10 papers
SkelWAM: A Skeleton-Guided World-Action Model for Zero-Shot Cross-Embodiment Manipulation
Pengjun Niu, Yujia Xie, Rui Peng +2
Reusing manipulation experience across robot embodiments is important for scaling robot learning and reducing repeated task-specific data collection. However, changes in embodiment…
OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining
Yuran Wang, Siqiao Huang, Mingleyang Li +21
World-Action Models inherit world knowledge from video-generative priors, and channel it into executable control signals through embodied experience. Existing systems, however, are…
G0.5: One Autoregressive Stream for Robot Reasoning and Action
Yicheng Liu, Zibin Dong, Baijun Ye +24
The prevailing recipe for Vision-Language-Action (VLA) models couples a pretrained VLM with a separately trained flow-matching action expert. This makes the VLM a context encoder r…
Orca: The World is in Your Mind
Yihao Wang, Yuheng Ji, Mingyu Cao +54
We introduce Orca, an initial instantiation of a general world foundation model. Orca learns a unified world latent space from multimodal world signals and exposes it through multi…
Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control
Zunzhe Zhang, Runhan Huang, Yicheng Liu +3
Diffusion models and flow matching have become a cornerstone of robotic imitation learning, yet they suffer from a structural inefficiency where inference is often bound to a fixed…
Fast-WAM: Do World Action Models Need Test-time Future Imagination?
Tianyuan Yuan, Zibin Dong, Yicheng Liu +1
World Action Models (WAMs) have emerged as a promising alternative to Vision-Language-Action (VLA) models for embodied control because they explicitly model how visual observations…
VolumeDP: Modeling Volumetric Representation for Manipulation Policy Learning
Tianxing Zhou, Feiyang Xue, Zhangchen Ye +3
Imitation learning is a prominent paradigm for robotic manipulation. However, existing visual imitation methods map 2D image observations directly to 3D action outputs, imposing a…
FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization
Yicheng Liu, Shiduo Zhang, Zibin Dong +12
Autoregressive vision-language-action (VLA) models have recently demonstrated strong capabilities in robotic manipulation. However, their core process of action tokenization often…
DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoning
Tianyuan Yuan, Yicheng Liu, Chenhao Lu +3
Vision-Language-Action (VLA) models have recently shown impressive generalization and language-guided manipulation capabilities. However, their performance degrades on tasks requir…
Galaxea Open-World Dataset and G0 Dual-System VLA Model
Tao Jiang, Tianyuan Yuan, Yicheng Liu +7
We present Galaxea Open-World Dataset, a large-scale, diverse collection of robot behaviors recorded in authentic human living and working environments. All demonstrations are gath…