Lightweight T2I Model
A lightweight text-to-image generation model based on CVAE + CLIP, solving the computational overhead problem on mobile devices. Published as first author in SCI Q3 journal.
Hi, my name is
I'm a Computer Science student at Lanzhou University, ranked 9/92 in my cohort. Currently focused on deep learning, multimodal fusion, and lightweight generative models — with a published SCI paper as first author and hands-on experience building real-world AI systems.
September 2022 - Present
March 2024 - December 2024
October 2023 - October 2024
July 2024 - May 2025
October 2022 - Present
A lightweight text-to-image generation model based on CVAE + CLIP, solving the computational overhead problem on mobile devices. Published as first author in SCI Q3 journal.
An intelligent emergency response system built with LLM Agents, collaborating with Gansu Provincial Emergency Management Bureau for automated plan generation and scheduling.
Leveraging GAI to generate personalized marketing content for Xiaohongshu merchants, with a multimodal user preference extraction algorithm. Supported by Lanzhou University Junzheng Fund.
A key computation-state data encryption system built on Huawei secGear platform. Won 1st prize at the provincial level in the E-Commerce Innovation & Entrepreneurship Competition.
Algorithm design focusing on graph theory, dynamic programming, and greedy algorithms
Utility model patent (ZL 2024 2 1805823.7) for an innovative modular computer case design
This website — migrated from Hexo blog to a pure frontend portfolio
Get In Touch
Although I'm not currently looking for any new opportunities, my inbox is always open. Whether you have a question or just want to say hi, I'll try my best to get back to you!
Say Hello