Picture for Xingchao Liu

Xingchao Liu

JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation

Add code
Nov 12, 2024
Viaarxiv icon

Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation

Add code
Oct 17, 2024
Viaarxiv icon

SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow

Add code
Jul 18, 2024
Viaarxiv icon

Consistency Flow Matching: Defining Straight Flows with Velocity Consistency

Add code
Jul 02, 2024
Figure 1 for Consistency Flow Matching: Defining Straight Flows with Velocity Consistency
Figure 2 for Consistency Flow Matching: Defining Straight Flows with Velocity Consistency
Figure 3 for Consistency Flow Matching: Defining Straight Flows with Velocity Consistency
Figure 4 for Consistency Flow Matching: Defining Straight Flows with Velocity Consistency
Viaarxiv icon

Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

Add code
May 14, 2024
Figure 1 for Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
Figure 2 for Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
Figure 3 for Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
Figure 4 for Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
Viaarxiv icon

PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator

Add code
May 13, 2024
Figure 1 for PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
Figure 2 for PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
Figure 3 for PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
Figure 4 for PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
Viaarxiv icon

Language Rectified Flow: Advancing Diffusion Language Generation with Probabilistic Flows

Add code
Mar 25, 2024
Viaarxiv icon

AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies

Add code
Feb 06, 2024
Viaarxiv icon

InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation

Add code
Sep 12, 2023
Figure 1 for InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
Figure 2 for InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
Figure 3 for InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
Figure 4 for InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
Viaarxiv icon

AutoML-GPT: Automatic Machine Learning with GPT

Add code
May 04, 2023
Viaarxiv icon