Learning to Assist: Collaborative VLAs for Implicit Human-Robot Collaboration

arXiv:2606.12475 · cs.RO · Submitted 2026-06-10 · Read on arXiv

cs.RO

Submitted: 2026-06-10

Updated: 2026-10-13

Comments: CoRL 2026

Project page: https://learning-to-assist.github.io

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

Terminology

• Steering — 2× in this paper · explained in 2 episodes
• Inference-Time Steering — 1× in this paper · explained in 2 episodes
• Vision-Language-Action (VLA) Models — 1× in this paper · explained in 2 episodes

Sources

• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• OpenVLA: An Open-Source Vision-Language-Action Model
• mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs
• World Action Models are Zero-shot Policies
• On the Opportunities and Risks of Foundation Models
• Yell At Your Robot: Improving On-the-Fly from Language Corrections
• OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning
• IntentionVLA: Generalizable and Efficient Embodied Intention Reasoning for Human-Robot Interaction
• Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models
• To the Noise and Back: Diffusion for Shared Autonomy
• Mixture of Horizons in Action Chunking
• VLA Knows Its Limits: Adaptive Execution Horizons for Robot Policies
• Multi-Cycle Spatio-Temporal Adaptation in Human-Robot Teaming
• Probabilistically Safe Robot Planning with Confidence-Based Human Predictions
• Robotic Assistant: Completing Collaborative Tasks with Dexterous Vision-Language-Action Models
• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
• VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference
• SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies
• A General Framework for Inference-time Scaling and Steering of Diffusion Models
• MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation

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