About Me
About Me
I am a robotics researcher working at the intersection of world models, cognitive robotics, and autonomous planning. I am interested in how robots can act through sparse, task-relevant internal representations rather than relying solely on dense reconstruction or reactive control.
My current work centers on intent-driven planning through sparse internal structure. In the long term, I aim to integrate reinforcement-learning-driven cognitive skill templates with latent world models, enabling robots to develop more autonomous and adaptive intelligence in complex environments.
- Cognitive Robotics
- World Representation
- Deep Reinforcement Learning
- Robotic Middleware (ROS/ROS2)
- LLM/VLM for Robotics
MEng Computer Technology
Central China Normal University
MSc Computer Science
University of Wollongong
BSc Computer Science and Technology
Huaiyin Institute of Technology
- Sparse Latent World Representation
I study how task-relevant and semantically grounded structures can be distilled from high-dimensional perceptual inputs. Rather than relying on dense reconstruction alone, this line of work explores sparse internal representations that preserve behavioral relevance while reducing computational cost.
- Cognitive Skill Templates
I explore how symbolic abstraction and large language models can be combined into cognitive systems for robots. This direction aims to enable robots to reason over scene context, execute actions, and reflect on errors during embodied interaction.
- Latent Representation Autoregression
I investigate how autoregressive latent representations can support future-oriented reasoning in sparse latent spaces. This formulation aims to enable long-horizon spatiotemporal planning while remaining more efficient than dense future rollout approaches.
