Huawei MindSpore Open-Source Community

Research Intern · February 2025–June 2025 · Remote

Contributed to the MindNLP open-source project within the MindSpore ecosystem, implementing and fine-tuning Autoformer, BEiT, and ALBERT models.

  • Worked on model integration, training stability, and cross-task evaluation across NLP and vision-language tasks.
  • Improved the reproducibility and robustness of training workflows through open-source issue, review, and documentation processes.

Automatic Inspection and Rescue Based on Drone Nest

Research Project · January 2024–July 2024 · Beijing Elite Intelligence Company and North China Institute of Science and Technology

Developed UAV-based inspection services for open-pit mine scenarios, including water counting, conveyor-belt deviation detection, and truck tracking.

  • Used DeepSORT and YOLOv8 for practical UAV inspection and rescue pipelines.
  • Optimized PyTorch detection models and exported them through ONNX for real-time inference on edge devices.

Baiyangdian Ecological IoT Monitoring System

Research Project · June 2023–January 2024 · Hebei Province Key Scientific Research and Development Project, No. 19270318D

Studied efficient object detection for mining trucks and low-altitude UAV monitoring under practical deployment constraints.

  • Developed mining-truck detection using YOLOv7-tiny and Darknet, improving recognition accuracy by 2% with minimal FPS loss.
  • Enhanced infrared-visible UAV object detection with YOLOv8, achieving 65% mAP at 30 FPS on a laptop while targeting edge deployment.