ACE ROBOTICS Open-Sources Real-Time Generative World Model Kairos 3.0-4B
- Published in News from Asia
- A native world model built from the ground up for embodied intelligence, Kairos 3.0-4B delivers exceptional physics-consistent deep understanding and cross-embodiment generalization, enabling a single "brain" to drive robots of multiple form factors.
- Kairos 3.0-4B leverages a unified "multi-modal understanding-generation-prediction" architecture for physical-level deep understanding, long-horizon dynamic interaction, precise action control, and long-horizon interaction — 7-minute coherent interaction videos set a new industry benchmark.
- As a lightweight 4B-parameter model, Kairos 3.0-4B outperforms mainstream embodied world models while delivering industry-leading inference efficiency. It achieves real-time edge generation on the THOR platform with a1:1.5 ratio of generation time to video duration, leading performance across both cloud and edge environments.
- Kairos 3.0-4B achieves top-ranking accuracy across multiple authoritative benchmarks. Furthermore, leveraging model capabilities and inference tooling, its inference speed is 72 times faster than Cosmos 2.5, setting a new global performance record for embodied world models.
SHANGHAI, CHINA - Media OutReach Newswire - 13 March 2026 - ACE ROBOTICS announced the open-source release of Kairos 3.0-4B, the industry's first native world model for embodied intelligence to realize unified "multi-modal understanding-generation-prediction" within a single architecture. As the technical cornerstone of the company's "Human-Centric" ACE Embodied Intelligence R&D Paradigm, Kairos 3.0-4B is designed from the ground up for real-world robotic operation — integrating physical laws, human behavior, and real robot actions to deliver physics-consistent deep understanding of the real world.
The prevailing approach to embodied world models has largely involved retrofitting general-purpose large language or vision models with motion interfaces. Kairos 3.0-4B takes a fundamentally different path. Rather than appending motion capabilities onto existing model architectures, it is built from the architectural level around the fundamental physical and causal laws that govern real-world environments, constructing a unified world-understanding framework capable of cross-embodiment generalization. By embedding causal reasoning chains directly into its decision-making process, the model transcends behavioral imitation and achieves what ACE ROBOTICS defines as physical-level deep understanding — enabling robots to not only know what to do, but to understand why. Its core breakthrough lies in the deep integration of three categories of data: real robot interaction data, structured human behavioral data, and chain-of-thought reasoning data, effectively breaking down multi-source data barriers and significantly improving the reuse efficiency of real-world data.
A landmark achievement of this release is Kairos 3.0-4B's real-time edge deployment capability. Deployed on the NVIDIA Jetson Thor T5000 platform at 517 TFLOPs, it is the world's first embodied world model to achieve real-time generation on edge hardware — achieving a 1.5x faster-than-real-time generation speed on the THOR platform — and the first capable of directly driving physical robot bodies for real-world task execution through native edge deployment. The model issues full-body control commands spanning upper limbs, fingers, and lower limbs without intermediate control layers, enabling robots to move from "capable of performing" to genuinely "capable of working."
Kairos 3.0-4B also delivers a breakthrough in long-horizon interaction. By combining its unified architecture with Agent-based hierarchical planning and a self-reflective iterative optimization mechanism, the model generates coherent future-state predictions up to 7 minutes in length while maintaining full scene coherence and physical fidelity throughout — setting a new industry benchmark for long-horizon embodied interaction and opening new pathways for embodied intelligence training and deployment.
On the A800 GPU benchmark, Kairos 3.0-4B's inference speed surpasses NVIDIA Cosmos 2.5 by 72 times, setting a new global performance record for embodied world models. This performance is delivered with a lightweight footprint of just 4B parameters and 23.5GB of VRAM — a fraction of Cosmos 2.5's 70.2GB requirement — demonstrating that efficiency and capability need not be in tension and fundamentally challenging the assumption that larger parameters are a prerequisite for superior performance. The model has also achieved top rankings across three authoritative global benchmarks: PAI-Bench-robot, co-developed by Georgia Tech and CMU; WorldModelBench-robot TI2V, introduced at CVPR 2025; and NVIDIA GEAR Lab's DreamGen Bench, outperforming all evaluated models on physical consistency and instruction-following metrics.
Supporting seamless cross-embodiment deployment across single-arm, dual-arm, and dexterous hand configurations with no additional per-embodiment training required, Kairos 3.0-4B is compatible with major hardware platforms including Agilex PIPER, Unitree G1, and Galaxy G1. Kairos 3.0-4B is now available on Github (https://github.com/kairos-agi/kairos-sensenova) and Hugging Face (https://huggingface.co/kairos-agi/kairos-sensenova-common).
Hashtag: #ACEROBOTICS
https://www.linkedin.com/company/acerobotics/posts/?feedView=all&viewAsMember=true｜
https://x.com/ace_robotics
The issuer is solely responsible for the content of this announcement.
About ACE ROBOTICS – Equipping robots with intelligent "brains" and engaging "souls"
ACE ROBOTICS is a pioneering robotics company dedicated to advancing the field of embodied intelligence. Founded by SenseTime co-founder Wang Xiaogang, the company has brought together a team of young, globally scarce AI scientists and industry experts to focus on embodied intelligence. Through breakthrough technological innovations and deep insights into embodied intelligence scenarios, we aim to empower robots with the ability to autonomously understand and explore the physical world, thereby accelerating their commercial implementation.
The company pioneered the ACE R&D paradigm and built a vision-based "environmental data engine, real-world cognition, embodied interaction generalization" technology chain. Using full spatiotemporal and multi-perspective environmental capture as its engine, along with Kairos 3.0 – China's first open-source and commercially applicable world model – plus the Embodied Foundation Model as its technical backbone, ACE ROBOTICS addresses core industry challenges such as data scarcity, common sense gaps, poor generalization, and limited versatility. Simultaneously, the company unveiled its flagship A1 Embodied Super Brain Module, accelerating the large-scale commercial deployment of embodied intelligence across diverse scenarios.
ACE ROBOTICS is both a technology pioneer and an ecosystem builder. Through strategic cooperation with top hardware manufacturers, cloud service providers, and vertical scenario partners, we have broken through the "model-hardware-scenario" industrial deadlock, providing standardized and customized solutions that are driving the development of China's embodied intelligence industry.
Daily Bulletin
