VIS-MPU-Agent

AI & ML interests

Our interests span a broad range of artificial intelligence and machine learning domains, including: Computer Vision: Developing algorithms to enable machines to interpret and understand visual information, such as image classification, object detection, semantic segmentation, and generative models for visual content. Multimodal Large Models: Exploring large-scale models that integrate and reason across diverse data modalities (text, images, audio, video), focusing on cross-modal understanding, alignment, and efficient fusion mechanisms. Multimodal Intelligent Agents: Building agents that perceive, process, and act on multimodal inputs in dynamic environments, leveraging computer vision, natural language processing, and sensor data for context-aware decision-making. GUI Agents: Developing AI agents specialized in interacting with graphical user interfaces (GUIs) to automate tasks, interpret user intent, and execute actions across interfaces. Reinforcement Learning (RL): Investigating algorithms that enable agents to learn optimal behaviors through environmental interaction, including deep RL, multi-agent RL, and integration with other modalities for versatile decision-making. And more, encompassing other emerging areas and intersections within AI & ML.

Team members 3