Hi, I'm Bruce Wang, a Computer Vision Engineer focusing on multimodal large models and high‑performance model deployment.
I use this GitHub to share my experiments, engineering practices, and some open‑source projects.
-
Computer Vision
- Image Classification
- Object Detection
- Semantic Segmentation
- OCR / Scene Text Detection & Recognition
-
Multimodal Large Models
- Image–Text retrieval and matching
- Multimodal pretraining and downstream finetuning
- Integration of visual encoders with LLMs
-
Model Optimization & Deployment
- High‑performance inference with TensorRT
- Inference acceleration with OpenVINO
- Model pruning / quantization / distillation
- Deployment across cloud and edge devices
- Applying multimodal LLMs to real-world vision tasks
- Lightweight multimodal models for edge deployment
- End‑to‑end pipelines for efficient training and inference
- Email: zhengwang0216@163.com
- Xiaohongshu (RED): 一个算法工程师
Feel free to reach out via Issues, PRs, or email if you’re interested in collaboration or discussion around CV, multimodal models, or model deployment.

