Hello, I'm Jiashu Yang (杨佳澍), an undergraduate student currently in my third year of studies.
Research Goal: Visual tasks are ubiquitous in daily life,and research on visual understanding has long been a focus in the academic community. However, traditional visual understanding models have shown limited capabilities in comprehension and reasoning. In recent years, large models have demonstrated powerful reasoning abilities and extensive knowledge, but their massive parameter sizes and the demand for real-time performance in complex scenarios make them difficult to deploy in practice.My research journey began with traditional visual understanding, and in mid-2024, I started exploring large models,aiming to address high-performance visual understanding tasks using low parameter counts.
Under the supervision of Prof. Wenzhao Lian, I conducted a research internship focused on robotic-arm manipulation driven by active visual perception.Here is the link to our project
I worked with Prof. Huchuan Lu (IEEE Fellow) and Prof. Xu Jia on research related to multimodal Retrieval-Augmented Generation (RAG).
🔥 News
- 2025.1.15 Stay tuned! On January 15th, I will release 🐿️Squirrel File Detective, a cutting-edge multimodal model based on Retrieval-Augmented Generation (RAG) for advanced document exploration.
📝 Publications
📖 Education
-
- Sincerely looking for PhD positions for fall 2026 admission!
💻 Projects
- 📂 Our multi-modal PDF interaction tool "Squirrel" will be launched on January 15, 2025!
- 📂 The "Zilu" model of our "Kongzi" series of large models will release its first version on December 31st, dedicated to translating modern Chinese into classical Chinese. The "Kongzi" model will release its first version by January 30, 2025, aiming to answer any question using the wisdom of ancient Chinese scholars in classical Chinese.
💼 Work Experience
-
2023.11 - 2024.08
Institute of Automation, Chinese Academy of Sciences (CAS) -
2024.05 - 2025.01
IIAU lab, Research Assistant -
2025.04 - 2025.07
ByteDance, Beijing, Applications of Large Language Models -
2025.07 - 2025.09
IIAU lab, School of Artificial Intelligence, Shanghai Jiao Tong University,Research Assistant
🎖 Honors and Awards
- 2023: Robocup, Advanced Vision Track - Industrial Measurement, National First Prize
- 2024: Robocup, Advanced Vision Track - 3D Detection, National Third Prize
- 2024: Robocup, Advanced Vision Track - Industrial Measurement, National Third Prize
- 2024: China University Computer Competition, National Third Prize
About Life
🚧 This section is under construction... 🚧