Research Interests
The Machine Perception and Learning (MAPLE) Lab has long been engaged in artificial intelligence, especially deep learning and its research in generative Artificial intelligence (AIGC), multimodal understanding and generative large models, 2D/3D intelligent creation, virtual reality, etc. 1.Intelligent creation based on generative artificial intelligence, such as GAN model, diffusion model, self-coding model and other deep learning theory and application;2.Multi-modal understanding and generation direction: video and image multi-modal generation and editing, 2D/3D scene and human body perception, reconstruction and interaction;3.Theory and application of artificial intelligence in 2D/3D virtual content creation, especially automatic 2D/3D virtual reality object and scene generation, non-rigid object generation and driving model with human main object;4.Embodied intelligence, including the design of general-purpose vision-language-action (VLA) models, robotic manipulation with robotic arms and dexterous hands, embodied agent reasoning, and world model–based VLA learning;
Group News
-
Feb 02, 2026 Accepted by ICLR 2026
Our Paper "Don't Settle Too Early: Self-Reflective Remasking for Diffusion Language Models" has been accepted by ICLR 2026. Congratulations to MAPLE Group!
-
Feb 02, 2026 Accepted by ICLR 2026
Our Paper "C-Evolve: Consensus-based Evolution for Prompt Groups" has been accepted by ICLR 2026. Congratulations to MAPLE Group!
-
Sep 19, 2025 Accepted by NeurIPS 2025
Our Paper "Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models" has been accepted by NeurIPS 2025. Congratulations to MAPLE Group!

