Robbyant, an embodied AI company within Ant Group, today announced the release of LingBot-VA 2.0, the industry’s first embodied-native video-action world model.

This release marks a key transition in robotics foundation models, shifting from repurposing digital world models to designing them natively for the physical world. Instead of relying on fine-tuned digital content generation models, LingBot-VA 2.0 is built from scratch to meet the original demands of dynamic modeling, causal prediction, and real-time execution in physical environments.

Integrating world models with embodied AI has been one of the major focuses of the AI industry. However, most mainstream approaches rely on video generation models designed for digital content, which are then fine-tuned for robot control. Because content creation prioritizes visual quality and creativity, while robot control requires execution efficiency and physical accuracy, this forced adaptation often leads to knowledge forgetting and reduced generalization.

LingBot-VA 2.0 takes a different approach. By pre-training from scratch using an autoregressive architecture, the model is designed to understand how an action will change the environment and to decide the next step based on that causal prediction.

Core Architectural Innovations

To achieve this, LingBot-VA 2.0 is built on four core designs:

• Semantic Visual-Action Tokenizer: A new visual encoder that aligns semantic and action information during visual compression, helping the model translate "understanding instructions" into "completing actions" more effectively.
• Strict Causal Pre-training: The model uses an autoregressive architecture from the beginning, ensuring that visual predictions and action generation strictly follow a one-way time sequence.
• Mixture of Experts (MoE): This architecture expands model capacity without sacrificing inference efficiency, balancing performance and speed.
• Enhanced Asynchronous Inference: This mechanism enables real-time closed-loop control, allowing robots to predict future states while executing actions and continuously corrects its next decisions using the latest real-world observations.

These designs solve the common industry challenge of low execution efficiency in embodied world models, delivering a real-time inference speed of 150 Hz on a single GPU. Furthermore, the model can generalize to new tasks using as few as 20 demonstrations through in-context learning without parameter updates.

A Complete Embodied-Native Full-Stack

LingBot-VA 2.0 serves as the capstone of Robbyant’s recent launch week, which introduced six models that together form a complete embodied-native full-stack for perception, world simulation, and action:

LingBot-Depth 2.0
LingBot-Vision
LingBot-VLA 2.0
LingBot-World 2.0
LingBot-Video
LingBot-VA 2.0

Zhu Xing, CEO of Robbyant, noted, “Robbyant will continue to explore new limits in embodied intelligence while accelerating the development of an open technology and application ecosystem to expedite robot deployment in industrial and real-world scenarios.”

About Robbyant

Robbyant is an embodied intelligence company within Ant Group, dedicated to advancing embodied intelligence through cutting-edge software and hardware technologies. Robbyant independently develops foundational large models for embodied AI and actively explores next-generation intelligent devices, aiming to create robotic companions and caregivers that truly understand and enhance people’s everyday lives and deliver reliable intelligent services across key use cases, such as elderly care, medical assistance, and household tasks.