The field of smart systems is moving towards a greater emphasis on spatial awareness and context-aware interaction. Researchers are exploring new methods to enable smart devices to understand and respond to their environment, allowing for more intuitive and natural user interaction. This includes the development of spatial context-aware control systems, which can interpret and respond to natural language commands that reference specific locations or objects. Furthermore, there is a growing recognition of the importance of spatial reasoning capabilities in Multimodal Large Language Models (MLLMs), and the need for dedicated attention to fundamental modifications in the current MLLM development approach. Noteworthy papers include:

• Intelligence of Things: A Spatial Context-Aware Control System for Smart Devices, which introduces a novel spatial context-aware control system that enhances smart home automation through intuitive spatial reasoning.
• Think Hierarchically, Act Dynamically: Hierarchical Multi-modal Fusion and Reasoning for Vision-and-Language Navigation, which proposes a Multi-level Fusion and Reasoning Architecture to enhance the agent's ability to reason over visual observations, language instructions and navigation history.