I am a graduate student with a strong interest in Artificial Intelligence, particularly in Computer Vision and Multimodal Learning. I have hands-on experience in developing and implementing AI models for tasks such as multimodal retrieval and intelligent surveillance systems. I am proficient in C++, Python, OpenCV, and YOLO, and have a solid academic background with a GPA of 3.88/4.00. I am seeking a position as an AI algorithm engineer specializing in computer vision and multimodal directions.
1 11
核心开发者 | 导师实验室
Singapore
Summary
Education
'%3e%3crect%20width='48'%20height='48'%20rx='4'%20fill='%23E6E3F9'/%3e%3crect%20width='0.6'%20height='10'%20transform='matrix(-1%200%200%201%2042.3999%2024)'%20fill='%2367E2F2'/%3e%3cpath%20d='M44%2036C44%2037.1046%2043.1046%2038%2042%2038C40.8954%2038%2040%2037.1046%2040%2036C40%2034.8954%2040.8954%2034%2042%2034C43.1046%2034%2044%2034.8954%2044%2036Z'%20fill='url(%23paint0_linear_2586_8632)'/%3e%3cpath%20d='M42%2036L43.7321%2042H40.2679L42%2036Z'%20fill='url(%23paint1_linear_2586_8632)'/%3e%3crect%20x='-12'%20y='21.5'%20width='48'%20height='32'%20rx='2'%20fill='%236754C8'/%3e%3cpath%20d='M15.5493%2010.4661C16.1408%2010.1135%2016.8721%2010.0901%2017.485%2010.4041L41.5254%2022.72C42.9762%2023.4632%2042.9762%2025.5368%2041.5254%2026.28L17.485%2038.5959C16.8721%2038.9099%2016.1408%2038.8865%2015.5493%2038.5339L-5.11706%2026.2181C-6.41859%2025.4424%20-6.41859%2023.5576%20-5.11706%2022.7819L15.5493%2010.4661Z'%20fill='url(%23paint2_linear_2586_8632)'/%3e%3ccircle%20cx='31.9247'%20cy='24.1795'%20r='1.5'%20transform='rotate(-3.37875%2031.9247%2024.1795)'%20fill='white'/%3e%3ccircle%20cx='23.5357'%20cy='27.282'%20r='1.5'%20transform='rotate(-3.37875%2023.5357%2027.282)'%20fill='white'/%3e%3c/g%3e%3cdefs%3e%3clinearGradient%20id='paint0_linear_2586_8632'%20x1='38.0748'%20y1='42'%20x2='47.3606'%20y2='39.6343'%20gradientUnits='userSpaceOnUse'%3e%3cstop%20offset='0.0781'%20stop-color='%239685F4'/%3e%3cstop%20offset='1'%20stop-color='%2367E2F2'/%3e%3c/linearGradient%3e%3clinearGradient%20id='paint1_linear_2586_8632'%20x1='38.0748'%20y1='42'%20x2='47.3606'%20y2='39.6343'%20gradientUnits='userSpaceOnUse'%3e%3cstop%20offset='0.0781'%20stop-color='%239685F4'/%3e%3cstop%20offset='1'%20stop-color='%2367E2F2'/%3e%3c/linearGradient%3e%3clinearGradient%20id='paint2_linear_2586_8632'%20x1='-20.7546'%20y1='11.7454'%20x2='57.7546'%20y2='37.2546'%20gradientUnits='userSpaceOnUse'%3e%3cstop%20offset='0.0781'%20stop-color='%239685F4'/%3e%3cstop%20offset='1'%20stop-color='%2367E2F2'/%3e%3c/linearGradient%3e%3cclipPath%20id='clip0_2586_8632'%3e%3crect%20width='48'%20height='48'%20rx='4'%20fill='white'/%3e%3c/clipPath%3e%3c/defs%3e%3c/svg%3e)
