Sirui Xie

@SiruiXie

Research Scientist @GoogleDeepMind. Prev: PhD @UCLA. BEng @HKUST. Views are my own.

California, USA

Sirui Xie
@SiruiXie
Sep 20, 2024
Happy to share that I have successfully defended my thesis @UCLA earlier this month. I will join @sirbayes’s team @GoogleDeepMind to continue working on (latent-variable) generative models! Thesis: escholarship.org/uc/item/85f7z0…
2
Sirui Xie
@SiruiXie
Jul 23, 2024
Congrats! @StefanoErmon
ICML Conference
@icmlconf
Jul 23, 2024
Congratulations to the best paper award winners
Sirui Xie
@SiruiXie
May 28, 2024
Thanks @_akhaliq for the tweet. EMD matches the teacher diffusion model’s marginal distribution by making the old EM great again. Check out our paper at: arxiv.org/abs/2405.16852
AK
@_akhaliq
May 28, 2024
EM Distillation for One-step Diffusion Models While diffusion models can learn complex distributions, sampling requires a computationally expensive iterative process. Existing distillation methods enable efficient sampling, but have notable limitations, such as
Sirui Xie
@SiruiXie
May 28, 2024
📢 Excited to share EM Distillation (EMD), a maximum likelihood method that distills pretrained diffusion models to one-step generators. EMD gracefully interpolates between mode-seeking and mode-covering KL to better capture the teacher's distribution. arxiv.org/abs/2405.16852
2