The field of imitation learning and robotics is rapidly advancing, with a focus on developing more efficient and effective methods for training agents to replicate expert behavior. Recent research has emphasized the importance of incorporating additional sources of information, such as tactile sensing and multimodal perception, to improve performance in complex tasks. Furthermore, there is a growing trend towards using skill-centric approaches, which involve abstracting actions into higher-level behaviors to enable more flexible and adaptive learning. Noteworthy papers in this area include: A Model-Based Approach to Imitation Learning through Multi-Step Predictions, which proposes a novel framework for imitation learning using predictive modeling. MOSAIC: A Skill-Centric Algorithmic Framework for Long-Horizon Manipulation Planning, which introduces a unified framework for planning long-horizon motions using a set of predefined skills. Physically Consistent Humanoid Loco-Manipulation using Latent Diffusion Models, which uses latent diffusion models to generate realistic RGB human-object interaction scenes for guiding humanoid loco-manipulation planning. Latent Diffusion Planning for Imitation Learning, which proposes a modular approach for imitation learning using a planner and an inverse dynamics model operating over a learned latent space.