Haoyu Li is an undergraduate student in Computer Science at Wuhan University. His research interests include 3D computer vision, multimodal learning, generative AI, and embodied intelligence. He has been a research assistant at the MARS Lab, Wuhan University, under Prof. Mang Ye, and a remote research intern at the Intelligent Interface Center, Harbin Institute of Technology, under Prof. Tiejun Zhao.
Contact: haoyuli404@outlook.com · +86-158-2700-2669 · CV (PDF)
Vision
My ambition is to work at the intersection of 3D computer vision, multimodal learning, generative AI, and embodied intelligence. I hope to study unified pipelines that move from scene geometry and multimodal representations to generative world models and language-driven robot execution, so that AI can not only see and synthesize plausible visual worlds, but also deliver verifiable, deployable closed-loop capabilities on real data and physical platforms. This is the research path I intend to pursue long term.
News
- 2026.06: FedMental was accepted to ECCV 2026.
- 2026.06: Released SkyArm-VLA, an embodied vision-language-action project for robotic arm manipulation.
- 2026.05: Released Diffusion Models from Zero to Hero as an open-source course; contributions are welcome.
- 2026.04: Project approved, National College Students’ Innovation and Entrepreneurship Training Program.
- 2026.04: S3Mamba-Pan was accepted by IEEE TGRS with DOI 10.1109/TGRS.2026.3686021.
- 2025.10: Received Meritorious Student Leader, Wuhan University Merit Student, and related honors.
- 2025.08: National Third Prize, National Computer System Capability Competition.
- 2025.05: Central-South Regional First Prize, National Undergraduate Computer Design Competition.
- 2025.05: Honorable Mention, Mathematical Contest in Modeling.
- 2024.11: Hubei Province Second Prize, National College Student Mathematics Competition.
Publications
FedMental: Topology-Aware Federated Prototype Learning for Polymorphic Multimodal Psychiatry
Haoyu Li; He Li; Wenke Huang; Yujing Rao; Xiaofen Zong; Mang Ye
European Conference on Computer Vision (ECCV), 2026.
S3Mamba-Pan: Spectral-Spatial-Scale Mamba With Frequency-Decoupled Dual-Stream for Pansharpening
Zishun Song; Yao Zhang; Haoyu Li; Yanlin He; Jiawei Zhao; Yi Yang; Wei Zhang; Dezhen Wang
IEEE Transactions on Geoscience and Remote Sensing, 2026. DOI: 10.1109/TGRS.2026.3686021
Honors and Awards
- 2025 Meritorious Student Leader, Wuhan University
- 2025 Wuhan University Merit Student
- 2025 National Third Prize, National Computer System Capability Competition
- 2025 Central-South Regional First Prize, National Undergraduate Computer Design Competition
- 2025 Hubei Province Second Prize, National College Student Mathematics Competition
- 2025 Honorable Mention, Mathematical Contest in Modeling
- 2026 Project Approved, National College Students’ Innovation and Entrepreneurship Training Program
Education
- Sept. 2023 - June 2027 (expected), Bachelor of Engineering in Computer Science, Wuhan University, Wuhan, China
- GPA: 91.75 / 100
- Selected coursework: Data Structures (97), Algorithm Design and Analysis (92), Computer Graphics (92), Fundamentals of Software Construction (94), Advanced Mathematics (96), Probability Theory and Mathematical Statistics (92)
Selected Coursework & Self-Study
Beyond my formal curriculum at Wuhan University, I completed a focused self-study track in robot learning, vision-language-action (VLA), generative modeling, and 3D vision to prepare for research in embodied intelligence, world models, and geometry-aware generation.
Robot learning & embodied AI
Vision-language-action & LeRobot
Generative modeling & diffusion
- MIT 6.S183: A Practical Introduction to Diffusion Models
- MIT: Flow Matching and Diffusion Models
- Hugging Face Diffusion Models Course
3D vision & inverse graphics
- Hugging Face ML for 3D
- MIT: Machine Learning for Inverse Graphics (Scene Representation Group)
- Stanford CS348N: Neural Models for 3D Geometry
Research Experience
- MARS Lab, Wuhan University - Research Assistant · Apr. 2025 - Present · Wuhan, China · Advisor: Prof. Mang Ye
- Studied federated prototype learning for multi-center, multimodal psychiatric diagnosis, focusing on non-IID data, privacy constraints, and cross-domain generalization; designed topology-aware prototype modeling to reduce prototype shift and semantic mixing across heterogeneous clinical centers.
