Picture for Simian Luo

Simian Luo

Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalability

Add code
Feb 19, 2024
Viaarxiv icon

PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Models

Add code
Jan 10, 2024
Viaarxiv icon

LCM-LoRA: A Universal Stable-Diffusion Acceleration Module

Add code
Nov 09, 2023
Viaarxiv icon

Large Trajectory Models are Scalable Motion Predictors and Planners

Add code
Oct 30, 2023
Viaarxiv icon

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

Add code
Oct 06, 2023
Viaarxiv icon

Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models

Add code
Jun 29, 2023
Figure 1 for Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models
Figure 2 for Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models
Figure 3 for Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models
Figure 4 for Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models
Viaarxiv icon

ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory

Add code
Jun 07, 2023
Viaarxiv icon

Learning Versatile 3D Shape Generation with Improved AR Models

Add code
Mar 26, 2023
Viaarxiv icon

QS-Craft: Learning to Quantize, Scrabble and Craft for Conditional Human Motion Animation

Add code
Mar 22, 2022
Figure 1 for QS-Craft: Learning to Quantize, Scrabble and Craft for Conditional Human Motion Animation
Figure 2 for QS-Craft: Learning to Quantize, Scrabble and Craft for Conditional Human Motion Animation
Figure 3 for QS-Craft: Learning to Quantize, Scrabble and Craft for Conditional Human Motion Animation
Figure 4 for QS-Craft: Learning to Quantize, Scrabble and Craft for Conditional Human Motion Animation
Viaarxiv icon