The Language and Vision Laboratory (LVLab), formerly the Learning and Vision Lab, is a cutting-edge research group focused on advancing the foundations of artificial intelligence through the integrated study of vision, language, and other modalities. In response to the paradigm shift brought by foundation models, our research agenda has expanded beyond single-modality learning toward multimodal representation, reasoning, and generation. We aim to develop general-purpose intelligent systems capable of structured perception, proactive inference, and continual adaptation across complex environments. Our work lies at the intersection of multimodal learning, large-scale model optimization, and cognitive-level decision-making, with the goal of bridging low-level sensory input and high-level intelligence. We actively welcome collaboration and participation from researchers and students who are passionate about shaping the next generation of AI.