Desai Xie

Hi! I am Desai Xie (谢德赛). I am a 4th-year CS PhD student at Stony Brook University, advised by Prof. Arie Kaufman, who fosters an environment of interdisciplinary research in our lab. I was a research intern in the 3D group at Adobe Research in Summer 2023, working with Dr. Xin Sun and Dr. Hao Tan. Prior to joining SBU, I spent 3 years at Lehigh University for my undergraduate CS education, where I worked on a protein volume classification project with Prof. Brian Chen.

My research is driven by my passion for advancing the state of Generative AI through Reinforcement Learning (RL). Research in RL has shown promising paths to superhuman intelligence (e.g. AlphaZero and OpenAI Five). Currently, I am interested in using RL to finetune large, pre-trained generative models (e.g. my Adobe research internship project Carve3D); pre-training provides great generalization and RL finetuning can unlock the full potential of the model by generating high-quality synthetic data from the pre-trained model itself.


News

I am actively seeking research internship opportunities in 2024, with flexible starting dates and durations.

2024/02/26 Excited to share that the paper from my Adobe internship, Carve3D, was accepted to CVPR 2024!

2023/07/17 My first publication got accepted to ICCV 2023!

2023/06/19 Started my internship at Adobe Research!


Publications

Teaser image for Carve3D

Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning
Desai Xie, Jiahao Li, Hao Tan, Xin Sun, Zhixin Shu, Yi Zhou, Sai Bi, Sören Pirk, Arie E. Kaufman
Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Project Paper Code

Teaser image for GAIT

GAIT: Generating Aesthetic Indoor Tours with Deep Reinforcement Learning
Desai Xie, Ping Hu, Xin Sun, Sören Pirk, Jianming Zhang, Radomír Měch, Arie E. Kaufman
International Conference on Computer Vision (ICCV), 2023
Project Paper Code


Misc

I love training my “Catificial” Intelligence/CatGPT🐈 agent, Purrari, using a blend of supervised learning (instruction finetuning) and RL (treats as positive reward). She understood many words in both English and Mandarin and has mastered numerous tricks. Currently, she is advancing her communication skills through pet talking buttons. For more cute cat pics and videos, please visit her instagram, lovingly maintained by her mom.