R.I.P.
๐ป
Ghosted
OmniVLA-RL: A Vision-Language-Action Model with Spatial Understanding and Online RL
April 20, 2026 ยท Grace Period ยท + Add venue
Authors
Haoxiang Jie, Yaoyuan Yan, Xiangyu Wei, Kailin Wang, Hongjie Yan, Zhiyou Heng, Daocheng Chen
arXiv ID
2604.17706
Category
cs.RO: Robotics
Citations
0
Abstract
Visual-Language-Action (VLA) models represent a paradigm shift in embodied AI, yet existing frameworks often struggle with imprecise spatial perception, suboptimal multimodal fusion, and instability in reinforcement learning. To bridge these gaps, we propose OmniVLA-RL, a novel architecture that leverages a Mix-of-Transformers (MoT) design to synergistically integrate reasoning, spatial, and action experts. Furthermore, we introduce Flow-GSPO, which reformulates flow matching as a Stochastic Differential Equation (SDE) process and integrates it with Group Segmented Policy Optimization (GSPO) to enhance action precision and training robustness. Extensive evaluations on the LIBERO and LIBERO-Plus benchmarks demonstrate that OmniVLA-RL significantly outperforms state-of-the-art methods, effectively overcoming the fundamental limitations of current VLA models.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Robotics
R.I.P.
๐ป
Ghosted
AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles
๐
๐
The Cartographer
A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehicles
๐
๐
The Cartographer
Unmanned Aerial Vehicles: A Survey on Civil Applications and Key Research Challenges
๐
๐
The Cartographer
A Survey of Autonomous Driving: Common Practices and Emerging Technologies
R.I.P.
๐ป
Ghosted