7 papers
Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulation
Junjin Xiao, Dongyang Li, Yandan Yang +9
This paper tackles spatial perception and manipulation challenges in Vision-Language-Action (VLA) models. To address depth ambiguity from monocular input, we leverage a pre-trained…
World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training
Junjin Xiao, Yandan Yang, Xinyuan Chang +5
Vision-Language-Action (VLA) models trained via imitation learning suffer from significant performance degradation in data-scarce scenarios due to their reliance on large-scale dem…
ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning
Yandan Yang, Shuang Zeng, Tong Lin +11
Building general-purpose embodied agents across diverse hardware remains a central challenge in robotics, often framed as the ''one-brain, many-forms'' paradigm. Progress is hinder…
ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment
Yuzhi Chen, Ronghan Chen, Dongjie Huo +11
Video-based world models offer a powerful paradigm for embodied simulation and planning, yet state-of-the-art models often generate physically implausible manipulations - such as o…
Learning Explicit Continuous Motion Representation for Dynamic Gaussian Splatting from Monocular Videos
Xuankai Zhang, Junjin Xiao, Shangwei Huang +2
We present an approach for high-quality dynamic Gaussian Splatting from monocular videos. To this end, we in this work go one step further beyond previous methods to explicitly mod…
Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos
Xuankai Zhang, Junjin Xiao, Qing Zhang
This paper presents a unified framework that allows high-quality dynamic Gaussian Splatting from both defocused and motion-blurred monocular videos. Due to the significant differen…