Skip to content
View Vivianmxmf's full-sized avatar
10 followers · 33 following

Achievements

Achievement: QuickdrawAchievement: YOLOAchievement: Pull Sharkx2

Achievements

Achievement: QuickdrawAchievement: YOLOAchievement: Pull Sharkx2

Block or report Vivianmxmf

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Vivianmxmf/README.md

Hi there 👋

🤖 AI & ML

Python PyTorch scikit-learn Pandas NumPy TensorFlow Hugging Face OpenAI OpenCV

🎨 Web Development

React Node.js JavaScript TypeScript HTML5 CSS3

⚙️ Backend & Infrastructure

Java Spring Boot Spring Cloud MySQL Redis RabbitMQ Nginx

🛠️ Tools

Git Docker VS Code Jupyter LaTeX Linux

Pinned Loading

  1. janus-terminal janus-terminal Public

    ⌖ JANUS — the two-faced AI investment terminal · LangGraph multi-agent + hybrid RAG + QLoRA-distilled analyst (vLLM-served) · Bloomberg-Terminal UI · 226 tests · RAGAS 1.00 · Sharpe +0.97

    Python 1

  2. crucible-ai crucible-ai Public

    End-to-end AI training-data platform — stealth crawl → LLM annotate → hybrid (dense + BM25) RAG → authenticated multi-tenant FastAPI. Live demo, load-tested at P95 54 ms / ~609 req/s, 120 tests.

    HTML

  3. xyzhang30/Schedule_Task_Management_App xyzhang30/Schedule_Task_Management_App Public

    Python 1

  4. LLM-Based_Agents_Evolving_Social_Networks LLM-Based_Agents_Evolving_Social_Networks Public

    A multi-agent simulation framework exploring how LLM-powered autonomous agents form, adapt, and evolve social network structures through strategic interactions and emergent behaviors.

    Python

  5. Jury_Deliberation_LLMAgents_Simulator Jury_Deliberation_LLMAgents_Simulator Public

    A multi-agent deliberation simulator inspired by 12 Angry Men, where LLM-powered juror agents engage in structured argumentation, persuasion, and consensus-building to model group decision dynamics.

    Jupyter Notebook

  6. WNBA_Courtcast_Pipeline WNBA_Courtcast_Pipeline Public

    An end-to-end WNBA broadcast analytics pipeline using YOLOv8x for player/ball detection (mAP@0.5 ~0.95), with ByteTrack/BoT-SORT tracking evaluation and planned homography mapping to 2D court coord…

    Python