Alert button
Picture for Shuangfei Zhai

Shuangfei Zhai

Alert button

Scalable Pre-training of Large Autoregressive Image Models

Jan 16, 2024
Alaaeldin El-Nouby, Michal Klein, Shuangfei Zhai, Miguel Angel Bautista, Alexander Toshev, Vaishaal Shankar, Joshua M Susskind, Armand Joulin

Viaarxiv icon

Matryoshka Diffusion Models

Oct 23, 2023
Jiatao Gu, Shuangfei Zhai, Yizhe Zhang, Josh Susskind, Navdeep Jaitly

Viaarxiv icon

Generative Modeling with Phase Stochastic Bridges

Oct 13, 2023
Tianrong Chen, Jiatao Gu, Laurent Dinh, Evangelos A. Theodorou, Josh Susskind, Shuangfei Zhai

Figure 1 for Generative Modeling with Phase Stochastic Bridges
Figure 2 for Generative Modeling with Phase Stochastic Bridges
Figure 3 for Generative Modeling with Phase Stochastic Bridges
Figure 4 for Generative Modeling with Phase Stochastic Bridges
Viaarxiv icon

BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping

Jun 08, 2023
Jiatao Gu, Shuangfei Zhai, Yizhe Zhang, Lingjie Liu, Josh Susskind

Figure 1 for BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping
Figure 2 for BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping
Figure 3 for BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping
Figure 4 for BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping
Viaarxiv icon

PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model

Jun 05, 2023
Yizhe Zhang, Jiatao Gu, Zhuofeng Wu, Shuangfei Zhai, Josh Susskind, Navdeep Jaitly

Figure 1 for PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model
Figure 2 for PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model
Figure 3 for PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model
Figure 4 for PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model
Viaarxiv icon

AutoFocusFormer: Image Segmentation off the Grid

Apr 24, 2023
Chen Ziwen, Kaushik Patnaik, Shuangfei Zhai, Alvin Wan, Zhile Ren, Alex Schwing, Alex Colburn, Li Fuxin

Figure 1 for AutoFocusFormer: Image Segmentation off the Grid
Figure 2 for AutoFocusFormer: Image Segmentation off the Grid
Figure 3 for AutoFocusFormer: Image Segmentation off the Grid
Figure 4 for AutoFocusFormer: Image Segmentation off the Grid
Viaarxiv icon

Learning Controllable 3D Diffusion Models from Single-view Images

Apr 13, 2023
Jiatao Gu, Qingzhe Gao, Shuangfei Zhai, Baoquan Chen, Lingjie Liu, Josh Susskind

Figure 1 for Learning Controllable 3D Diffusion Models from Single-view Images
Figure 2 for Learning Controllable 3D Diffusion Models from Single-view Images
Figure 3 for Learning Controllable 3D Diffusion Models from Single-view Images
Figure 4 for Learning Controllable 3D Diffusion Models from Single-view Images
Viaarxiv icon

Stabilizing Transformer Training by Preventing Attention Entropy Collapse

Mar 11, 2023
Shuangfei Zhai, Tatiana Likhomanenko, Etai Littwin, Dan Busbridge, Jason Ramapuram, Yizhe Zhang, Jiatao Gu, Josh Susskind

Figure 1 for Stabilizing Transformer Training by Preventing Attention Entropy Collapse
Figure 2 for Stabilizing Transformer Training by Preventing Attention Entropy Collapse
Figure 3 for Stabilizing Transformer Training by Preventing Attention Entropy Collapse
Figure 4 for Stabilizing Transformer Training by Preventing Attention Entropy Collapse
Viaarxiv icon

TRACT: Denoising Diffusion Models with Transitive Closure Time-Distillation

Mar 07, 2023
David Berthelot, Arnaud Autef, Jierui Lin, Dian Ang Yap, Shuangfei Zhai, Siyuan Hu, Daniel Zheng, Walter Talbott, Eric Gu

Figure 1 for TRACT: Denoising Diffusion Models with Transitive Closure Time-Distillation
Figure 2 for TRACT: Denoising Diffusion Models with Transitive Closure Time-Distillation
Figure 3 for TRACT: Denoising Diffusion Models with Transitive Closure Time-Distillation
Figure 4 for TRACT: Denoising Diffusion Models with Transitive Closure Time-Distillation
Viaarxiv icon

f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation

Oct 10, 2022
Jiatao Gu, Shuangfei Zhai, Yizhe Zhang, Miguel Angel Bautista, Josh Susskind

Figure 1 for f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation
Figure 2 for f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation
Figure 3 for f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation
Figure 4 for f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation
Viaarxiv icon