Portfolio
Renwei Meng
I build systems that translate curiosity into usable tools — from papers to production.
Renwei Meng
A snapshot of my academic path and undergraduate journey.
Across frontend, backend, APIs, deployment, and performance tuning.
Turning raw data into actionable insights via modeling and visualization.
Focused on machine learning, deep learning, LLMs, computer vision, and intelligent systems, spanning data processing, training, and inference deployment.
I work across four research tracks from method exploration to system delivery.
Computer Vision
LLM
Brain-Computer Interface
Deep Learning & Machine Learning
Musician
Code + Music
I am a drummer, and I also play guitar and piano. I compose music as well.
My Gears
Music and software both reward rhythm, structure, and deliberate practice.
Music Component
Tap the vinyl to play
Music Tags
An Agent-RAG framework that organizes knowledge as method nodes with dual-tree indexing, strategy-guided synthesis, and verification-based pruning, enabling explainable and controllable innovation.
A group-aware EEG emotion recognition framework that combines individual neural dynamics, learnable group prototypes, and multi-subject resonance modeling to improve cross-subject generalization.
A layered multi-agent workflow for repository-level bug and vulnerability detection: risk triage → context expansion → specialist agents → selective verification → evidence fusion, aiming for higher recall, fewer false positives, and better interpretability.
An AI-native product built around pet vocalization understanding, multimodal behavior analysis, and data flywheel design, covering an internal annotation platform, a consumer-facing app, agent workflows, RAG pipelines, and monetization strategy.
An interactive computer graphics lab for rasterization algorithms, covering DDA, Bresenham, circles, scanline polygons, region filling, fonts, and OpenGL primitive modes.
A latest hands-on tutorial for AI-assisted mathematical modeling, covering agents, workflow automation, and competition-oriented methodology.
Research does not magically become a product. The real transformation happens when technical novelty is translated into user value, engineering reliability, and a repeatable business model.
About
I enjoy turning complex problems into clean interfaces and reliable systems. My work sits at the intersection of AI, data, and product.
About