Skip to content
RobotWorld
← Back to Videos

Galaxea G0.5: One Autoregressive VLA for Reasoning and Action

Loading video
Loading video

Galaxea G0.5 unifies reasoning and action in one autoregressive stream, with a single transformer generating both reasoning and action tokens under the same objective.

VLAGalaxeaG0.5Vision-language-action (VLA)AutoregressiveEmbodied AIWorld Models
Category: research
Author: @robotsdigest
Date: 2026-08-13T00:00:00
Duration: 262.06s
Source: https://x.com/robotsdigest/status/2087967348561269170

Related Videos

Hydra-0 world model learns actions as pixel motion
0:05

Hydra-0 world model learns actions as pixel motion

@techniahqrobot · 778 views · 2026-09-02
Hydra-0NVIDIAVLA
τ0-VLA: Robot VLA that searches over subtask sequences at test time with a world model
3:33

τ0-VLA: Robot VLA that searches over subtask sequences at test time with a world model

@jiqizhixin · 681 views · 2026-08-07
VLAWorld ModelsEmbodied AI
RoboJEPA: The First Scaling Law for Multi-Embodiment World Models
1:06

RoboJEPA: The First Scaling Law for Multi-Embodiment World Models

@artemZholus · 212 views · 2026-10-10
World ModelsJEPAScaling Law
Long-WAM: Scaling World-Action Model Context to 19.2s in Real Time
2:38

Long-WAM: Scaling World-Action Model Context to 19.2s in Real Time

@AaronWeiHuang · 370 views · 2026-10-08
World-action modelsVLAReal-time control
Reka Releases Rho-1, a 19B Omni Model
1:00

Reka Releases Rho-1, a 19B Omni Model

@RekaAILabs · 425 views · 2026-10-05
Embodied AIOmni ModelMultimodal
FLUX 3 Action: Open-Weights 7B World Action Model
0:05

FLUX 3 Action: Open-Weights 7B World Action Model

@HuggingPapers · 758 views · 2026-09-23
World-action modelsVLARobot Learning

As an Amazon Associate, we earn from qualifying purchases.