San Jose, CA

Desai Xie

Advanced
@desaixie

Final year CS Ph.D. candidate at SBU. Intern @adobe-research @ByteDance-Seed. Visual generative models, RL, Distributed Training.

desaixie.github.io/

zeroverse. Official code for NeurIPS 2024 paper LRM-Zero: Training Large Reconstruction Models with Synthesized Data

155

pa_vdm. CVPRW 2025 paper Progressive Autoregressive Video Diffusion Models: https://arxiv.org/abs/2410.08151

88

carve3d. Code for Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning

37

gait. Official code for ICCV 2023 paper: GAIT: Generating Aesthetic Indoor Tours with Deep Reinforcement Learning

12

better-page-preview. An Obsidian plugin that fixes those annoying unwanted preview pop‑ups that appear when you press Cmd shortcut.

1

Learning-from-a-Driving-Simulator. Zero-trial Model-based Imitation Learning with Partial Trajectory

1
6
Apply