- Designed a multimodal agentic diagnosis framework that organizes clinical text, structured scales, and multimodal evidence into a hierarchical reasoning chain.
- Co-developed a multidimensional psychiatric benchmark, focusing on interpretability, robustness, and failure-mode diagnosis in complex settings; the dataset is released on Harvard Dataverse.
- Intelligent Interface Center, Harbin Institute of Technology - Remote Research Intern · Dec. 2025 - Present · Remote · Advisor: Prof. Tiejun Zhao
- Contributed to S3Mamba-Pan, an efficient visual modeling project, studying the trade-offs among spatial detail, spectral consistency, and inference efficiency through frequency-decoupled dual-stream Mamba, Haar-wavelet decomposition, spectral anchors, and adaptive distribution recalibration.
- Time-series generation: Developed ChronoRect, using rectified flow to model continuous distribution transport in clinical time-series data, and proposed EHR-TriDiT to improve synthetic fidelity, downstream utility, and empirical privacy safety, gaining hands-on understanding of flow matching, generative sampling, and conditional modeling.
- Controllable video generation: Studied region and trajectory conditioning in object-centric text-to-video diffusion, aiming to improve object motion control, identity preservation, attribute binding, and temporal consistency in generated videos.
Projects
SkyArm-VLA - Apr. 2026 - June 2026 · Vision-Language-Action, robotic manipulation, LeRobot, embodied AI
- Built a robotic-arm VLA project around LingBot-VLA, adapting a pretrained vision-language-action model to a custom desktop manipulation setting and connecting language-conditioned perception with executable robot actions.
- Completed the post-training workflow from LeRobot data collection, camera/robot-state alignment, action-space mapping, and action-expert training to open-loop evaluation and WebSocket-based remote inference deployment.
Diffusion Models from Zero to Hero - Oct. 2025 - Present · Diffusers, Stable Diffusion, LoRA, ControlNet, video generation
- Organized runnable notebooks and documentation around Diffusers, scheduler design, UNet training loops, fine-tuning, classifier-free guidance, class conditioning, Stable Diffusion components (VAE, CLIP text encoder, UNet, cross-attention), img2img, inpainting, and depth-to-image.
- Covered DDIM inversion, DreamBooth personalization, audio spectrogram diffusion, toy video diffusion, troubleshooting notes, GPU-memory guidance, and a modern roadmap spanning LoRA, ControlNet, SDXL, DiT, Flow Matching, and video models.
Happy-LLM - Aug. 2025 - Apr. 2026 · Decoder-only, Pretraining -> SFT, LLM engineering
- Co-developed Happy-LLM (30k+ stars), organizing teaching and practice materials around building LLMs from scratch, covering tokenizer, embedding, Transformer decoder, attention, MLP, normalization, RoPE, and KV Cache.
- Structured the end-to-end engineering workflow across pretraining, supervised fine-tuning, PEFT, and inference optimization, connecting data preparation, training objectives, memory management, inference caching, evaluation, and application extensions to bridge model understanding and runnable LLM practice.
CyberMars: Intelligent CyberDog Robotics Control - Apr. 2025 - Aug. 2025 · ROS reinforcement learning
- Built an embodied control system for Xiaomi CyberDog, using ROS to coordinate task scheduling, real-time visual perception, lane following, QR / marker recognition, and obstacle-aware navigation, and converting fused sensor observations into executable motion decisions.
- Mapped visual recognition outputs into task states and action constraints, designed low-level motion interfaces and an LCMT trajectory-tracking pipeline, and combined reinforcement-learning-guided policy tuning with real-time feedback correction to improve closed-loop stability under sensor noise, action delay, and scene disturbance.
Leadership & Service
- Class monitor, Wuhan University · Sept. 2023 - Present - responsible for a class of 31 students; coordinated academic, administrative, and collective affairs; organized 16 themed activities across class, college, and inter-college settings.
- Committee member, External Liaison Department · Sept. 2023 - Present - facilitated 2 campus-enterprise collaborations; planned events reaching 5,000+ participants cumulatively.
