Embodied AI · VLA systems · Image enhancement
Advancing task transfer and cross-scenario generalization in embodied AI.
I am an MPhil student at The University of Sydney, advised by Prof. Chang Xu.
My research focuses on embodied AI, especially the architecture, reasoning, and acceleration of Vision-Language-Action (VLA) and World Action Model (WAM) systems. I also work on low-light image enhancement and machine learning.
01 · UPDATES
News
Started an embodied AI algorithm engineering internship at JD Joy Future Academy, building an automated task-evaluation benchmark for embodied AI.
See What Matters is accepted by ICML 2026.
FusionNet wins 1st place in the NTIRE 2025 Low-Light Enhancement challenge.
HVI is accepted by CVPR 2025 and released as an open-source implementation.
Flow-Guided HDR Restoration wins 2nd place in the NTIRE 2025 Burst HDR Restoration challenge.
DiffLight receives an oral presentation and 4th place in the NTIRE 2024 Low-Light Enhancement challenge.
02 · SERVICE
Academic Reviewing
I serve as a reviewer for leading venues across computer vision, multimedia, machine learning, and AI systems.
03 · TRAINING
Education
The University of Sydney · Advisor: Chang Xu
Research: Embodied AI, VLA/WAM architecture, reasoning and acceleration.
Northwestern Polytechnical University · Jichang Kang Intelligent Systems Elite Class
04 · EXPERIENCE
Internship
Beijing, China
Developing an automated task-evaluation benchmark for embodied AI to improve overall model evaluation efficiency and support faster, more effective model iteration.
Hangzhou, China
Built an end-to-end VLA pipeline for humanoid robots and Franka/SO100 arms, from data collection and fine-tuning to real-robot deployment; worked on visual compression to improve task transfer and cross-scenario generalization.
Beijing, China
Developed low-light enhancement and real-time video analysis modules for bank-counter surveillance, improving violation detection accuracy by more than 15%.
Beijing, China
Assisted the intelligent production-line scheduling algorithm architect in introducing AI large models for architecture design and algorithm optimization.
05 · RECOGNITION
Honors and Awards
- 2024 National Collegiate Computer System Capability Contest – OS Kernel Implementation Track, First Prize (Team Leader)
- The 2nd CrowdOS Open-Source Challenge, First Prize (Team Leader)
- The 7th National Collegiate Computer System Capability Contest – “Loongson Cup”, Third Prize (Team Leader)
- The 15th “Challenge Cup” Shaanxi Provincial Academic & Technology Competition, Grand Prize (Team Member)