河北工业大学 本科, 人工智能与数据科学学院 Grade : GPA: 3.88/4.00 专业排名:11/142(前8%) 已修课程:高等数学(96)、复变函数(97)、概率论(97)、操作系统(93)、数据结构(89)、计算机组成原理(88) Aug 2023 - Present
Experience
'%3e%3crect%20x='0.5'%20width='64'%20height='64'%20rx='8'%20fill='%23E6E3F9'/%3e%3cpath%20fill-rule='evenodd'%20clip-rule='evenodd'%20d='M44.4684%2011.2093C45.323%2011.7834%2045.8334%2012.7311%2045.8334%2013.7437V71.5903C45.8334%2073.2895%2044.4222%2074.667%2042.6813%2074.667H14.3188C12.578%2074.667%2011.1667%2073.2895%2011.1667%2071.5903V25.3228C11.1667%2024.0475%2011.9728%2022.9044%2013.1932%2022.449L41.5557%2010.8699C42.5247%2010.5083%2043.6139%2010.6352%2044.4684%2011.2093Z'%20fill='%236754C8'/%3e%3cpath%20fill-rule='evenodd'%20clip-rule='evenodd'%20d='M28.0802%2029.6378C28.6491%2029.2817%2029.364%2029.2345%2029.9764%2029.5127L55.3543%2041.0415C56.0531%2041.359%2056.5003%2042.0452%2056.5003%2042.8002V72.7279C56.5003%2073.7985%2055.6149%2074.6663%2054.5226%2074.6663H29.1447C28.0525%2074.6663%2027.167%2073.7985%2027.167%2072.7279V31.2715C27.167%2030.6099%2027.5113%2029.9939%2028.0802%2029.6378Z'%20fill='url(%23paint0_linear_2515_20613)'/%3e%3ccircle%20cx='45.9958'%20cy='45.5768'%20r='2.06863'%20transform='rotate(-3.92943%2045.9958%2045.5768)'%20fill='white'/%3e%3cellipse%20cx='34.7058'%20cy='42.2052'%20rx='2.06864'%20ry='2.06864'%20transform='rotate(-3.92943%2034.7058%2042.2052)'%20fill='white'/%3e%3c/g%3e%3cdefs%3e%3clinearGradient%20id='paint0_linear_2515_20613'%20x1='26.325'%20y1='65.8186'%20x2='57.9007'%20y2='59.5553'%20gradientUnits='userSpaceOnUse'%3e%3cstop%20offset='0.160358'%20stop-color='%239685F4'/%3e%3cstop%20offset='1'%20stop-color='%2367E2F2'/%3e%3c/linearGradient%3e%3cclipPath%20id='clip0_2515_20613'%3e%3crect%20x='0.5'%20width='64'%20height='64'%20rx='8'%20fill='white'/%3e%3c/clipPath%3e%3c/defs%3e%3c/svg%3e)
核心开发者 导师实验室 May 2025 - Dec 2025 • 8 mos
项目背景:本项目依托于导师实验室课题组,聚焦于边缘计算与多模态感知在无人系统中的应用研究。 核心工作:负责设计“端-边-云”协同架构:基于Jetson Xavier NX平台搭建嵌入式硬件系统,融合可见光与红外双光视觉数据,利用YOLO与OpenCV实现动态目标的实时检测与追踪;设计基于RTSP/WebRTC的低延迟双路视频流传输协议,解决了复杂网络环境下的远程监控难题;开发边缘端数据预处理与云端决策控制的协同算法,实现了本地自主巡检与远程人工接管的无缝切换,验证了轻量化模型在边缘侧部署的可行性。 项目成果:成功构建了“端-边-云”协同的无人小车智能巡检原型系统。实现了在动态复杂环境下的高精度目标识别与低延迟视频回传,验证了多模态感知与边缘计算在无人巡检场景中的有效性。
- 核心开发者 面向专利 PDF 的多模态检索增强问答系统 Jan 2026 - Apr 2026 • 4 mos
项目背景:针对专利文档中图文混排、长文本理解及跨页证据定位的学术难点,设计并实现了一套基于多模态大模型的检索增强生成框架。 核心工作:利用PyMuPDF构建页面级图像与文本的统一索引结构,解决了非结构化数据的模态对齐问题;提出BM25+Dense+Visual的混合检索策略,通过图文协同证据定位与邻域页面加权算法,显著提升了长文档检索的召回率,指标达到;针对不同题型设计了差异化的模态融合机制,并基于结构化提示词工程优化了大模型的答案生成逻辑,增强了系统对复杂专利信息的推理能力。 项目成果:显著提升了问答系统的性能表现,Char-F1 指标上达到0.3849, Rouge-L 指标达到0.3726。
Skills
- c/c++Expert
- pythonExpert
Languages
- CET-4Native speaker
- CET-6Native speaker