Skills
- Languages: Mandarin (native), English (fluent)
- Programming: Python, Java, C#, C++, SQL, Go
- Tools & frameworks: PyTorch, Linux, Git, ROS, Docker
Haoyu Li is an undergraduate student in Computer Science at Wuhan University. His research interests include 3D computer vision, multimodal learning, generative AI, and embodied intelligence. He has been a research assistant at the MARS Lab, Wuhan University, under Prof. Mang Ye, and a remote research intern at the Intelligent Interface Center, Harbin Institute of Technology, under Prof. Tiejun Zhao.
Contact: haoyuli404@outlook.com · +86-158-2700-2669 · CV (PDF)
Vision
My ambition is to work at the intersection of 3D computer vision, multimodal learning, generative AI, and embodied intelligence. I hope to study unified pipelines that move from scene geometry and multimodal representations to generative world models and language-driven robot execution, so that AI can not only see and synthesize plausible visual worlds, but also deliver verifiable, deployable closed-loop capabilities on real data and physical platforms. This is the research path I intend to pursue long term.
News
- 2026.06: FedMental was accepted to ECCV 2026.
- 2026.06: Released SkyArm-VLA, an embodied vision-language-action project for robotic arm manipulation.
- 2026.05: Released Diffusion Models from Zero to Hero as an open-source course; contributions are welcome.
- 2026.04: Project approved, National College Students’ Innovation and Entrepreneurship Training Program.
- 2026.04: S3Mamba-Pan was accepted by IEEE TGRS with DOI 10.1109/TGRS.2026.3686021.
- 2025.10: Received Meritorious Student Leader, Wuhan University Merit Student, and related honors.
- 2025.08: National Third Prize, National Computer System Capability Competition.
- 2025.05: Central-South Regional First Prize, National Undergraduate Computer Design Competition.
- 2025.05: Honorable Mention, Mathematical Contest in Modeling.
- 2024.11: Hubei Province Second Prize, National College Student Mathematics Competition.
Publications
FedMental: Topology-Aware Federated Prototype Learning for Polymorphic Multimodal Psychiatry
Haoyu Li; He Li; Wenke Huang; Yujing Rao; Xiaofen Zong; Mang Ye
European Conference on Computer Vision (ECCV), 2026.
S3Mamba-Pan: Spectral-Spatial-Scale Mamba With Frequency-Decoupled Dual-Stream for Pansharpening
Zishun Song; Yao Zhang; Haoyu Li; Yanlin He; Jiawei Zhao; Yi Yang; Wei Zhang; Dezhen Wang
IEEE Transactions on Geoscience and Remote Sensing, 2026. DOI: 10.1109/TGRS.2026.3686021
Honors and Awards
- 2025 Meritorious Student Leader, Wuhan University
- 2025 Wuhan University Merit Student
- 2025 National Third Prize, National Computer System Capability Competition
- 2025 Central-South Regional First Prize, National Undergraduate Computer Design Competition
- 2025 Hubei Province Second Prize, National College Student Mathematics Competition
- 2025 Honorable Mention, Mathematical Contest in Modeling
- 2026 Project Approved, National College Students’ Innovation and Entrepreneurship Training Program
Education
- Sept. 2023 - June 2027 (expected), Bachelor of Engineering in Computer Science, Wuhan University, Wuhan, China
- GPA: 91.75 / 100
- Selected coursework: Data Structures (97), Algorithm Design and Analysis (92), Computer Graphics (92), Fundamentals of Software Construction (94), Advanced Mathematics (96), Probability Theory and Mathematical Statistics (92)
Selected Coursework & Self-Study
Beyond my formal curriculum at Wuhan University, I completed a focused self-study track in robot learning, vision-language-action (VLA), generative modeling, and 3D vision to prepare for research in embodied intelligence, world models, and geometry-aware generation.
Robot learning & embodied AI
Vision-language-action & LeRobot
Generative modeling & diffusion
- MIT 6.S183: A Practical Introduction to Diffusion Models
- MIT: Flow Matching and Diffusion Models
- Hugging Face Diffusion Models Course
3D vision & inverse graphics
- Hugging Face ML for 3D
- MIT: Machine Learning for Inverse Graphics (Scene Representation Group)
- Stanford CS348N: Neural Models for 3D Geometry
Research Experience
- MARS Lab, Wuhan University - Research Assistant · Apr. 2025 - Present · Wuhan, China · Advisor: Prof. Mang Ye
- Studied federated prototype learning for multi-center, multimodal psychiatric diagnosis, focusing on non-IID data, privacy constraints, and cross-domain generalization; designed topology-aware prototype modeling to reduce prototype shift and semantic mixing across heterogeneous clinical centers.
