|
Jingzhe Shi
This page is still under construction, some information might be outdated or missing.
Hi! I'm a senior undergraduate student majoring Computer Science and Technology at IIIS,
Tsinghua University (a.k.a Yao Class, directed by the Turing Award Laureate Andrew Chi-Chih Yao).
Email / CV / Google Scholar / Github |
|
|
My research interests lie broadly in Deep Learning and Machine Learning. For Applications of DL/ML, I am interested in the application of LLMs in all aspects, including pure NLP tasks as well as Computer Vision tasks for Multimodal Large Language Models (MLLM). For Physics of DL/ML, I am interested especially for Scaling Law and its explanation in various areas. As a gold medalist in IPhO, I find it interesting to study theoretically and experimentally the impact of dataset size, model size as well as other physical quantities (e.g. context length) on model performance. |
|
|
|
CHOPS: CHat with custOmer Profile Systems for Customer Service with LLMs
Jingzhe Shi, Jialuo Li, Qinwei Ma, Zaiwen Yang, Huan Ma, Lei Li COLM 2024 Project Page / arXiv / OpenReview - We proposed CHOPS, an LLM agent designed to efficiently access user information, interact with existing systems, and provided accurate, safe responses by leveraging a combination of small and large LLMs. Validated using the CPHOS-dataset we proposed in the same work, CHOPS demonstrated its potential to enhance or replace human customer service. |
|
Large Trajectory Models are Scalable Motion Predictors and Planners
Qiao Sun, Shiduo Zhang, Danjiao Ma, Jingzhe Shi, Derun Li, Simian Luo, Yu Wang, Ningyi Xu, Guangzhi Cao, Hang Zhao arXiv 2023 Project Page / arXiv - We leveraged successful backbones in NLP for trajectory prediction, demonstrating scalability on diverse datasets and achieving state-of-the-art performance on Nuplan dataset - I was responsible for the decoder part. I ustilized DDPM to generate trajectory in Key Point Space to capture multi-modal distribution of future trajectories. |
 |
Tsinghua University
2021.09 - Present Undergraduate Student Research Advisor: Prof. Hang Zhao. |
 |
CPHOS
2020.12 - Present Co-founder, Former Techgroup Leader, Council Member - Academical non-profit organization dedicated to providing Physics Olympiad simulations for high school contestants for free through an online platform. - Founded in the late 2020 by a group of 10 (including myself), now with 100+ members. 1000+ students from 200+ high schools participate in most Olympiads held by CPHOS. - I led the tech group to develope tools supporting online Olympiads, as well as conducting interesting researches including the CHOPS project. |
|
|
|
This homepage is designed based on Jon Barron's homepage and deployed on GitHub Pages. Last updated: Aug 06, 2024.
|