Media Recognition and Understanding (MAGUS) Group focuses on technological innovation and applications in the field of multi-modal media intelligent processing. We are dedicated to tackling core technical challenges in this domain, advancing machine intelligence, and empowering various industries to improve quality and efficiency. Recently, we have made steady progress in key areas such as embodied perception and decision-making, visual media semantic understanding, physical simulation and reasoning, and intelligent pharmacy. We have published several papers in high-impact journals and conferences including TIP, MM, AAAI, and TCSVT. Our team has also achieved outstanding results in technical challenges hosted by top-tier conferences such as MM, ICME, and ECCV, repeatedly winning championships and runner-up positions. We also prioritize the transformation and application of our research outcomes, providing technical support and services to several industry-leading enterprises, including CSSC, SGCC, and China Telecom.