|
曾丹妮 |
Biography
I am currently a Ph.D. preparatory student at BJZGCA and a member of the Zhaojian AI Lab research group.
Currently, I am working on an AI-powered cross-border e-commerce startup, exploring automated solutions for overseas marketing.
Research Interests
My research interests include Machine Learning and Deep Learning. Specifically, I am focusing on:
Large Language Models Multimodal Learning Agent AI Natural Language Processing Prompt Engineering & Chain-of-Thought
Work Experience
-
Technical Intern, Shanghai Woaini Technology Co., Ltd. (初创公司) | Sept. 2025 - Dec. 2025
Participated in AI smart bracelet co-creation and followed up on B-end order development.
-
Technical Project Management Intern, Migu Culture Co., Ltd. (Beijing Research Institute) (北京咪咕文化有限公司) | June 2025 - Sept. 2025
Assisted in advancing digital human live streaming platform projects.
-
AIGC Algorithm Engineering Intern, Beijing Unicom Shike Company (北京联通时科公司) | Aug. 2024 - Nov. 2024
Responsible for Unity debugging and scripting in the Metaverse project.
-
Intern, Beijing Haibaichuan Technology Co., Ltd. (北京海百川科技有限公司) | Dec. 2024 - Feb. 2025
Responsible for "Virtual Girlfriend" product design and research, including initial mini-program feature design.
Awards & Honors
- Migu Zone AI+ University Innovation and Wisdom Plan Most Application Value Award (最具应用落地奖), 2025
"famlee伐木布雷" - An AI psychological companion specifically designed for college students. Uses multimodal emotion recognition technology to analyze emotional state through text and voice input, providing immediate, empathetic feedback and companionship.
- The 5th National Artificial Intelligence Competition (NAIC) AI + Digital Human Capabilities and Customer Service Application Track Third Prize (全国三等奖), 2024
AI + Digital Human Capabilities and Customer Service Application (Team Leader, Mar. 2025 - May 2025) — An end-to-end digital human broadcasting system based on multimodal AI technology. Integrates FaceVerseV4 3D face modeling, F5-TTS voice synthesis, and NVIDIA Audio2Face audio-driven technologies to achieve functional collaboration in avatar generation, voice cloning, face driving, and digital human broadcasting. My contributions: Overall program integration, model calling and optimization for each module, and face driving solution implementation.
- The 16th China University Student Service Outsourcing Innovation and Entrepreneurship Competition Enterprise Proposition Track Second Prize (全国二等奖), 2024
"Soul Matrix" (声灵矩阵) AI + Education Project (Team Leader, Apr. 2025 - Aug. 2025) — An AI-based voice cloning and intelligent teaching video synthesis system with web and desktop applications. Provides a full-process multimodal education tool for voice cloning, long-text reading, and teaching courseware explanation. My contributions: Software frontend/backend development (PySide), web backend, PPT parsing with LLM polishing, and model debugging.
- China Collegiate Computing Contest Network Technology Challenge North China Regional Second Prize (华北赛区), 2025
- The 10th National University Student Internet of Things Technology and Application "3S Cup" Competition Third Prize (全国三等奖), 2024
- China International College Students' Innovation Competition Beijing Regional Second Prize (北京赛区), 2025
- "National Youth Cup" National University Art and Design Works Exhibition First Prize, 2024
- NCDA National University Digital Art and Design Competition Second Prize, 2025
Software Copyrights
- "AI Voice Cloning and Intelligent Teaching Video Synthesis System V1.0", First Author, 2025
Skills
- Programming: Python, C#, SQL, Web Frontend, Flask, Vue, PySide6
- Design: 剪映, PS, LR, Figma, AE
- Other: Unity, Blender, Cubase, Arduino