article{arxiv.2604.17876,
title = {OFlow: Injecting Object-Aware Temporal Flow Matching for Robust Robotic Manipulation},
author = {Kuanning Wang and Ke Fan and Chenhao Qiu and Zeyu Shangguan and Yuqian Fu and Yanwei Fu and Daniel Seita and Xiangyang Xue},
journal= {arXiv preprint arXiv:2604.17876},
year = {2026}
}