PINT: A Unified Model with Shared Predictive Intent for Robot Manipulation
cs.RO
Submitted: 2026-10-12
Updated: 2026-10-12
Comments: 29 pages, 9 figures, 17 tables. Project page: https://zgca-hmi-lab.github.io/PINT
Code: https://github.com/ZGCA-HMI-Lab/PINT
Project page: https://zgca-hmi-lab.github.io/PINT
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- OpenVLA: An Open-Source Vision-Language-Action Model
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- Wan: Open and Advanced Large-Scale Video Generative Models
- World Action Models are Zero-shot Policies
- Fast-WAM: Do World Action Models Need Test-time Future Imagination?
- Motubrain: An Advanced World Action Model for Robot Control
- InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization
- World Tokens: Enhancing Embodied Policies with Training-Time World Modeling
- RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
- StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
- FAST: Efficient Action Tokenization for Vision-Language-Action Models
- PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models
- Feeling the Unexpected: ResTacVLA for Contact-Rich Manipulation via Residual Tactile Representation
- CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models
- UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent
- DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
- GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation
- WorldVLA: Towards Autoregressive Action World 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
- 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