Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation
cs.RO
Submitted: 2026-10-01
Updated: 2026-10-01
Comments: 19 pages, 9 figures
Code: https://github.com/DAGroup-PKU/ViGAR
Project page: https://dagroup-pku.github.io/ViGAR
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Cosmos 3: Omnimodal World Models for Physical AI
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
- Large Video Planner Enables Generalizable Robot Control
- Robots Acquire Manipulation Skills in Seconds from a Single Human Video
- 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
- InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
- StableVLA: Towards Robust Vision-Language-Action Models without Extra Data
- BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- ${\pi}_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities
- DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
- Causal World Modeling for Robot Control
- RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
- Scaling World Model for Hierarchical Manipulation Policies
- HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining
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