- Designed a multimodal agentic diagnosis framework that organizes clinical text, structured scales, and multimodal evidence into a hierarchical reasoning chain.
- Co-developed a multidimensional psychiatric benchmark, focusing on interpretability, robustness, and failure-mode diagnosis in complex settings; the dataset is released on Harvard Dataverse.
- Intelligent Interface Center, Harbin Institute of Technology - Remote Research Intern · Dec. 2025 - Present · Remote · Advisor: Prof. Tiejun Zhao
- Contributed to S3Mamba-Pan, an efficient visual modeling project, studying the trade-offs among spatial detail, spectral consistency, and inference efficiency through frequency-decoupled dual-stream Mamba, Haar-wavelet decomposition, spectral anchors, and adaptive distribution recalibration.
- Time-series generation: Developed ChronoRect, using rectified flow to model continuous distribution transport in clinical time-series data, and proposed EHR-TriDiT to improve synthetic fidelity, downstream utility, and empirical privacy safety, gaining hands-on understanding of flow matching, generative sampling, and conditional modeling.
- Controllable video generation: Studied region and trajectory conditioning in object-centric text-to-video diffusion, aiming to improve object motion control, identity preservation, attribute binding, and temporal consistency in generated videos.
Projects
SkyArm-VLA - Apr. 2026 - June 2026 · Vision-Language-Action, robotic manipulation, LeRobot, embodied AI
- Built a robotic-arm VLA project around LingBot-VLA, adapting a pretrained vision-language-action model to a custom desktop manipulation setting and connecting language-conditioned perception with executable robot actions.
- Completed the post-training workflow from LeRobot data collection, camera/robot-state alignment, action-space mapping, and action-expert training to open-loop evaluation and WebSocket-based remote inference deployment.
Diffusion Models from Zero to Hero - Oct. 2025 - Present · Diffusers, Stable Diffusion, LoRA, ControlNet, video generation
- Organized runnable notebooks and documentation around Diffusers, scheduler design, UNet training loops, fine-tuning, classifier-free guidance, class conditioning, Stable Diffusion components (VAE, CLIP text encoder, UNet, cross-attention), img2img, inpainting, and depth-to-image.
- Covered DDIM inversion, DreamBooth personalization, audio spectrogram diffusion, toy video diffusion, troubleshooting notes, GPU-memory guidance, and a modern roadmap spanning LoRA, ControlNet, SDXL, DiT, Flow Matching, and video models.
Happy-LLM - Aug. 2025 - Apr. 2026 · Decoder-only, Pretraining -> SFT, LLM engineering
- Co-developed Happy-LLM (30k+ stars), organizing teaching and practice materials around building LLMs from scratch, covering tokenizer, embedding, Transformer decoder, attention, MLP, normalization, RoPE, and KV Cache.
- Structured the end-to-end engineering workflow across pretraining, supervised fine-tuning, PEFT, and inference optimization, connecting data preparation, training objectives, memory management, inference caching, evaluation, and application extensions to bridge model understanding and runnable LLM practice.
CyberMars: Intelligent CyberDog Robotics Control - Apr. 2025 - Aug. 2025 · ROS reinforcement learning
- Built an embodied control system for Xiaomi CyberDog, using ROS to coordinate task scheduling, real-time visual perception, lane following, QR / marker recognition, and obstacle-aware navigation, and converting fused sensor observations into executable motion decisions.
- Mapped visual recognition outputs into task states and action constraints, designed low-level motion interfaces and an LCMT trajectory-tracking pipeline, and combined reinforcement-learning-guided policy tuning with real-time feedback correction to improve closed-loop stability under sensor noise, action delay, and scene disturbance.
Leadership & Service
- Class monitor, Wuhan University · Sept. 2023 - Present - responsible for a class of 31 students; coordinated academic, administrative, and collective affairs; organized 16 themed activities across class, college, and inter-college settings.
- Committee member, External Liaison Department · Sept. 2023 - Present - facilitated 2 campus-enterprise collaborations; planned events reaching 5,000+ participants cumulatively.
