Object-Centric Conditioning for Visuomotor Flow Matching

arXiv:2609.24155 · cs.RO · Submitted 2026-09-21 · Read on arXiv

cs.RO

Submitted: 2026-09-21

Updated: 2026-09-29

Comments: Accepted to the 10th Conference on Robot Learning (CoRL 2026)

Code: https://github.com/Li-Jijie/Object-Centric-Visuomotor-Flow

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Grounding — 32× in this paper · explained in 3 episodes
• Flow Matching — 29× in this paper · explained in 8 episodes
• Robustness — 28× in this paper · explained in 5 episodes
• Cascaded Foveated Module — 10× in this paper
• Representation Learning — 6× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Consistency — 5× in this paper · explained in 3 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• Regularization — 4× in this paper · explained in 3 episodes
• Spatial Broadcast Decoder — 4× in this paper
• Visual Grounding — 4× in this paper · explained in 2 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Decoupling — 2× in this paper · explained in 2 episodes
• Distillation — 2× in this paper · explained in 2 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Latent Space — 2× in this paper · explained in 7 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Action Chunking — 1× in this paper · explained in 1 episode
• Computational overhead — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Entanglement — 1× in this paper · explained in 3 episodes
• Exponential Moving Average (EMA) — 1× in this paper · explained in 2 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Flow Matching Model — 1× in this paper · explained in 2 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Latent Dynamics — 1× in this paper · explained in 2 episodes
• Normalizing Flow — 1× in this paper · explained in 3 episodes
• Normalizing Flows — 1× in this paper · explained in 4 episodes
• Optimal Transport — 1× in this paper · explained in 5 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
• Score-Based Generative Modeling through Stochastic Differential Equations
• Flow Matching for Generative Modeling
• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
• Action-to-Action Flow Matching
• RT-1: Robotics Transformer for Real-World Control at Scale
• WarmPrior: Straightening Flow-Matching Policies with Temporal Priors
• MONet: Unsupervised Scene Decomposition and Representation
• Conditional Object-Centric Learning from Video
• Focusing on What Matters: Object-Agent-centric Tokenization for Vision Language Action models
• ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models
• GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
• PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction
• Clutter-Robust Vision-Language-Action Models through Object-Centric and Geometry Grounding
• SlotVLA: Towards Modeling of Object-Relation Representations in Robotic Manipulation
• STORM: Slot-based Task-aware Object-centric Representation for robotic Manipulation
• SOLD: Slot Object-Centric Latent Dynamics Models for Relational Manipulation Learning from Pixels
• Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs
• VITA: Vision-to-Action Flow Matching Policy

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies