About me

@HungryNeko
Backend Engineering + AI Engineering (CV, speech, RL, multimodal)
Current focus: production AI pipelines (ONNX inference, Dockerized services, async cloud workflows)
Interests: IoT backend, speech processing, and research-to-production engineering
More technical notes: blog posts

Tech Stack

Area	Stack
Languages	Python, C/C++, Java, C#, SQL
AI/ML	PyTorch, TensorFlow, scikit-learn, OpenCV, YOLOv8, ONNX, ONNX Runtime
Speech & Multimodal	Frameworks: Whisper, MossFormer2, SpeechBrain, WeSpeaker Focus: short-window cross-lingual speaker verification, code-switch analysis
Backend & Cloud	Flask, REST APIs, JWT, MySQL, Docker, Linux, MQTT, AWS (EC2/S3/SQS/Lambda/DynamoDB/IAM/Secrets Manager), Dockerized ONNX inference services
Engineering	Git, GitHub Actions, CI/CD, async job pipelines, PyQt, TCP/IP

Selected Projects

GBC: Gaussian-Based Colorization and Super-Resolution for 3D Reconstruction
- Tech: optical-flow super-resolution, temporal colorization, FFmpeg preprocessing, COLMAP + 3D Gaussian splatting.
- Publication: ACM SIGGRAPH VRCAI 2024.
BMS^3: Bayesian Modeling Based SwinUNet Segmentation on Self-distillation Architecture
- Tech: Bayesian modeling, SwinUNet backbone, self-distillation, cross-domain segmentation setup.
- Publication: ICONIP 2025.
Safety-driven Path Selection Using Reinforcement Learning in Autonomous Driving
- Tech: Q-learning, dynamic confidence update, noisy-source filtering, OpenStreetMap-based routing context.
- Publication: RSAE 2025.
Multilingual Speech Separation + Code-switch Correction Pipeline (Ongoing)
- Tech: MossFormer2, Whisper, PyTorch, SpeechBrain/WeSpeaker, custom TDNN/SincNet variants.
- Experiments: short-window (~1s) cross-lingual speaker verification benchmark across ECAPA, x-vector, WavLM, Resemblyzer, and custom models, with ablation + speed/accuracy comparison.
AI Cloud Album (AWS)
- Tech: Flask, JWT, S3, SQS, Lambda, DynamoDB, IAM, Secrets Manager, status-driven async workflow (uploaded -> processing -> complete/failed).
- AI Deployment: YOLOv8 inference exported to ONNX and packaged with Docker for reproducible cloud inference.
IoT Debugging & Testing System (Intern)
- Tech: Python, PyQt, MQTT, queue-based multithreading, protocol encryption, JSON-driven test framework.
- Metrics: 40% operation-time reduction, up to 80% less adaptation code, <20ms latency, 40% lower CPU usage.
R2 Gateway
- Tech: Flask, Docker, Cloudflare R2, S3-compatible APIs, Flask-Limiter.
- Features: Dockerized R2 gateway with token-based access control, public/private bucket policy, traffic and operation-quota guardrails, and health/usage endpoints.
SAR Data Pipeline with YOLOv8
- Tech: YOLOv8, OpenCV preprocessing, augmentation pipeline, format conversion, classification/detection/OBB training.
- Metrics: 35% effective data expansion, 12% accuracy improvement over baseline.

Project Links

R2 Gateway: Repository
GBC: Archived Repo | Paper
Safety-driven Path Selection: Abstract
BMS^3: Abstract
Image Compression Study: Report | Repository

Note: Some projects are in private repositories (course/research or confidentiality reasons).