Skills
- Languages: Mandarin (native), English (fluent)
- Programming: Python, Java, C#, C++, SQL, Go
- Tools & frameworks: PyTorch, Linux, Git, ROS, Docker
李浩宇是 武汉大学 计算机科学与技术专业本科生。研究兴趣包括 三维计算机视觉、多模态、生成式人工智能 与 具身智能。曾在武汉大学 MARS 实验室 叶茫教授 组担任科研助理，并在哈尔滨工业大学智能接口技术中心 赵铁军教授 组远程实习。
联系方式：haoyuli404@outlook.com · +86-158-2700-2669 · 简历 (PDF)
愿景
我的志向是在三维计算机视觉、多模态学习、生成式人工智能与具身智能的交叉领域长期深耕。我希望研究从场景几何与多模态表征，到生成式世界模型，再到语言驱动的机器人执行的一体化方法，使 AI 不仅能看懂并生成可信的视觉世界，也能在真实数据与硬件平台上形成可验证、可部署的闭环能力。这是我计划长期投入的研究路径。
动态
- 2026.06：FedMental 被 ECCV 2026 接收。
- 2026.06：发布 SkyArm-VLA，面向机械臂操作的具身视觉-语言-动作项目。
- 2026.05：Diffusion Models from Zero to Hero 作为开源课程发布，欢迎贡献。
- 2026.04：大学生创新创业训练计划 国家级项目立项。
- 2026.04：S3Mamba-Pan 被 IEEE TGRS 接收，DOI：10.1109/TGRS.2026.3686021。
- 2025.10：获评武汉大学 优秀学生干部、优秀学生 等荣誉。
- 2025.08：全国大学生计算机系统能力大赛 全国三等奖。
- 2025.05：中国大学生计算机设计大赛 中南赛区一等奖。
- 2025.05：美国大学生数学建模竞赛 Honorable Mention。
- 2024.11：全国大学生数学竞赛 湖北赛区二等奖。
发表论文
FedMental: Topology-Aware Federated Prototype Learning for Polymorphic Multimodal Psychiatry
Haoyu Li; He Li; Wenke Huang; Yujing Rao; Xiaofen Zong; Mang Ye
European Conference on Computer Vision (ECCV)，2026。
S3Mamba-Pan: Spectral-Spatial-Scale Mamba With Frequency-Decoupled Dual-Stream for Pansharpening
Zishun Song; Yao Zhang; Haoyu Li; Yanlin He; Jiawei Zhao; Yi Yang; Wei Zhang; Dezhen Wang
IEEE Transactions on Geoscience and Remote Sensing，2026。DOI： 10.1109/TGRS.2026.3686021
荣誉与奖项
- 2025 优秀学生干部，武汉大学
- 2025 武汉大学优秀学生
- 2025 全国大学生计算机系统能力大赛 全国三等奖
- 2025 中国大学生计算机设计大赛 中南赛区一等奖
- 2025 全国大学生数学竞赛 湖北赛区二等奖
- 2025 美国大学生数学建模竞赛 Honorable Mention
- 2026 国家级大学生创新创业训练计划 项目立项
教育背景
- 2023 年 9 月 – 2027 年 6 月（预计），计算机科学与技术 工学学士，武汉大学，武汉
- GPA： 91.75 / 100
- 部分课程： 数据结构（97）、算法设计与分析（92）、计算机图形学（92）、软件构造基础（94）、高等数学（96）、概率论与数理统计（92）
精选课程与自学
除武汉大学正式课程外，我还系统完成了面向 机器人学习、视觉-语言-动作（VLA）、生成建模 与 三维视觉 的自学训练，为具身智能、world model 与 geometry-aware generation 方向的研究做准备。
机器人学习与具身智能
视觉-语言-动作（VLA）与 LeRobot
生成建模与扩散模型
- MIT 6.S183: A Practical Introduction to Diffusion Models
- MIT: Flow Matching and Diffusion Models
- Hugging Face Diffusion Models Course
三维视觉与逆图形学
- Hugging Face ML for 3D
- MIT: Machine Learning for Inverse Graphics（Scene Representation Group）
- Stanford CS348N: Neural Models for 3D Geometry
