I am a PhD student at the University of Sussex (funded by CSC). I received my MSc in Robotics from the University of Sussex in June 2025.
Currently, I conduct research on embodied intelligence in the Autonomous Intelligence & Robotic Embodiment Lab at the University of Sussex, supervised by Professor Bao Kha Nguyen. I am also a visiting doctoral student at the School of Artificial Intelligence, Shanghai Jiao Tong University (HIROL Lab), supervised by Professor Professor Lian Wenzhao.
As a newcomer to embodied intelligence, I’m eager to learn from senior researchers and peers. If you’re interested in my work, please feel free to contact me.
🌟 Research Orientation
Embodied AI & Multimodal Foundation Models
Leveraging Large Vision-Language Models (LVLMs) for embodied reasoning and decision-making.
Instruction following and long-horizon planning in complex environments (VLN).
Parameter-efficient fine-tuning (PEFT) and alignment of foundation models for robotics tasks.
Bridging the gap between high-level linguistic instructions and low-level control policies.
Cross-modal representation learning for embodied agents in 3D environments.
📖 Education
2025.10 – Present: PhD Student, University of Sussex, UK
2023.09 – 2025.06: MSc in Robotics, University of Sussex, UK
2017.09 – 2021.06: BEng in Computer Science and Technology, Henan Normal University, China
💻 Internships & Research Experience
-
2025.09 - Now: Visiting student at Shanghai Jiao Tong University, School of AI, HIROL Lab.
-
2025.03 - 2025.09: Research Assistant at Shanghai Jiao Tong University, School of AI, HIROL Lab.
Embodied intelligence platform: Hand-eye calibration section. The programming of the underlying interfaces for different robots. Motion capture system, object marking and data acquisition.
🔥 News
- 2026.02: 🎉 One paper accepted by ICRA2026
- 2025.06: 🎉 I received funding from CSC.
📖 Publications
SAGE: Scene Graph-Aware Guidance and Execution for Long-Horizon Manipulation Tasks
- we propose SAGE, a novel framework for Scene Graph-Aware Guidance and Execution in Long-Horizon Manipulation Tasks
- we propose an unsupervised multi-view stereoscopic system based on Gaussian Splatting, called Low-Light Gaussian Splatting.
🤔 Review & correction
4DGS point flow Convert 3DGS to a time series format and simultaneously use semantic-driven methods to track objects.
FSAG: Enhancing Human-to-Dexterous-Hand Finger-Specific Affordance Grounding via Diffusion Models
- we propose a data-efficient framework, which is designed to bypass robot grasp data collection by exploiting the rich, object-centric semantic priors latent in pretrained generative diffusion models.
Meta-Scoop: A Coarse-to-Precise Policy Learning Framework for Precision Scooping Across Task Variations
- We have proposed a framework that progresses from rough to precise, enabling precise extraction operations in various task variations.
🤖 Some Work
LTCF-Net: A Transformer-Enhanced Dual-Channel Fourier Framework for Low-Light Image Restoration \
- We introduce LTCF-Net, a novel network architecture designed for enhancing low-light images.
Lighting SLAM Paths in Darkness: A Low-Light Augmented SLAM with Hybrid Window Transformer-Mamba \
- We propose Low-Light Enhanced SLAM with Hybrid Window Transformer-Mamba (HWTM-SLAM), a novel framework that integrates low-light image enhancement as a fundamental front-end component to address the fragility of traditional SLAM systems in dark environments.
✅ Demo
🎖 Honors and Awards
- [2025]: CSC Government Scholarship for Doctoral Studies Abroad
- [2025]: sussex University Dean’s Scholarship (Top 1%)
- [2025]: Sussex University International Doctoral Scholarship (Top 5%)
🌸 others
Reproduce interesting projects
Track the hand and complete the remote operation to collect data.
🔍 Reviewers
- ICRA2026
- ICME2026