Name: Desai Xie
Type: User
Company: Stony Brook University
Bio: 4th year CS Ph.D. candidate at SBU. Working on training foundation models in 3D and video without real data, e.g. RLAIF and synthetic data.
Location: San Jose, CA
Blog: https://desaixie.github.io/
Desai Xie's Projects
Code for Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning
DDPO for finetuning diffusion models, implemented in PyTorch with LoRA support
Deep Learning Inferred Multiplex ImmunoFluorescence for IHC Image Quantification (https://deepliif.org) [Nature Machine Intelligence'22, CVPR'22]
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
DrQ-v2: Improved Data-Augmented Reinforcement Learning
Official code for ICCV 2023 paper: GAIT: Generating Aesthetic Indoor Tours with Deep Reinforcement Learning
My first repository in GitHub
Zero-trial Model-based Imitation Learning with Partial Trajectory
A thread-safe memory allocator based on Buddy Memory Allocation Alogirithm
Official code for arxiv paper LRM-Zero: Training Large Reconstruction Models with Synthesized Data