Decoupling Vision, Language, and Action for Efficient Multi-Task Robot Policies

arXiv:2609.18374 · cs.RO · Submitted 2026-09-16 · Read on arXiv

cs.RO

Submitted: 2026-09-16

Updated: 2026-09-17

Code: https://github.com/Apollo-Lab-Yale/decoupled-embodiment-model

Terminology

• Flow Matching — 7× in this paper · explained in 8 episodes
• Transformer — 7× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Action Chunking — 4× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Decoupled Embodiment Model — 3× in this paper
• Decoupling — 2× in this paper · explained in 2 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Vision-Language Model — 2× in this paper
• Vision-Language Model (VLM) — 2× in this paper · explained in 3 episodes
• Action Flow — 1× in this paper · explained in 1 episode
• Active Perception — 1× in this paper · explained in 2 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• IEEE International Conference on Robotics and Automation — 1× in this paper
• Most Vision-Language-Action — 1× in this paper
• Vision-Language-Action (VLA) Models — 1× in this paper · explained in 2 episodes

Sources

• GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
• DINOv3
• NeoBERT: A Next-Generation BERT
• BAKU: An Efficient Transformer for Multi-Task Policy Learning
• Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
• SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
• VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching
• PRISM-DP: Spatial Pose-based Observations for Diffusion-Policies via Segmentation, Mesh Generation, and Pose Tracking
• Optimizing Active Perception for Learning Simultaneous Viewpoint Selection and Manipulation with Diffusion Policy
• Artificial Foveated Perception for Mitigating Shortcut Learning in Robotic Foundation Models
• mmBERT: A Modern Multilingual Encoder with Annealed Language Learning
• TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM
• ReactVLA: Fast and Lightweight Reactive Robot Manipulation via Improved Mean Flow Action Generation
• Mean-Flow based One-Step Vision-Language-Action
• Let It Be Simple: One-Step Action Generation for Vision-Language-Action Models
• DAM-VLA: Decoupled Asynchronous Multimodal Vision Language Action model

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
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving