The journal Nature, published on the 30th, published a cover article on the research results of the brain computing research team from the Department of Precision Instruments at Tsinghua University: they have developed the world's first brain complementary visual chip, "Tianmu Xin.". The team has previously developed the heterogeneous fusion brain computing "Tianjixin", which marks a fundamental breakthrough in China's two important directions of brain computing and brain perception. With the rapid development of artificial intelligence, unmanned systems such as autonomous driving and embodied intelligence are constantly being promoted and applied in real society. In these intelligent systems, visual perception plays a crucial role as the core pathway for obtaining information. In the open world, these intelligent systems not only need to handle large amounts of data, but also need to deal with various extreme events, such as sudden dangers during driving, drastic changes in lighting at tunnel entrances, and strong flash interference at night. Traditional visual perception chips are often limited by "power consumption walls" and "bandwidth walls", which often face problems such as distortion, failure, or high latency when dealing with these scenarios, seriously affecting the stability and security of the system. In response to these issues, the research team focuses on brain like visual perception chip technology and proposes a new paradigm of complementary dual pathway brain like visual perception based on visual primitives. Drawing on the basic principles of the human visual system, the open world visual information is decomposed into information representations based on visual primitives, and these primitives are organically combined to mimic the characteristics of the human visual system, forming two complementary and information complete visual perception pathways. On this basis, the team developed the world's first brain like complementary visual chip, "Tianmou Core," which not only breaks through the performance bottleneck of traditional visual perception paradigms, but also can efficiently cope with various extreme scenarios, ensuring the stability and security of the system. (Lai Xin She)