Jialuo Li

I'm a junior 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). Currently I am a research intern at NYU advised by Prof. Saining Xie. In addition, I am privileged to work with Prof. Li Yi.

Email  /  CV  /  Google Scholar  /  Twitter  /  Github

My research interests lie broadly in Computer Vision and Deep Learning, with a particular focus on Diffusion Models and Multimodal Large Language Models (MLLM). I am especially interested in advancing models capable of comprehending and generating visual content, enabling them to truly perceive and understand the world. Furthermore, I also possess some experience in 3D Vision.

Currently I am also open to exploring other fields of research. If you are interested in my research or have any questions, feel free to contact me!

We propose CHOPS, an LLM agent designed to efficiently access user information, interact with existing systems, and provide accurate, safe responses by leveraging a combination of small and large LLMs. Validated using the CPHOS-dataset, CHOPS demonstrates its potential to enhance or replace human customer service.

We proposes enhancing the realism of mirrors and reflections in diffusion models through supervised fine-tuning (SFT) on a curated dataset and reinforcement learning (RL) guided by a custom reward model. While SFT provides modest improvements, the RL approach significantly boosts the accuracy and realism of generated reflections.

Our project extends MeshDiffusion by incorporating class conditioning for 3D mesh generation and using a pre-trained 2D diffusion model to align textures with textual descriptions, effectively generates and textures category-specific 3D meshes.

This homepage is designed based on Jon Barron's homepage and deployed on GitHub Pages. Last updated: Sept 02, 2024.
© 2024 Jialuo Li