pith. sign in

OFlow: Injecting Object-Aware Temporal Flow Matching for Robust Robotic Manipulation

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

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.

citation-role summary

background 1

citation-polarity summary

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

roles

background 1

polarities

background 1

representative citing papers

Focusable Monocular Depth Estimation

cs.CV · 2026-05-12 · unverdicted · novelty 6.0

FocusDepth is a prompt-conditioned framework that fuses SAM3 features into Depth Anything models via Multi-Scale Spatial-Aligned Fusion to improve target-region depth accuracy on the new FDE-Bench.

citing papers explorer

Showing 1 of 1 citing paper.

  • Focusable Monocular Depth Estimation cs.CV · 2026-05-12 · unverdicted · none · ref 29 · internal anchor

    FocusDepth is a prompt-conditioned framework that fuses SAM3 features into Depth Anything models via Multi-Scale Spatial-Aligned Fusion to improve target-region depth accuracy on the new FDE-Bench.