The field of humanoid robotics is moving towards the development of more generalizable and natural interaction systems. Researchers are focusing on creating systems that can autonomously perform diverse interaction tasks while maintaining lifelike behaviors. This includes advancements in simulation training pipelines, real-world deployment systems, and motion imitation techniques. Noteworthy papers in this area include PhysHSI, which presents a physical-world humanoid-scene interaction system that enables humanoids to perform interactive tasks with high success rates and natural motion patterns. Another notable paper is Towards Adaptable Humanoid Control via Adaptive Motion Tracking, which introduces a novel motion tracking algorithm that enables adaptable humanoid control from a single reference motion, allowing for flexible time warping and improved imitation accuracy.