**Abstract:** A significant advancement has been made by Professor Li Manrong’s team from the School of Chemistry at Sun Yat-sen University in the precise prediction and synthesis of exotic magnetoelectric materials under extreme conditions. This breakthrough, published in npj Quantum Materials, showcases the team's innovative approach combining big data mining and high-throughput computational methods to predict and experimentally realize a novel R3-phase polar magnet, Co3TeO6, under high temperature and pressure conditions. **Key Events, People, Locations, and Time Elements:** - **Event:** Development of a method to predict and synthesize exotic magnetoelectric materials, specifically the R3-phase polar magnet Co3TeO6. - **People:** Professor Li Manrong and his team from Sun Yat-sen University, along with collaborators from Southeast University, the National Institute of Standards and Technology (NIST), the Chinese Spallation Neutron Source, Skolkovo Institute of Science and Technology (Russia), University of Cologne (Germany), Rutgers University (USA), Brookhaven National Laboratory (USA), and Beijing Institute of Technology. - **Location:** Sun Yat-sen University, Guangzhou, China, and various international research institutions. - **Time:** Recent publication in 2020. **Summary:** High-temperature and high-pressure (HTHP) conditions are widely recognized as powerful tools in the synthesis of novel materials, particularly in the fields of physics, chemistry, geology, and materials science. Under these extreme conditions, the interatomic and intermolecular distances of substances are significantly reduced, leading to enhanced interactions and structural phase transitions. These changes can result in unique electromagnetic properties. Notable examples include the discovery of high-temperature superconductivity in H2S at 90 GPa and 203 K by German scientists in 2015, the transformation of lanthanum hydride into a superconductor at 170 GPa and 250 K by the Drozdov team in 2019, and the observation of room-temperature superconductivity in a hydrogen compound at 267 GPa and 288 K by Ranga P. Dias et al. in 2020. Exotic perovskite materials, known for their multifunctional magnetic and electric properties, have been limited due to their highly distorted structures (small tolerance factor t). However, the application of HTHP techniques has recently expanded the range of these materials available for study. Traditional HTHP synthesis methods often rely on trial and error, requiring numerous repetitive experiments, which are time-consuming and resource-intensive. The ability to precisely synthesize specific exotic perovskite phases under extreme conditions is crucial for accelerating the discovery of new materials and properties. Professor Li Manrong’s team at Sun Yat-sen University has addressed this challenge by integrating big data mining and high-throughput computational methods to predict and synthesize exotic perovskite materials. They focused on the compound A3TeO6, where A represents different elements such as Mg, Mn, Fe, Co, Ni, Cu, and Zn. Through extensive calculations, they predicted that Co3TeO6 would transform into a polar R3 phase (HP-CTO) when subjected to pressures above 5 GPa. This phase is expected to exhibit multiferroic properties, characterized by a complex interplay between magnetic and electric orders. The team successfully synthesized HP-CTO under conditions of 5 GPa and 1123 K, confirming the theoretical predictions. HP-CTO showed two magnetic transition points at T1 ~ 24 K and T2 ~ 58 K. Below T2, the material exhibited a c-axis spiral magnetic order, as determined by powder neutron diffraction experiments. Further characterization revealed an intrinsic dielectric constant anomaly at T2 ~ 58 K, indicating pyroelectric behavior rather than ferroelectricity. The material also demonstrated a coupling between magnetic and electric properties, likely due to magnetostriction. The research underscores the potential of combining computational predictions with experimental synthesis to efficiently identify and produce novel materials with desired properties. Big data mining and high-throughput calculations can rapidly predict stable crystal structures, even under complex conditions, thereby accelerating the discovery of materials that are difficult to obtain through conventional methods. This approach not only shortens the research and development cycle but also reduces experimental costs. The study was supported by the National Natural Science Foundation of China (NSFC), the Guangdong Innovation and Entrepreneurship Team Program, and involved significant contributions from various international experts. Professor Dong Shuai’s group at Southeast University participated in the high-throughput computational research. Dr. Huang Qingzhen from NIST, and Dr. He Lunhua and Dr. Chen Jie from the Chinese Spallation Neutron Source, provided guidance on neutron diffraction data collection. Dr. Alexandra A. Savina and Dr. Artem M. Abakumov from Skolkovo Institute of Science and Technology analyzed the magnetic structure. Dr. Christoph P. Grams and Dr. Joachim Hemberger from the University of Cologne conducted magnetic and dielectric property tests. Dr. Mark Croft from Rutgers University, and Dr. Steven Ehrlich and Dr. Syed Khalid from Brookhaven National Laboratory, performed XANES testing and analysis. Professor Hong Jiawang and Associate Researcher Wang Xueyun from Beijing Institute of Technology conducted PFM testing. Professor Huang Feng and Dr. Wang Biao from Sun Yat-sen University’s School of Materials Science were responsible for the preparation of Co3TeO6 precursors and stability testing. This collaborative effort highlights the importance of interdisciplinary research and international cooperation in advancing the field of materials science. The team’s success in predicting and synthesizing HP-CTO under extreme conditions provides a valuable reference for the design and development of exotic perovskite materials with superior magnetic and electric properties. Future work aims to extend this methodology to other material systems, enhancing the exploration of chemical space through computational techniques and the development of machine learning models to build comprehensive material databases.