科研经历
- 武汉大学 MARS 实验室 — 科研助理 · 2025 年 4 月 – 至今 · 武汉 · 导师：叶茫教授
- 研究多中心、多模态精神医学诊断中的 联邦学习，围绕非独立同分布数据、隐私约束与跨域泛化问题设计拓扑感知的原型建模思路，以缓解异质中心之间的原型偏移与语义混叠。
- 提出模拟临床 MDT 会诊流程的多智能体推理范式，融合文本/语音/视觉等多模态数据，解决了多模态融合与可解释性难题，准确率比现有 SOTA 方法高出 18.9%。
- 构建大规模多模态医学数据基准，提出 MDDF 模态动态分解融合基线模型设计, 数据集开源至哈佛 DataversHarvard Dataverse。
- 哈尔滨工业大学 智能接口技术中心 — 远程科研实习 · 2025 年 12 月 – 至今 · 远程 · 导师：赵铁军教授
- 出频率解耦双流 Mamba 架构，通过 Haar 小波多尺度分解实现高低频特征分离建模，引入光谱锚点对齐与自适应分布再校准机制，解决了遥感多模态融合中空间细节丢失、光谱畸变与推理效率三者的固有矛盾，在多个公开数据集上同时取得精度与速度的 SOTA 性能。
- 研究时序生成，开发 ChronoRect，以 rectified flow 建模临床时序数据的连续分布传输，解耦扩散中的双流时间，并提出 EHR-TriDiT 结构。
- 研究可控视频生成，聚焦以物体为中心的文本到视频生成任务，分析区域掩码与运动轨迹的细粒度条件控制机制，解决生成视频中物体运动偏差、身份漂移、属性错配与时间不一致性的痛点。
项目
SkyArm-VLA — 2026 年 4 月 – 2026 年 6 月 · Vision-Language-Action、机械臂操作、LeRobot、具身智能
- 围绕 LingBot-VLA 搭建机械臂 VLA 项目，将预训练视觉-语言-动作模型适配到自定义桌面操作场景，把语言指令理解、视觉观测与可执行机器人动作连接起来。
- 完成从 LeRobot 数据采集、相机与机器人状态对齐、动作空间映射、动作专家后训练，到开环评估与 WebSocket 远程推理部署的完整后训练流程。
Diffusion Models from Zero to Hero — 2025 年 10 月 – 至今 · Diffusers、Stable Diffusion、LoRA、ControlNet、视频生成
- 围绕 Diffusers、scheduler 设计、UNet 训练循环、微调、classifier-free guidance、类别条件生成、Stable Diffusion 组件（VAE、CLIP 文本编码器、UNet、cross-attention）、img2img、inpainting 与 depth-to-image 编写可运行 notebook 与文档。
- 覆盖 DDIM inversion、DreamBooth 个性化、音频频谱图扩散、toy video diffusion、运行排查、显存优化建议，以及 LoRA、ControlNet、SDXL、DiT、Flow Matching 和视频模型 等现代路线图。
Happy-LLM — 2025 年 8 月 – 2026 年 4 月 · Decoder-only、Pretraining -> SFT、LLM engineering
- 共建 Happy-LLM（30k+ stars），围绕从零实现大语言模型的核心链路组织教学与实践材料，覆盖 tokenizer、embedding、Transformer decoder、attention、MLP、归一化、RoPE 与 KV Cache 等基础模块。
- 梳理 预训练、监督微调、PEFT 与推理优化 的完整工程流程，将数据构造、训练目标、显存管理、推理缓存、模型评测与应用扩展串联起来，帮助读者从模型结构理解过渡到可运行的 LLM 实践。
CyberMars: Intelligent CyberDog Robotics Control — 2025 年 4 月 – 8 月 · ROS、强化学习
- 面向小米 CyberDog 构建具身控制系统，基于 ROS 组织任务调度、实时视觉感知、车道跟随、二维码 / 标记识别与障碍导航模块，并通过传感信息融合把环境观测转化为可执行的运动决策。
- 将视觉目标识别结果映射为任务状态与动作约束，设计低层运动接口和 LCMT 轨迹跟踪链路；结合强化学习引导的运动策略调参与实时反馈修正，提升在传感噪声、动作延迟和场景扰动下的闭环执行稳定性。
学生工作与志愿服务
- 班长，武汉大学 · 2023 年 9 月 – 至今 — 负责 31 人班级的大小事务；协调教学、行政与集体事务；组织 16 场覆盖班级、院系与校际的主题活动。
- 外联部部委 · 2023 年 9 月 – 至今 — 促成 2 次校企对接；策划活动累计覆盖 5000+ 人次。
技能
- 语言： 中文（母语）、英文（流利）
- 编程： Python、Java、C#、C++、SQL、Go
- 工具与框架： PyTorch、Linux、Git、ROS、Docker